René's URL Explorer Experiment


Title: GitHub - web3-engineer/awesome-harness-engineering: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. · GitHub

Open Graph Title: GitHub - web3-engineer/awesome-harness-engineering: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

X Title: GitHub - web3-engineer/awesome-harness-engineering: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

Description: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. - web3-engineer/awesome-harness-engineering

Open Graph Description: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. - web3-engineer/awesome-harness-engineering

X Description: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. - web3-engineer/awesome-harness-engineering

Opengraph URL: https://github.com/web3-engineer/awesome-harness-engineering

X: @github

direct link

Domain: github.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:e7901f34-8421-6493-7005-3d0ffbb81dab
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-id96AA:35F95A:30C49AB:40CD3DD:6A652F25
html-safe-nonceccda1dcfe28111b3a9a52d3e71b03a4248ecfacfcf3e74e609c683cbe80f0d6d
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiI5NkFBOjM1Rjk1QTozMEM0OUFCOjQwQ0QzREQ6NkE2NTJGMjUiLCJ2aXNpdG9yX2lkIjoiMTc4NTYxMzU5NDAzMjE1NjQ1NCIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9
visitor-hmac9f20b946730361e7d4cc8d4d29e90d95a0ac2f16e4dd09a93b21f0f1562d59d5
hovercard-subject-tagrepository:1292534238
github-keyboard-shortcutsrepository,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location//
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/web3-engineer/awesome-harness-engineering
twitter:imagehttps://opengraph.githubassets.com/e23dc6f77ca54736d534bab93fc4e1eb86c3e5504d7ce24d3c29b617e827fd8a/web3-engineer/awesome-harness-engineering
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/e23dc6f77ca54736d534bab93fc4e1eb86c3e5504d7ce24d3c29b617e827fd8a/web3-engineer/awesome-harness-engineering
og:image:altAwesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. - web3-engineer/awesome-harness-engineering
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
None52c76df668885aaff23b50bdca1fa1ea44ac9c1553e888ebc70ff1e4daa4625b
turbo-cache-controlno-cache
go-importgithub.com/web3-engineer/awesome-harness-engineering git https://github.com/web3-engineer/awesome-harness-engineering.git
octolytics-dimension-user_id101522909
octolytics-dimension-user_loginweb3-engineer
octolytics-dimension-repository_id1292534238
octolytics-dimension-repository_nwoweb3-engineer/awesome-harness-engineering
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forktrue
octolytics-dimension-repository_parent_id1195371847
octolytics-dimension-repository_parent_nwoai-boost/awesome-harness-engineering
octolytics-dimension-repository_network_root_id1195371847
octolytics-dimension-repository_network_root_nwoai-boost/awesome-harness-engineering
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
release309153364422b3c499922d1a2a6404910a58ed8e
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://github.com/web3-engineer/awesome-harness-engineering#start-of-content
https://github.com/
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fweb3-engineer%2Fawesome-harness-engineering
GitHub CopilotWrite better code with AIhttps://github.com/features/copilot
GitHub Copilot appDirect agents from issue to mergehttps://github.com/features/ai/github-app
MCP RegistryNewIntegrate external toolshttps://github.com/mcp
ActionsAutomate any workflowhttps://github.com/features/actions
CodespacesInstant dev environmentshttps://github.com/features/codespaces
IssuesPlan and track workhttps://github.com/features/issues
Code ReviewManage code changeshttps://github.com/features/code-review
Code QualityEnforce quality at mergehttps://github.com/features/code-quality
GitHub Advanced SecurityFind and fix vulnerabilitieshttps://github.com/security/advanced-security
Code securitySecure your code as you buildhttps://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they starthttps://github.com/security/advanced-security/secret-protection
Why GitHubhttps://github.com/why-github
Documentationhttps://docs.github.com
Bloghttps://github.blog
Changeloghttps://github.blog/changelog
Marketplacehttps://github.com/marketplace
View all featureshttps://github.com/features
Enterpriseshttps://github.com/enterprise
Small and medium teamshttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
App Modernizationhttps://github.com/solutions/use-case/app-modernization
DevSecOpshttps://github.com/solutions/use-case/devsecops
DevOpshttps://github.com/solutions/use-case/devops
CI/CDhttps://github.com/solutions/use-case/ci-cd
View all use caseshttps://github.com/solutions/use-case
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
View all industrieshttps://github.com/solutions/industry
View all solutionshttps://github.com/solutions
AIhttps://github.com/resources/articles?topic=ai
Software Developmenthttps://github.com/resources/articles?topic=software-development
DevOpshttps://github.com/resources/articles?topic=devops
Securityhttps://github.com/resources/articles?topic=security
View all topicshttps://github.com/resources/articles
Customer storieshttps://github.com/customer-stories
Events & webinarshttps://github.com/resources/events
Ebooks & reportshttps://github.com/resources/whitepapers
Business insightshttps://github.com/solutions/executive-insights
GitHub Skillshttps://skills.github.com
Documentationhttps://docs.github.com
Customer supporthttps://support.github.com
Community forumhttps://github.com/orgs/community/discussions
Trust centerhttps://github.com/trust-center
Partnershttps://github.com/partners
View all resourceshttps://github.com/resources
GitHub SponsorsFund open source developershttps://github.com/open-source/sponsors
Security Labhttps://securitylab.github.com
Maintainer Communityhttps://maintainers.github.com
Acceleratorhttps://github.com/open-source/accelerator
GitHub Starshttps://stars.github.com
Archive Programhttps://archiveprogram.github.com
Topicshttps://github.com/topics
Trendinghttps://github.com/trending
Collectionshttps://github.com/collections
Enterprise platformAI-powered developer platformhttps://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security featureshttps://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/enterprise/premium-support
Pricinghttps://github.com/pricing
Search syntax tipshttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentationhttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fweb3-engineer%2Fawesome-harness-engineering
Sign up https://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=web3-engineer%2Fawesome-harness-engineering
Reloadhttps://github.com/web3-engineer/awesome-harness-engineering
Reloadhttps://github.com/web3-engineer/awesome-harness-engineering
Reloadhttps://github.com/web3-engineer/awesome-harness-engineering
web3-engineer https://github.com/web3-engineer
awesome-harness-engineeringhttps://github.com/web3-engineer/awesome-harness-engineering
ai-boost/awesome-harness-engineeringhttps://github.com/ai-boost/awesome-harness-engineering
Notifications https://github.com/login?return_to=%2Fweb3-engineer%2Fawesome-harness-engineering
Fork 0 https://github.com/login?return_to=%2Fweb3-engineer%2Fawesome-harness-engineering
Star 0 https://github.com/login?return_to=%2Fweb3-engineer%2Fawesome-harness-engineering
Code https://github.com/web3-engineer/awesome-harness-engineering
Pull requests 0 https://github.com/web3-engineer/awesome-harness-engineering/pulls
Actions https://github.com/web3-engineer/awesome-harness-engineering/actions
Projects https://github.com/web3-engineer/awesome-harness-engineering/projects
Security and quality 0 https://github.com/web3-engineer/awesome-harness-engineering/security
Insights https://github.com/web3-engineer/awesome-harness-engineering/pulse
Code https://github.com/web3-engineer/awesome-harness-engineering
Pull requests https://github.com/web3-engineer/awesome-harness-engineering/pulls
Actions https://github.com/web3-engineer/awesome-harness-engineering/actions
Projects https://github.com/web3-engineer/awesome-harness-engineering/projects
Security and quality https://github.com/web3-engineer/awesome-harness-engineering/security
Insights https://github.com/web3-engineer/awesome-harness-engineering/pulse
https://github.com/web3-engineer/awesome-harness-engineering
Brancheshttps://github.com/web3-engineer/awesome-harness-engineering/branches
Tagshttps://github.com/web3-engineer/awesome-harness-engineering/tags
https://github.com/web3-engineer/awesome-harness-engineering/branches
https://github.com/web3-engineer/awesome-harness-engineering/tags
178 Commitshttps://github.com/web3-engineer/awesome-harness-engineering/commits/main/
https://github.com/web3-engineer/awesome-harness-engineering/commits/main/
assetshttps://github.com/web3-engineer/awesome-harness-engineering/tree/main/assets
assetshttps://github.com/web3-engineer/awesome-harness-engineering/tree/main/assets
templateshttps://github.com/web3-engineer/awesome-harness-engineering/tree/main/templates
templateshttps://github.com/web3-engineer/awesome-harness-engineering/tree/main/templates
.gitignorehttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/.gitignore
.gitignorehttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/.gitignore
AGENTS.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/AGENTS.md
AGENTS.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/AGENTS.md
CLAUDE.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/CLAUDE.md
CLAUDE.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/CLAUDE.md
CONTRIBUTING.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/CONTRIBUTING.md
CONTRIBUTING.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/CONTRIBUTING.md
LICENSEhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/LICENSE
LICENSEhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/LICENSE
README.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/README.md
README.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/README.md
verify_urls.pyhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/verify_urls.py
verify_urls.pyhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/verify_urls.py
READMEhttps://github.com/web3-engineer/awesome-harness-engineering
Contributinghttps://github.com/web3-engineer/awesome-harness-engineering
Licensehttps://github.com/web3-engineer/awesome-harness-engineering
https://github.com/web3-engineer/awesome-harness-engineering/blob/main/assets/banner.jpg
https://github.com/web3-engineer/awesome-harness-engineering#awesome-harness-engineering
https://awesome.re
https://github.com/web3-engineer/awesome-harness-engineering/blob/main/LICENSE
https://github.com/ai-boost/awesome-harness-engineering/stargazers
https://github.com/ai-boost/awesome-harness-engineering/network/members
https://github.com/ai-boost/awesome-harness-engineering/commits/main
https://linux.do
Deutschhttps://zdoc.app/de/ai-boost/awesome-harness-engineering
Englishhttps://zdoc.app/en/ai-boost/awesome-harness-engineering
Españolhttps://zdoc.app/es/ai-boost/awesome-harness-engineering
Françaishttps://zdoc.app/fr/ai-boost/awesome-harness-engineering
日本語https://zdoc.app/ja/ai-boost/awesome-harness-engineering
한국어https://zdoc.app/ko/ai-boost/awesome-harness-engineering
Portuguêshttps://zdoc.app/pt/ai-boost/awesome-harness-engineering
Русскийhttps://zdoc.app/ru/ai-boost/awesome-harness-engineering
中文https://zdoc.app/zh/ai-boost/awesome-harness-engineering
https://github.com/web3-engineer/awesome-harness-engineering#contents
📐 Foundationshttps://github.com/web3-engineer/awesome-harness-engineering#foundations
🧩 Design Primitiveshttps://github.com/web3-engineer/awesome-harness-engineering#design-primitives
🔄 Agent Loophttps://github.com/web3-engineer/awesome-harness-engineering#agent-loop
🗺️ Planning & Task Decompositionhttps://github.com/web3-engineer/awesome-harness-engineering#planning--task-decomposition
📦 Context Delivery & Compactionhttps://github.com/web3-engineer/awesome-harness-engineering#context-delivery--compaction
🔧 Tool Designhttps://github.com/web3-engineer/awesome-harness-engineering#tool-design
🔌 Skills & MCPhttps://github.com/web3-engineer/awesome-harness-engineering#skills--mcp
🛡️ Permissions & Authorizationhttps://github.com/web3-engineer/awesome-harness-engineering#permissions--authorization
🧠 Memory & Statehttps://github.com/web3-engineer/awesome-harness-engineering#memory--state
⚙️ Task Runners & Orchestrationhttps://github.com/web3-engineer/awesome-harness-engineering#task-runners--orchestration
✔️ Verification & CI Integrationhttps://github.com/web3-engineer/awesome-harness-engineering#verification--ci-integration
👁️ Observability & Tracinghttps://github.com/web3-engineer/awesome-harness-engineering#observability--tracing
🐛 Debugging & Developer Experiencehttps://github.com/web3-engineer/awesome-harness-engineering#debugging--developer-experience
🧑‍💼 Human-in-the-Loophttps://github.com/web3-engineer/awesome-harness-engineering#human-in-the-loop
🔍 Reference Implementationshttps://github.com/web3-engineer/awesome-harness-engineering#reference-implementations
🎓 Tutorials & Educationalhttps://github.com/web3-engineer/awesome-harness-engineering#tutorials--educational
🏭 Generators & Meta-Harnesseshttps://github.com/web3-engineer/awesome-harness-engineering#generators--meta-harnesses
🧪 Demo Harnesseshttps://github.com/web3-engineer/awesome-harness-engineering#demo-harnesses
🗂️ Adjacent Collectionshttps://github.com/web3-engineer/awesome-harness-engineering#adjacent-collections
🔒 Security, Sandbox & Permissionshttps://github.com/web3-engineer/awesome-harness-engineering#security-sandbox--permissions
✅ Evals & Verificationhttps://github.com/web3-engineer/awesome-harness-engineering#evals--verification
📋 Templateshttps://github.com/web3-engineer/awesome-harness-engineering#templates
📚 Related Awesome Listshttps://github.com/web3-engineer/awesome-harness-engineering#related-awesome-lists
🤝 Contributinghttps://github.com/web3-engineer/awesome-harness-engineering#contributing
https://github.com/web3-engineer/awesome-harness-engineering#foundations
Harness Engineeringhttps://openai.com/index/harness-engineering/
Unrolling the Codex Agent Loophttps://openai.com/index/unrolling-the-codex-agent-loop/
Run Long-Horizon Tasks with Codexhttps://developers.openai.com/blog/run-long-horizon-tasks-with-codex/
Building Effective Agentshttps://www.anthropic.com/research/building-effective-agents
Harness Design for Long-Running Application Developmenthttps://www.anthropic.com/engineering/harness-design-long-running-apps
Writing Effective Tools for Agentshttps://www.anthropic.com/engineering/writing-effective-tools-for-agents
Beyond Permission Promptshttps://www.anthropic.com/engineering/beyond-permission-prompts
Demystifying Evals for AI Agentshttps://www.anthropic.com/engineering/demystifying-evals-for-ai-agents
What is an AI Agent?https://www.ibm.com/think/topics/ai-agents
Agent Development Kit: Making it easy to build multi-agent applicationshttps://developers.googleblog.com/en/agent-development-kit-easy-to-build-multi-agent-applications/
Harness Engineeringhttps://martinfowler.com/articles/exploring-gen-ai/harness-engineering.html
The Anatomy of an Agent Harnesshttps://blog.langchain.com/the-anatomy-of-an-agent-harness/
Building AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learnedhttps://arxiv.org/abs/2603.05344
Natural-Language Agent Harnesseshttps://arxiv.org/abs/2603.25723
Ranking Engineer Agent (REA): Meta's Autonomous AI System for Ads Rankinghttps://engineering.fb.com/2026/03/17/developer-tools/ranking-engineer-agent-rea-autonomous-ai-system-accelerating-meta-ads-ranking-innovation/
Supercharge Your AI Agents: The New ADK Integrations Ecosystemhttps://developers.googleblog.com/en/supercharge-your-ai-agents-adk-integrations-ecosystem/
2026 Agentic Coding Trends Reporthttps://resources.anthropic.com/hubfs/2026%20Agentic%20Coding%20Trends%20Report.pdf?hsLang=en
How We Build Azure SRE Agent with Agentic Workflowshttps://techcommunity.microsoft.com/blog/appsonazureblog/how-we-build-azure-sre-agent-with-agentic-workflows/4508753
Context Engineering for Reliable AI Agents: Lessons from Building Azure SRE Agenthttps://techcommunity.microsoft.com/blog/appsonazureblog/context-engineering-lessons-from-building-azure-sre-agent/4481200/
Harness Engineering: Structured Workflows for AI-Assisted Developmenthttps://developers.redhat.com/articles/2026/04/07/harness-engineering-structured-workflows-ai-assisted-development
Harness engineering for coding agent usershttps://martinfowler.com/articles/harness-engineering.html
A Practical Guide to Building AI Agentshttps://openai.com/business/guides-and-resources/a-practical-guide-to-building-ai-agents/
An Update on Recent Claude Code Quality Reportshttps://www.anthropic.com/engineering/april-23-postmortem
Code as Agent Harnesshttps://arxiv.org/abs/2605.18747
Harness Engineering: How to Build Reliable AI Agents by Engineering the System, Not the Modelhttps://www.deepset.ai/blog/harness-engineering
What makes a harness a harness: necessary and sufficient conditions for an agent harnesshttps://arxiv.org/abs/2606.10106
Architectural Design Decisions in AI Agent Harnesseshttps://arxiv.org/abs/2604.18071
RUCAIBox/awesome-agent-harnesshttps://github.com/RUCAIBox/awesome-agent-harness
https://camo.githubusercontent.com/52a58c182e58fdb98edaf37428b4caedd525defb2d1e59035b3704c79415ae33/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5255434149426f782f617765736f6d652d6167656e742d6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#design-primitives
https://github.com/web3-engineer/awesome-harness-engineering#agent-loop
ReAct: Synergizing Reasoning and Acting in Language Modelshttps://arxiv.org/abs/2210.03629
Unrolling the Codex Agent Loophttps://openai.com/index/unrolling-the-codex-agent-loop/
LangGraph — Low Level Conceptshttps://langchain-ai.github.io/langgraph/concepts/low_level/
Unlocking the Codex Harness: How We Built the App Serverhttps://openai.com/index/unlocking-the-codex-harness/
Hooks – Codexhttps://developers.openai.com/codex/hooks
Extended Thinking — Claude API Docshttps://docs.anthropic.com/en/docs/build-with-claude/extended-thinking
Getting started with loopshttps://claude.com/blog/getting-started-with-loops
Improving Deep Agents with Harness Engineeringhttps://blog.langchain.com/improving-deep-agents-with-harness-engineering/
Life-Harnesshttps://github.com/Tianshi-Xu/Life-Harness
https://camo.githubusercontent.com/4500dafff8793b1b3b05c4ead6a154e94aa0d9ed4d13087413159bbbe87fa10f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5469616e7368692d58752f4c6966652d4861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
How Middleware Lets You Customize Your Agent Harnesshttps://blog.langchain.com/how-middleware-lets-you-customize-your-agent-harness/
Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semanticshttps://arxiv.org/abs/2603.01209
Real-Time Deadlines Reveal Temporal Awareness Failures in LLM Strategic Reasoninghttps://arxiv.org/abs/2601.13206
A Scheduler-Theoretic Framework for LLM Agent Executionhttps://arxiv.org/abs/2604.11378
Confucius Code Agent (CCA)https://github.com/facebookresearch/cca-swebench
The Design Space of Today's and Future AI Agent Systemshttps://arxiv.org/abs/2604.14228
deepclaudehttps://github.com/aattaran/deepclaude
https://camo.githubusercontent.com/e181a3035f1713910ac034eb919905d8e0b022752bf6faded2f12b985d68d7f9/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616174746172616e2f64656570636c617564653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
The Coding Harness Behind GitHub Copilot in VS Codehttps://code.visualstudio.com/blogs/2026/05/15/agent-harnesses-github-copilot-vscode
statewrighthttps://github.com/statewright/statewright
https://camo.githubusercontent.com/c7a989e4b252e1664c8dba9d4e82b7a6a1b7db102c00fa0af72cc5eb85711d82/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f73746174657772696768742f73746174657772696768743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Introducing dynamic workflows in Claude Codehttps://claude.com/blog/introducing-dynamic-workflows-in-claude-code
AgentSPEXhttps://github.com/ScaleML/AgentSPEX
https://camo.githubusercontent.com/4ad90c851704b9b421e78d5506667e02e5b19f03fc6826292d40798c5751616a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5363616c654d4c2f4167656e74535045583f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#planning--task-decomposition
Run Long-Horizon Tasks with Codexhttps://developers.openai.com/blog/run-long-horizon-tasks-with-codex/
Harness Design for Long-Running Application Developmenthttps://www.anthropic.com/engineering/harness-design-long-running-apps
Plan-and-Execute Agentshttps://blog.langchain.com/plan-and-execute-agents/
microsoft/TaskWeaverhttps://github.com/microsoft/TaskWeaver
https://camo.githubusercontent.com/9eac2feb01f76a64aea460789938d2d5abcb6f2d63e2bc99d2effa11bfc0b35a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f5461736b5765617665723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
LATS: Language Agent Tree Searchhttps://arxiv.org/abs/2310.04406
Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineeringhttps://arxiv.org/abs/2602.01465
Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskshttps://arxiv.org/abs/2503.09572
Choosing the Right Multi-Agent Architecturehttps://blog.langchain.com/choosing-the-right-multi-agent-architecture/
Multi-Agent Workflows Often Fail. Here's How to Engineer Ones That Don't.https://github.blog/ai-and-ml/generative-ai/multi-agent-workflows-often-fail-heres-how-to-engineer-ones-that-dont/
Effective Harnesses for Long-Running Agentshttps://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents
Task-Adaptive Multi-Agent Orchestration (AdaptOrch)https://arxiv.org/abs/2602.16873
Task-Decoupled Planning for Long-Horizon Agents (TDP)https://arxiv.org/abs/2601.07577
https://github.com/web3-engineer/awesome-harness-engineering#context-delivery--compaction
Harness Engineeringhttps://openai.com/index/harness-engineering/
Effective Context Engineering for AI Agentshttps://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
Compaction — Claude API Docshttps://platform.claude.com/docs/en/build-with-claude/compaction
LLMLinguahttps://github.com/microsoft/LLMLingua
https://camo.githubusercontent.com/fce6cd9b8eed056b04b2f7573ba8eef85819a9820b5599b918936c333d416ae7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f4c4c4d4c696e6775613f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Prompt Caching — Claude API Docshttps://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
Autonomous Context Compressionhttps://blog.langchain.com/autonomous-context-compression/
Active Context Compression: Autonomous Memory Management in LLM Agentshttps://arxiv.org/abs/2601.07190
context-modehttps://github.com/mksglu/context-mode
https://camo.githubusercontent.com/6ec967e0690f67ec525b3708edf607b44dd2ed323b2f28914b6fb5363ae65d19/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6b73676c752f636f6e746578742d6d6f64653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Making Agent-Friendly Pages with Content Negotiationhttps://vercel.com/blog/making-agent-friendly-pages-with-content-negotiation
A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaceshttps://arxiv.org/abs/2602.03442
LLM Readiness Harness: Evaluation, Observability, and CI Gates for LLM/RAG Applicationshttps://arxiv.org/abs/2603.27355
ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Contexthttps://arxiv.org/abs/2604.01599
Claude Code Compaction: How Context Compression Workshttps://okhlopkov.com/claude-code-compaction-explained/
Token Saviorhttps://github.com/Mibayy/token-savior
https://camo.githubusercontent.com/efa7e315dd76560aa4131358885c6a5cab5c6b89c8dd13a39fb97226601b0070/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4d69626179792f746f6b656e2d736176696f723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Trellishttps://github.com/mindfold-ai/Trellis
https://camo.githubusercontent.com/813175fa5cb39ac0c3a0cdef55807f8199bff4b1f4a3c1cd9a8418c9880b794f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d696e64666f6c642d61692f5472656c6c69733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
OpenVikinghttps://github.com/volcengine/OpenViking
https://camo.githubusercontent.com/9b2282f98cf13c8635e66313236d5636db81cc452d3c4ca141383b1b0dd966a6/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f766f6c63656e67696e652f4f70656e56696b696e673f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
DESIGN.mdhttps://github.com/google-labs-code/design.md
https://camo.githubusercontent.com/3e42b265d14d251a153e82368810fddc483eee18ca0a9e6fe9ee0f1e7136f5d5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f676f6f676c652d6c6162732d636f64652f64657369676e2e6d643f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
codebase-memory-mcphttps://github.com/DeusData/codebase-memory-mcp
https://camo.githubusercontent.com/b1aa49752894bbf2b8ce0101b7815268898da0bdae7f9dbc7f9349655abe2cf2/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f44657573446174612f636f6465626173652d6d656d6f72792d6d63703f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Miragehttps://github.com/strukto-ai/mirage
https://camo.githubusercontent.com/e40bea82afbbbdac26641909f783b8d57ed959b39e9823f7117e0c32d0d54c9e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f737472756b746f2d61692f6d69726167653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
dirachttps://github.com/dirac-run/dirac
https://camo.githubusercontent.com/03e2ab4035e29d19a6b853f90d573e0ec5fce620b90cbde7cd4b8c6a865287fa/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f64697261632d72756e2f64697261633f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
MinishLab/semblehttps://github.com/MinishLab/semble
https://camo.githubusercontent.com/b8ed3bc1ae04d84470977f3eddf8f89dbf584a4865cd9f446f6518ec4af821e7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4d696e6973684c61622f73656d626c653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
harness-experimentalhttps://github.com/hoangnb24/harness-experimental
https://camo.githubusercontent.com/a7fdc12d24088188b9a0d75b2983d9426071ba122a71028a77a3089b6e97b1b1/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f686f616e676e6232342f6861726e6573732d6578706572696d656e74616c3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
headroomhttps://github.com/chopratejas/headroom
https://camo.githubusercontent.com/8c822fdce8254c03912d4b2a73545d9e31a186200b047e6d5032cf4d43e728bf/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f63686f70726174656a61732f68656164726f6f6d3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Context7https://github.com/upstash/context7
https://camo.githubusercontent.com/cef75c3dc95bbd789bf9461a1e77f13b06d92263aa1f33d2d38f99fb9a40292c/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f757073746173682f636f6e74657874373f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Context Pruning for Coding Agents via Multi-Rubric Latent Reasoninghttps://arxiv.org/abs/2605.15315
https://github.com/web3-engineer/awesome-harness-engineering#tool-design
Writing Effective Tools for Agentshttps://www.anthropic.com/engineering/writing-effective-tools-for-agents
Tool Use — Claude API Docshttps://platform.claude.com/docs/en/agents-and-tools/tool-use/overview
Function Calling — OpenAI Docshttps://platform.openai.com/docs/guides/function-calling
Tool Annotations as Risk Vocabularyhttps://blog.modelcontextprotocol.io/posts/2026-03-16-tool-annotations/
outlineshttps://github.com/dottxt-ai/outlines
https://camo.githubusercontent.com/972fed3626cb54942702078b5e3211cd42b592ea77f2c7fec27887f4169be231/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f646f747478742d61692f6f75746c696e65733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
instructorhttps://python.useinstructor.com/
https://camo.githubusercontent.com/987a1f663d9f7ebadfde56e96a6952df1dc2744d2e3ac1c0eaab126751a16eb5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f696e7374727563746f722d61692f696e7374727563746f723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
SkillTester: Benchmarking Utility and Security of Agent Skillshttps://arxiv.org/abs/2603.28815
AutoHarness: Improving LLM Agents by Automatically Synthesizing a Code Harnesshttps://arxiv.org/abs/2603.03329
Scaling Parallel Tool Calling for Efficient Deep Researchhttps://arxiv.org/abs/2602.07359
EigentSearch-Q+https://arxiv.org/abs/2604.07927
TopoCurate: Modeling Interaction Topology for Tool-Use Agent Traininghttps://arxiv.org/abs/2603.01714
Design Patterns for Deploying AI Agents with Model Context Protocolhttps://arxiv.org/abs/2603.13417
tui-usehttps://github.com/onesuper/tui-use
https://camo.githubusercontent.com/1e89763cd28a048b5c14baf6e787a4033f2689a51b1c719a60a801e2da20301d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6f6e6573757065722f7475692d7573653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
CLI-Anythinghttps://github.com/HKUDS/CLI-Anything
https://camo.githubusercontent.com/563b3bc402e721f89e5493c93982a3df4ad294ef1844d65fbd61a2444f3ba6a7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f484b5544532f434c492d416e797468696e673f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
zerolanghttps://github.com/vercel-labs/zerolang
https://camo.githubusercontent.com/2e11f97d1a485fa1ed1bf6e060c18ee30ca1778f47f73b8ba36102280863af36/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f76657263656c2d6c6162732f7a65726f6c616e673f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#skills--mcp
Model Context Protocolhttps://modelcontextprotocol.io/introduction
modelcontextprotocol/servershttps://github.com/modelcontextprotocol/servers
https://camo.githubusercontent.com/15ad837a6c812b6d6aaf0655ea17891f797b5d364c03a9e06924c230998f87fb/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6f64656c636f6e7465787470726f746f636f6c2f736572766572733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
microsoft/playwright-mcphttps://github.com/microsoft/playwright-mcp
https://camo.githubusercontent.com/3a8b2c2a919dc1506b8ed96e5472ff1ed506248dd910292e6662e995a3efef24/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f706c61797772696768742d6d63703f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Chrome DevTools MCPhttps://github.com/ChromeDevTools/chrome-devtools-mcp
https://camo.githubusercontent.com/5dbcefdb57e50519c9a2bef0e1454fb6e96ce7f66bb7e91658f1860d47f520da/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4368726f6d65446576546f6f6c732f6368726f6d652d646576746f6f6c732d6d63703f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
agent-devicehttps://github.com/callstackincubator/agent-device
https://camo.githubusercontent.com/9f682c6c52b2c0e6204dc304b45c775a2a2394496e47d96925bf578c60a8dafb/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f63616c6c737461636b696e63756261746f722f6167656e742d6465766963653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
A2A Protocolhttps://github.com/a2aproject/A2A
https://camo.githubusercontent.com/621c9ccc220fdba26c55de01069b8daf228690d6ac7a18c351c47b222f8bb269/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f61326170726f6a6563742f4132413f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Announcing the Agentic Resource Discovery specificationhttps://developers.googleblog.com/announcing-the-agentic-resource-discovery-specification/
MCP Inspectorhttps://github.com/modelcontextprotocol/inspector
https://camo.githubusercontent.com/60e0a7b71ceee9047772501de1fc318b4c0770eb1ba1ab50cbcbbd9d37cd5f2e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6f64656c636f6e7465787470726f746f636f6c2f696e73706563746f723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Shell + Skills + Compaction: Tips for Long-Running Agentshttps://developers.openai.com/blog/skills-shell-tips
Composiohttps://github.com/ComposioHQ/composio
https://camo.githubusercontent.com/464c9f4f48693f6737fdfded814a04a4e8ebf5bdcd2f8be4d1bf1b9b28a8352d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f436f6d706f73696f48512f636f6d706f73696f3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
MCP Streamable HTTP Transporthttps://modelcontextprotocol.io/specification/2025-11-25/basic/transports
The 2026 MCP Roadmaphttps://blog.modelcontextprotocol.io/posts/2026-mcp-roadmap/
The 2026-07-28 MCP Specification Release Candidatehttps://blog.modelcontextprotocol.io/posts/2026-07-28-release-candidate/
Developer's Guide to AI Agent Protocolshttps://developers.googleblog.com/en/developers-guide-to-ai-agent-protocols/
AG-UIhttps://github.com/ag-ui-protocol/ag-ui
https://camo.githubusercontent.com/f868b196989431b3c07f8812407ccf22e2d9410424b51eef2a990e046e8d2b8a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f61672d75692d70726f746f636f6c2f61672d75693f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Code Execution with MCP: Building More Efficient Agentshttps://www.anthropic.com/engineering/code-execution-with-mcp
Microsoft Skills Frameworkhttps://github.com/microsoft/skills
https://camo.githubusercontent.com/5b51b5cbd712478f31fbedf3ae317b161c6e32174b8e8bbc83962d3f64adc7d8/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f736b696c6c733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
SkillNet & SkillsBench: Infrastructure for AI Agent Skills at Scalehttps://github.com/skillmatic-ai/awesome-agent-skills
https://camo.githubusercontent.com/ca1b2c61001f647921ae82dca9ecf1b285f4f11c9c4856a914d850c5aee2ec59/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f736b696c6c6d617469632d61692f617765736f6d652d6167656e742d736b696c6c733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
AWS Bedrock AgentCore with WebRTC Supporthttps://aws.amazon.com/about-aws/whats-new/2026/03/amazon-bedrock-webrtc/
Hermes Agent: Unified Streaming for Real-Time Agent Workflowshttps://juliangoldie.com/hermes-agent-unified-streaming/
Google Developers: Closing the Knowledge Gap with Agent Skillshttps://developers.googleblog.com/closing-the-knowledge-gap-with-agent-skills/
What's New with GitHub Copilot Coding Agenthttps://github.blog/ai-and-ml/github-copilot/whats-new-with-github-copilot-coding-agent/
Announcing Official MCP Support for Google Serviceshttps://cloud.google.com/blog/products/ai-machine-learning/announcing-official-mcp-support-for-google-services
Dataverse Skills: Your Coding Agent Now Speaks Dataversehttps://devblogs.microsoft.com/powerplatform/dataverse-skills-your-coding-agent-now-speaks-dataverse
Agent Toolkit for AWShttps://github.com/aws/agent-toolkit-for-aws
https://camo.githubusercontent.com/c0680bbfc8a4e7ed18aa98ec31ea73e7ac409f1ae12d87ab882ec8504652e1c1/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6177732f6167656e742d746f6f6c6b69742d666f722d6177733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
agentic-stackhttps://github.com/codejunkie99/agentic-stack
https://camo.githubusercontent.com/3654a836355d321f3ff817389aa913264cf2327c86718a82829978fff60b928b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f636f64656a756e6b696539392f6167656e7469632d737461636b3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
mcp-agenthttps://github.com/lastmile-ai/mcp-agent
https://camo.githubusercontent.com/d88940054b29c46b123e560879b09b4c3a6c9b45f28922695c72cf4a9c4f6eb4/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6c6173746d696c652d61692f6d63702d6167656e743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
vurb.tshttps://github.com/vinkius-labs/vurb.ts
https://camo.githubusercontent.com/b2356f76f6ffe975efde150fe8e624aac0a94f31d881b5d17fbee1e6b85381c2/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f76696e6b6975732d6c6162732f767572622e74733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
SkillOpthttps://github.com/microsoft/SkillOpt
https://camo.githubusercontent.com/7faa2d2baf48b900f3ff67344bfa8687f33a7e6b2722e715ea22344c384ee963/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f536b696c6c4f70743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
superpowershttps://github.com/obra/superpowers
https://camo.githubusercontent.com/5c8a306b3471d0d66d92054b3fc92b99745f95bd6f10a45c8b975a4b8e79dc02/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6f6272612f7375706572706f776572733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Antigravity Awesome Skillshttps://github.com/sickn33/antigravity-awesome-skills
https://camo.githubusercontent.com/7670b915f00348108ff788068f9207fca10628c8a3770b46a8f94d9a35e9cd08/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7369636b6e33332f616e7469677261766974792d617765736f6d652d736b696c6c733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
agentgatewayhttps://github.com/agentgateway/agentgateway
https://camo.githubusercontent.com/11b43125af88af194fe9444d016959fb976e672ffb4e68b9782a73ad9b8d4eed/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6167656e74676174657761792f6167656e74676174657761793f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
AIP: A Graph Representation for Learning and Governing Agent Skillshttps://arxiv.org/abs/2606.04781
https://github.com/web3-engineer/awesome-harness-engineering#permissions--authorization
Beyond Permission Promptshttps://www.anthropic.com/engineering/beyond-permission-prompts
OWASP LLM06:2025 — Excessive Agencyhttps://genai.owasp.org/llmrisk/llm062025-excessive-agency/
GitHub Enterprise — Governing Agentshttps://wellarchitected.github.com/library/governance/recommendations/governing-agents/
Claude Code Auto Mode: A Safer Way to Skip Permissionshttps://www.anthropic.com/engineering/claude-code-auto-mode
Claude Agent SDK — Configure Permissionshttps://platform.claude.com/docs/en/agent-sdk/permissions
Two Different Types of Agent Authorizationhttps://blog.langchain.com/two-different-types-of-agent-authorization/
Authorization and Governance for AI Agents: Runtime Authorization Beyond Identity at Scalehttps://techcommunity.microsoft.com/blog/microsoft-security-blog/authorization-and-governance-for-ai-agents-runtime-authorization-beyond-identity/4509161
IETF draft-klrc-aiagent-auth: AI Agent Authentication and Authorizationhttps://datatracker.ietf.org/doc/draft-klrc-aiagent-auth/
Nango: Pre-Built Authentication for AI Agentshttps://nango.dev
https://camo.githubusercontent.com/957a8cf8667f08b2eda3c49c8fcb4b5d73d01743c101bdca9c9a808a9427374d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4e616e676f48512f6e616e676f3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Securityhttps://arxiv.org/abs/2601.18491
Open Agent Passport (OAP): Deterministic Pre-Action Authorization for Autonomous AI Agentshttps://arxiv.org/abs/2603.20953
nahhttps://github.com/manuelschipper/nah
https://camo.githubusercontent.com/018316dd8fc0c368ca4bc67db1f8246ae8e34117705b40c8759daba4a13d0273/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d616e75656c73636869707065722f6e61683f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#memory--state
Building Effective Agentshttps://www.anthropic.com/research/building-effective-agents
Letta (MemGPT)https://github.com/letta-ai/letta
agent loop redesign posthttps://www.letta.com/blog/letta-v1-agent
https://camo.githubusercontent.com/0eaa1349c8b560d75b3ca3b2b1b84a1d7ddae1371bf2a7cdf3cbd685dc625ea3/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6c657474612d61692f6c657474613f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
mem0https://github.com/mem0ai/mem0
https://camo.githubusercontent.com/b963e7c8b678e4347d803314e3522f64330a417f6fa332a444b9dedbf4aacf32/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d656d3061692f6d656d303f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Stashhttps://github.com/alash3al/stash
https://camo.githubusercontent.com/613ede5c2bfb1fe6303e8b05025e31e57ed53391f671ebb585712571906b8b30/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616c61736833616c2f73746173683f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
TencentDB-Agent-Memoryhttps://github.com/Tencent/TencentDB-Agent-Memory
https://camo.githubusercontent.com/8fa609ba81714b1ac86e3fa71a8ef6e505364a7db87c18f64dbd3f06f47d99a5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f54656e63656e742f54656e63656e7444422d4167656e742d4d656d6f72793f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Zephttps://github.com/getzep/zep
https://camo.githubusercontent.com/194f9239424ce0b4fb2aaaeb61591b1cc91a3e87f2b3fa4107505845c5fd10ac/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6765747a65702f7a65703f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
engramhttps://github.com/Gentleman-Programming/engram
https://camo.githubusercontent.com/9ea3e799e873dcaf31a2aecf1ad50a99d36430ed1e3af4f22d09102e0a09cdc1/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f47656e746c656d616e2d50726f6772616d6d696e672f656e6772616d3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
MemPalacehttps://github.com/MemPalace/mempalace
https://camo.githubusercontent.com/4a50436af58399e1a68b5149696c050ad971c0e4527fbbec01a36bce3e00a495/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4d656d50616c6163652f6d656d70616c6163653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
agentmemoryhttps://github.com/rohitg00/agentmemory
https://camo.githubusercontent.com/3ffae1a0e6095d04622eef94423bcb17d915e1086186f9520aa26d39cedca17e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f726f6869746730302f6167656e746d656d6f72793f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
claude-memory-compilerhttps://github.com/coleam00/claude-memory-compiler
https://camo.githubusercontent.com/7c03a591dbfbb6472eebf349f0f0e5c87d16875d50bcb4ba320bc76bf2612d7b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f636f6c65616d30302f636c617564652d6d656d6f72792d636f6d70696c65723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
How We Built Agent Builder's Memory Systemhttps://blog.langchain.com/how-we-built-agent-builders-memory-system/
Building an Agentic Memory System for GitHub Copilothttps://github.blog/ai-and-ml/github-copilot/building-an-agentic-memory-system-for-github-copilot/
MemArchitect: A Policy-Driven Memory Governance Layerhttps://arxiv.org/abs/2603.18330
Codified Context: Infrastructure for AI Agents in a Complex Codebasehttps://arxiv.org/abs/2602.20478
Facts as First Class Objects: Knowledge Objects for Persistent LLM Memoryhttps://arxiv.org/abs/2603.17781
Recoverability Has a Law: The ERR Measure for Tool-Augmented Agentshttps://arxiv.org/abs/2601.22352
MAGMA: Multi-Graph Agentic Memory Architecturehttps://arxiv.org/abs/2601.03236
GAAMA: Graph Augmented Associative Memory for Agentshttps://arxiv.org/abs/2603.27910
Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectureshttps://arxiv.org/abs/2603.17244
Continual learning for AI agentshttps://blog.langchain.com/continual-learning-for-ai-agents/
cogneehttps://github.com/topoteretes/cognee
https://camo.githubusercontent.com/f99465218379e968ebb12150c0d673df0d4bc17106c7859d2d7d8de2d70dcda5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f746f706f746572657465732f636f676e65653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Hindsighthttps://github.com/vectorize-io/hindsight
https://camo.githubusercontent.com/864c8e91fea70e32cf67bb72bfe65a4c8050e923d3ca238a7b0de6d8a75ca1c7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f766563746f72697a652d696f2f68696e6473696768743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agentshttps://arxiv.org/abs/2604.10352
MAGE: Memory as Agent-Guided Explorationhttps://arxiv.org/abs/2606.06090
https://github.com/web3-engineer/awesome-harness-engineering#task-runners--orchestration
Harness Engineeringhttps://openai.com/index/harness-engineering/
Building a C Compiler with a Team of Parallel Claudeshttps://www.anthropic.com/engineering/building-c-compiler
LiteLLMhttps://github.com/BerriAI/litellm
https://camo.githubusercontent.com/c22798b27ba1e00fbf5ec10b4bb8f37903b5cfa27c37d74668d90dc1e1ee4dbc/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f426572726941492f6c6974656c6c6d3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
LangGraphhttps://github.com/langchain-ai/langgraph
https://camo.githubusercontent.com/c6c2bd861e48586569c1b6e63388caeed9191b7168839bd117a48197fe67bc78/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6c616e67636861696e2d61692f6c616e6767726170683f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
OpenAI Agents SDKhttps://github.com/openai/openai-agents-python
https://camo.githubusercontent.com/9ceac5fd149cd031fd7037b1825ee383a3e5d6bf185964c3466f6fb07a7a8f47/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6f70656e61692f6f70656e61692d6167656e74732d707974686f6e3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Codex SDKhttps://developers.openai.com/codex/sdk
Google ADKhttps://github.com/google/adk-python
https://camo.githubusercontent.com/bd6ea28682caeea211b1c45d1bc6c3c8eaed5353555f08c69a1343e93bc13530/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f676f6f676c652f61646b2d707974686f6e3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
strands-agents/harness-sdkhttps://github.com/strands-agents/harness-sdk
https://camo.githubusercontent.com/c0b8de8c44fcf35ab7287ec7606c35ae5ab092e7e1f093badee1ef3d72e89021/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f737472616e64732d6167656e74732f6861726e6573732d73646b3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Build Long-running AI agents that pause, resume, and never lose context with ADKhttps://developers.googleblog.com/build-long-running-ai-agents-that-pause-resume-and-never-lose-context-with-adk/
Build Cross-Language Multi-Agent Team with Google's Agent Development Kit and A2Ahttps://developers.googleblog.com/en/build-cross-language-multi-agent-team-with-google-agent-development-kit-and-a2a/
AutoGenhttps://github.com/microsoft/autogen
https://camo.githubusercontent.com/9329acf785571ad02f0cca3985daa85b69433fbf47eb899b85abb01c3f192069/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f6175746f67656e3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
CrewAIhttps://github.com/crewAIInc/crewAI
https://camo.githubusercontent.com/1bfaeff36a0d7fb6b8223e336d307242bf29ea7973dd38401b894a4824154b6e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f637265774149496e632f6372657741493f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Pydantic AI v2https://github.com/pydantic/pydantic-ai
https://camo.githubusercontent.com/f115011f5149702f7ecfa15f5851db0266bd05d21e2b884f07e39ccce8de32a9/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f707964616e7469632f707964616e7469632d61693f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
LangGraph 2.0 Releasehttps://github.com/langchain-ai/langgraph
https://camo.githubusercontent.com/c6c2bd861e48586569c1b6e63388caeed9191b7168839bd117a48197fe67bc78/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6c616e67636861696e2d61692f6c616e6767726170683f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
OmniRoute: Multi-Provider LLM Gatewayhttps://github.com/diegosouzapw/OmniRoute
https://camo.githubusercontent.com/7965a34be85a46cbae79acfd9511e34943878b1e23791c8f8793d8292a2b226b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f646965676f736f757a6170772f4f6d6e69526f7574653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
OpenSquillahttps://github.com/opensquilla/opensquilla
https://camo.githubusercontent.com/ecfc2c0b87dc2aa75a93edb7c0f9a0251c9c5a32a837677a3b7571ac4c76556e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6f70656e737175696c6c612f6f70656e737175696c6c613f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Scaling Managed Agents: Decoupling the Brain from the Handshttps://www.anthropic.com/engineering/managed-agents
Microsoft Agent Framework at BUILD 2026: Agent Harness, Hosted Agents, CodeAct, and morehttps://devblogs.microsoft.com/agent-framework/microsoft-agent-framework-at-build-2026-announce/
Microsoft Agent Framework 1.0https://devblogs.microsoft.com/agent-framework/microsoft-agent-framework-version-1-0/
Conductorhttps://github.com/microsoft/conductor
https://camo.githubusercontent.com/6733b535aae9387794a5c0a2f5eb89edc0ade19dc743e5be37635490535ed88f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f636f6e647563746f723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
AgentScope Runtimehttps://github.com/agentscope-ai/agentscope-runtime
https://camo.githubusercontent.com/7393b853ac96b2016e21d628f95d1aa765a2a206add2655ff3867e8299797f0b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6167656e7473636f70652d61692f6167656e7473636f70652d72756e74696d653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Orchestrating Ambient Agents with Temporalhttps://temporal.io/blog/orchestrating-ambient-agents-with-temporal
Vercel AI SDKhttps://github.com/vercel/ai
https://camo.githubusercontent.com/f501f8707151f98e74a190c625901f664dd722aca535c000090cd2538b10b6ac/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f76657263656c2f61693f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Mastrahttps://github.com/mastra-ai/mastra
https://camo.githubusercontent.com/f8c56d103cf857d216d7b575dc0976f06adb42db60115aabc99c5836eca67988/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d61737472612d61692f6d61737472613f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
open-multi-agenthttps://github.com/JackChen-me/open-multi-agent
https://camo.githubusercontent.com/31a706d45b59fdc70c6ae671ccffd1dab5b907b6bfc9abfb14c9c4dbca894e96/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4a61636b4368656e2d6d652f6f70656e2d6d756c74692d6167656e743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
The next evolution of the Agents SDKhttps://openai.com/index/the-next-evolution-of-the-agents-sdk/
Symphonyhttps://github.com/openai/symphony
https://camo.githubusercontent.com/7ae0ece422740675861b762114a098c6c32882eb972d3086cf5930596e4c0ab5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6f70656e61692f73796d70686f6e793f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Harmonisthttps://github.com/GammaLabTechnologies/harmonist
https://camo.githubusercontent.com/cacdca9cca2900b29f69e06daf197fcdc436f8d31c34af3d0115adb0d62c4505/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f47616d6d614c6162546563686e6f6c6f676965732f6861726d6f6e6973743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Hivehttps://github.com/aden-hive/hive
https://camo.githubusercontent.com/939ed6b14c15969a792e11cb4eae5e88af99655328d11652be5e52936971a01c/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6164656e2d686976652f686976653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
thClawshttps://github.com/thClaws/thClaws
https://camo.githubusercontent.com/e833e3d2ffa8dbb2611805f01ca8d243c280e0992cdac635debdd552858caf3f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7468436c6177732f7468436c6177733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
sandcastlehttps://github.com/mattpocock/sandcastle
https://camo.githubusercontent.com/9a45464c7421bc44eb76908c0812261d4bf0d7c52c31ce795254d3e0476248e1/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d617474706f636f636b2f73616e64636173746c653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
bernsteinhttps://github.com/sipyourdrink-ltd/bernstein
https://camo.githubusercontent.com/b7bdd5468626594c8d1391622b734b0435874b199574ea71ce92c6550e8ff8dc/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f736970796f75726472696e6b2d6c74642f6265726e737465696e3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#verification--ci-integration
Demystifying Evals for AI Agentshttps://www.anthropic.com/engineering/demystifying-evals-for-ai-agents
promptfoohttps://github.com/promptfoo/promptfoo
https://camo.githubusercontent.com/250d4a29e2b879c0a5072147377f970511574fd8258f2619eff7df9928f9510d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f70726f6d7074666f6f2f70726f6d7074666f6f3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
AgentBenchhttps://github.com/THUDM/AgentBench
https://camo.githubusercontent.com/de1a21b5c852dc2df90cb2573e1e1182c4c2207aefa8819c0626e3b2309ba9b8/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f544855444d2f4167656e7442656e63683f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Testing Agent Skills Systematically with Evalshttps://developers.openai.com/blog/eval-skills
Agent Evaluation Readiness Checklisthttps://blog.langchain.com/agent-evaluation-readiness-checklist/
Evaluating Skillshttps://blog.langchain.com/evaluating-skills/
AgentAssay: Token-Efficient Regression Testing for Non-Deterministic Agent Workflowshttps://arxiv.org/abs/2603.02601
Agentic Harness for Real-World Compilers: A Case Study in Specialized Tool Designhttps://arxiv.org/abs/2603.20075
Eval-Driven Development: Build and Evaluate Reliable AI Agentshttps://developers.redhat.com/articles/2026/03/23/eval-driven-development-build-evaluate-ai-agents
Agent Evaluation Framework 2026: Metrics, Rubrics & Benchmarkshttps://galileo.ai/blog/agent-evaluation-framework-metrics-rubrics-benchmarks
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systemshttps://arxiv.org/abs/2602.17753
sentruxhttps://github.com/sentrux/sentrux
https://camo.githubusercontent.com/8897a83b85865f452ab0a82b36396d1a8690399709bc580d451a02bca40bf770/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f73656e747275782f73656e747275783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Driving the Agent Quality Flywheel from Your Coding Agenthttps://developers.googleblog.com/en/driving-the-agent-quality-flywheel-from-your-coding-agent/
https://github.com/web3-engineer/awesome-harness-engineering#observability--tracing
OpenLLMetryhttps://github.com/traceloop/openllmetry
https://camo.githubusercontent.com/0dea75e3017d1ecc29186a6ff81d30bc198d9f68af307faef03aab3dee508d56/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f74726163656c6f6f702f6f70656e6c6c6d657472793f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Arize Phoenixhttps://github.com/Arize-ai/phoenix
https://camo.githubusercontent.com/93df64ed028e2d3ead571c30f1bde725f8cf97bf1f8ec5723fddffb1d5f4960b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4172697a652d61692f70686f656e69783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Langfusehttps://github.com/langfuse/langfuse
https://camo.githubusercontent.com/9d14e50c9f86a59320d988c08a0b050b8d277539f739fd9640a79502fcff45d5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6c616e67667573652f6c616e67667573653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Weights & Biases Weavehttps://github.com/wandb/weave
https://camo.githubusercontent.com/79813e5ffc3774c90966b7fd0c3edc849c3f9b12016bad3c4f5eb942e9215240/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f77616e64622f77656176653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
OTel GenAI Semantic Conventionshttps://opentelemetry.io/docs/specs/semconv/gen-ai/
Pydantic Logfirehttps://github.com/pydantic/logfire
https://camo.githubusercontent.com/05a26fa370068ffa9a940b29fb86b065e08b82c1e55a11c025c5475921f27541/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f707964616e7469632f6c6f67666972653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Heliconehttps://github.com/Helicone/helicone
https://camo.githubusercontent.com/1810e4753b6010a317232850b8cb64e412ebde5ad65f85b8920b82302d330d55/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f48656c69636f6e652f68656c69636f6e653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
OpenObserve: Unified Observability for LLM Agentshttps://openobserve.ai/
https://camo.githubusercontent.com/1bad170bf5c98caef57462314b4bd73d68c4cce500a772ce95522c249b1549c9/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6f70656e6f6273657276652f6f70656e6f6273657276653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Braintrusthttps://www.braintrust.dev
Building Observable AI Agents: Temporal Now Integrates with Braintrusthttps://temporal.io/blog/building-observable-ai-agents-temporal-now-integrates-with-braintrust
Introducing BigQuery Agent Analyticshttps://cloud.google.com/blog/products/data-analytics/introducing-bigquery-agent-analytics/
Distributed Tracing for Agentic Workflows with OpenTelemetryhttps://developers.redhat.com/articles/2026/04/06/distributed-tracing-agentic-workflows-opentelemetry
Red-Teaming Anthropic's Internal Agent Monitoring Systems — METRhttps://metr.org/blog/2026-03-25-red-teaming-anthropic-agent-monitoring/
Future AGIhttps://github.com/future-agi/future-agi
https://camo.githubusercontent.com/d5470ad8ddb0c27a2134b74c49500e970de491c0c1dd1231e87e051ad5f7acea/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6675747572652d6167692f6675747572652d6167693f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#debugging--developer-experience
AgentOpshttps://github.com/AgentOps-AI/agentops
https://camo.githubusercontent.com/268fcedd9595c20fcfa7593f7d6dfc3c7efa12010eda103611de45d4720693f9/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4167656e744f70732d41492f6167656e746f70733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
claude-devtoolshttps://github.com/matt1398/claude-devtools
https://camo.githubusercontent.com/24356099f19e0bd4332c87c3df3f73a5be809b7c0b45d08f9a9d00da31b5ef7f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d617474313339382f636c617564652d646576746f6f6c733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Syncause/debug-skillhttps://github.com/Syncause/debug-skill
https://camo.githubusercontent.com/ac8818705941906300c622d2f6e10489ac78b9686b9504af289adbadf949e7f5/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f53796e63617573652f64656275672d736b696c6c3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
AgentTrace: Causal Graph Tracing for Root Cause Analysis in Multi-Agent Systemshttps://arxiv.org/abs/2603.14688
TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Codehttps://arxiv.org/abs/2602.06875
AgentRx: Systematic Debugging for AI Agentshttps://www.microsoft.com/en-us/research/blog/systematic-debugging-for-ai-agents-introducing-the-agentrx-framework/
https://camo.githubusercontent.com/f1356d7702dbf0b7942394c2e652373fd25d62700a9015f01d86755538296e47/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f4167656e7452783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Debugging Deep Agents with LangSmithhttps://blog.langchain.com/debugging-deep-agents-with-langsmith/
Where LLM Agents Fail and How They Can Learn From Failures (AgentDebug)https://arxiv.org/abs/2509.25370
AgentPrismhttps://github.com/evilmartians/agent-prism
https://camo.githubusercontent.com/3ad0acdba71f50776648f57fa797e178d4fd4a747767da682b9072ec0575d3a9/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6576696c6d61727469616e732f6167656e742d707269736d3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Characterizing Faults in Agentic AIhttps://arxiv.org/abs/2603.06847
More Visibility into Copilot Coding Agent Sessionshttps://github.blog/changelog/2026-03-19-more-visibility-into-copilot-coding-agent-sessions/
AgentStepper: Interactive Debugging of Software Development Agentshttps://arxiv.org/abs/2602.06593
https://github.com/web3-engineer/awesome-harness-engineering#human-in-the-loop
aws-samples/sample-human-in-the-loop-patternshttps://github.com/aws-samples/sample-human-in-the-loop-patterns
https://camo.githubusercontent.com/d5633de7a6a727e3f915562ba15bdb9724de70ffdaf170fc3e654cac1b033819/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6177732d73616d706c65732f73616d706c652d68756d616e2d696e2d7468652d6c6f6f702d7061747465726e733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Dify Human-in-the-Loop Nodehttps://github.com/langgenius/dify/discussions/32245
HITL Protocolhttps://github.com/rotorstar/hitl-protocol
LangGraph — Human-in-the-Loop Conceptshttps://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/
AutoGen — Human-in-the-Loophttps://microsoft.github.io/autogen/0.2/docs/tutorial/human-in-the-loop/
Claude Agent SDK — Handle Approvals and User Inputhttps://platform.claude.com/docs/en/agent-sdk/user-input
HiL-Bench: Do Agents Know When to Ask for Help?https://arxiv.org/abs/2604.09408
Human Judgment in the Agent Improvement Loophttps://blog.langchain.com/human-judgment-in-the-agent-improvement-loop/
Humans and Agents in Software Engineering Loopshttps://martinfowler.com/articles/exploring-gen-ai/humans-and-agents.html
Measuring AI Agent Autonomy in Practicehttps://www.anthropic.com/news/measuring-agent-autonomy
AutoResearchClaw HITL Co-Pilothttps://github.com/aiming-lab/AutoResearchClaw
https://github.com/web3-engineer/awesome-harness-engineering#reference-implementations
https://github.com/web3-engineer/awesome-harness-engineering#tutorials--educational
Learn Harness Engineeringhttps://walkinglabs.github.io/learn-harness-engineering/en/
https://camo.githubusercontent.com/7481a454608412aa0b1671c0c2e8c38f10a20f4ca11c8c8c6d56967faed72929/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f77616c6b696e676c6162732f6c6561726e2d6861726e6573732d656e67696e656572696e673f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
ML6 x AISO Agent Workshophttps://github.com/ml6team/AISO-workshop
https://camo.githubusercontent.com/8208d95ef0bdf9696b9cd54285373d6b4501b348e6db6c3e2197e5641871f274/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6c367465616d2f4149534f2d776f726b73686f703f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
mastra-ai/workshop-mastracodehttps://github.com/mastra-ai/workshop-mastracode
https://camo.githubusercontent.com/117f3300c1dfb72c759b9c2483d2e8b8a3277e6507bf7d8bf9901e69eb8fea12/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d61737472612d61692f776f726b73686f702d6d6173747261636f64653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Building Governed AI Agentshttps://developers.openai.com/cookbook/examples/partners/agentic_governance_guide/agentic_governance_cookbook
anthropics/claude-cookbookshttps://github.com/anthropics/claude-cookbooks
https://camo.githubusercontent.com/4db51df54c4b6917a49e095915fcbbe0bdafcb0c0548ce573a04c96be84d5beb/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616e7468726f706963732f636c617564652d636f6f6b626f6f6b733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
huggingface/smolagentshttps://github.com/huggingface/smolagents
https://camo.githubusercontent.com/d7385055e2be7a795972ec10e67756329d053bf6b67cc6ce1828ec1d94f9a87a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f68756767696e67666163652f736d6f6c6167656e74733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
rasbt/mini-coding-agenthttps://github.com/rasbt/mini-coding-agent
https://camo.githubusercontent.com/be82f73c67809c0455422fb72f9f8833ccb4ecfbfd3e7f8d966c9c7008d256cc/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f72617362742f6d696e692d636f64696e672d6167656e743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
shareAI-lab/learn-claude-codehttps://github.com/shareAI-lab/learn-claude-code
https://camo.githubusercontent.com/0f7e8eb13209d6054daca32269534068c574791d98673e4a873ed5b361ae0a95/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f736861726541492d6c61622f6c6561726e2d636c617564652d636f64653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
AutoJunjie/awesome-agent-harnesshttps://github.com/AutoJunjie/awesome-agent-harness
https://camo.githubusercontent.com/4cf22b2414c7ef9484411eb6f310bdeb750ceaee5c3d7c8c721aa286bd34a3c8/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4175746f4a756e6a69652f617765736f6d652d6167656e742d6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Skill Issue: Harness Engineering for Coding Agentshttps://www.humanlayer.dev/blog/skill-issue-harness-engineering-for-coding-agents
How to orchestrate agents using mission controlhttps://github.blog/ai-and-ml/github-copilot/how-to-orchestrate-agents-using-mission-control/
awslabs/agentcore-sampleshttps://github.com/awslabs/agentcore-samples
Engineering Trustworthy Multi-Agent Systemshttps://www.ieeesmc.org/cai-2026/tutorial-3-engineering-trustworthy-multi-agent-systems/
https://camo.githubusercontent.com/08e74280ca71dee774a6e2945343e4baf1da5d69b5d6de7a94b19e255403a7d0/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6177736c6162732f6167656e74636f72652d73616d706c65733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
agents-best-practiceshttps://github.com/DenisSergeevitch/agents-best-practices
https://camo.githubusercontent.com/2e7f4be4fba4d9e2b22fb439b7832f7fef1ad3e82d277ecb28b2557ad8644e4f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f44656e697353657267656576697463682f6167656e74732d626573742d7072616374696365733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#generators--meta-harnesses
everything-claude-codehttps://github.com/affaan-m/everything-claude-code
https://camo.githubusercontent.com/b21dbd02587c503377b9b04364e8e3dbbc946e90b91317ad692d8402424c701b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f61666661616e2d6d2f65766572797468696e672d636c617564652d636f64653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Claude Agent SDKhttps://platform.claude.com/docs/en/agent-sdk/overview
https://camo.githubusercontent.com/d26403e266d7a493fbda9076969cdcd8f4ecf5bf7559da142171aad34094ecff/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616e7468726f706963732f636c617564652d6167656e742d73646b2d707974686f6e3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
revfactory/harnesshttps://github.com/revfactory/harness
https://camo.githubusercontent.com/423bef4f15d624ef17a776709693a46ac8081f95536a0898cb3d479f863f01ae/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f726576666163746f72792f6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
raphaelchristi/harness-evolverhttps://github.com/raphaelchristi/harness-evolver
https://camo.githubusercontent.com/4f36110ffeaf963729702570b3bc16be7e3b1473cdf26c128932bb04ca429e9b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7261706861656c636872697374692f6861726e6573732d65766f6c7665723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
neosigmaai/auto-harnesshttps://github.com/neosigmaai/auto-harness
https://camo.githubusercontent.com/d09ec5d984814c41a626a8cef30a99c808413744557aa50dd0179d4d12cf73c4/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6e656f7369676d6161692f6175746f2d6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
agentic-harness-engineeringhttps://github.com/china-qijizhifeng/agentic-harness-engineering
https://camo.githubusercontent.com/fc599643607caeab805c2fa2685b9c11308036dd8340fe511ac4c5f8faf50c05/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6368696e612d71696a697a686966656e672f6167656e7469632d6861726e6573732d656e67696e656572696e673f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Meta-Harness: End-to-End Optimization of Model Harnesseshttps://arxiv.org/abs/2603.28052
Self-Harness: Harnesses That Improve Themselveshttps://arxiv.org/abs/2606.09498
HyperAgents: Self-Improving AI Systemshttps://pooya.blog/blog/hyperagents-self-improving-ai-meta-research-2026/
AutoAgenthttps://github.com/kevinrgu/autoagent
https://camo.githubusercontent.com/fd8a3bfff238a85f02b5b373455d4eaf8f9edc62e7eb1e018851e48e95a0894f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6b6576696e7267752f6175746f6167656e743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
metaharnesshttps://github.com/SuperagenticAI/metaharness
https://camo.githubusercontent.com/9f468607e52ba1e7bc4a70c7366dc2f05ecf5ae5e519c655e2693166818b1a22/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f53757065726167656e74696341492f6d6574616861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
meta-agenthttps://github.com/canvas-org/meta-agent
stanford-iris-lab/meta-harnesshttps://github.com/stanford-iris-lab/meta-harness
https://camo.githubusercontent.com/5b29299a3e963eea1bd0687477d1d00bb63b4ccc990f54df23b760491714c78f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7374616e666f72642d697269732d6c61622f6d6574612d6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
autocontexthttps://github.com/greyhaven-ai/autocontext
https://camo.githubusercontent.com/1be6ba43f3d9314d4da6b012baf04ac7597637547149da3016c792101014b8e4/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f67726579686176656e2d61692f6175746f636f6e746578743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
retro-harnesshttps://github.com/wbopan/retro-harness
https://camo.githubusercontent.com/f7bf438103e446ecde00d1bcb8b4d3b304c432cf1329a187c08b5c8233f39b31/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f77626f70616e2f726574726f2d6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Continual Harnesshttps://github.com/sethkarten/continual-harness
https://camo.githubusercontent.com/abcd3cfcb0f0287fc8b203c6206618cb62169f8623889e73a668e1d5bf4aa1bc/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f736574686b617274656e2f636f6e74696e75616c2d6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Omnigenthttps://github.com/omnigent-ai/omnigent
https://camo.githubusercontent.com/1751239ec93c915b40ab8db954a402eeaf2ec5c4e3a4f205b8298e4b8c1ae8fd/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6f6d6e6967656e742d61692f6f6d6e6967656e743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#demo-harnesses
Anthropic Computer Use Demohttps://github.com/anthropics/anthropic-quickstarts/tree/main/computer-use-demo
https://camo.githubusercontent.com/23eb337732618bf31b3f98cb4333ac3eb7ca406685a7090028e65f33f7c426d1/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616e7468726f706963732f616e7468726f7069632d717569636b7374617274733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
coleam00/your-claude-engineerhttps://github.com/coleam00/your-claude-engineer
https://camo.githubusercontent.com/7bad1af6da64c9d0e188586083464e7bde15990bd037c8a9c8a2657cf41ac26f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f636f6c65616d30302f796f75722d636c617564652d656e67696e6565723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
OpenHandshttps://github.com/OpenHands/OpenHands
https://camo.githubusercontent.com/dfa2ee33ac621a01f906279694b2f33d78e489df9f6a08d14b63c11409e1798a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4f70656e48616e64732f4f70656e48616e64733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Goosehttps://github.com/aaif-goose/goose
https://camo.githubusercontent.com/b5b158f3ba2d836cdf57118c90799430a850e7cc34eaa049c3dc19df2d0cf109/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616169662d676f6f73652f676f6f73653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
browser-usehttps://github.com/browser-use/browser-use
https://camo.githubusercontent.com/64e11ab65bad3298313d70ee5b936caa000897217a2b55ae1a147ca4d95e962a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f62726f777365722d7573652f62726f777365722d7573653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
browser-harnesshttps://github.com/browser-use/browser-harness
https://camo.githubusercontent.com/b2b23462ebc470a36009ef9c629c3da42ae20a0543ced9c7ac03ca3f3916fd22/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f62726f777365722d7573652f62726f777365722d6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
buxhttps://github.com/browser-use/bux
https://camo.githubusercontent.com/8ea6e191653c0e06355bd1b7e0f63984c67eb4a6c9caff6ca1edcfaf40475cea/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f62726f777365722d7573652f6275783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
SWE-agenthttps://github.com/SWE-agent/SWE-agent
https://camo.githubusercontent.com/bec81440251cd25fa4326e0b35f57266950fe1784936f4f1d027c8246cdf3955/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5357452d6167656e742f5357452d6167656e743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Aiderhttps://github.com/Aider-AI/aider
https://camo.githubusercontent.com/7757424afbc228a20b23127096b08b3d82536d023c7690e5e2276d566b480666/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f41696465722d41492f61696465723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Open SWE: An Open-Source Framework for Internal Coding Agentshttps://blog.langchain.com/open-swe-an-open-source-framework-for-internal-coding-agents/
Live-SWE-agent: Autonomous Software Agent with Self-Evolving Harnesshttps://arxiv.org/html/2511.13646v3
Pipecat: Python Framework for Real-Time Voice Agent Pipelineshttps://github.com/pipecat-ai/pipecat
https://camo.githubusercontent.com/6494d3134827b9ff9d6992b7e1f0bce1a21a3151a3b1d7d3591423215781f059/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f706970656361742d61692f706970656361743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
The Virtual Biotech: Multi-Agent AI Framework for Drug Discoveryhttps://www.biorxiv.org/content/10.64898/2026.02.23.707551v1
Building NVIDIA Nemotron 3 Agents for Reasoning, Multimodal RAG, Voice, and Safetyhttps://developer.nvidia.com/blog/building-nvidia-nemotron-3-agents-for-reasoning-multimodal-rag-voice-and-safety/
AIO Sandboxhttps://github.com/agent-infra/sandbox
https://camo.githubusercontent.com/416f12c5bccfd2b1a48365cf09149dfa8776a5382710518b0b5a39ef949da4e7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6167656e742d696e6672612f73616e64626f783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
GitHub Agentic Workflowshttps://github.blog/changelog/2026-02-13-github-agentic-workflows-are-now-in-technical-preview/
langchain-ai/deepagentshttps://github.com/langchain-ai/deepagents
https://camo.githubusercontent.com/bb3cec7517184b1d12827de3c79c8d92507813941a97534a922bb5b0319ce2cb/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6c616e67636861696e2d61692f646565706167656e74733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
HKUDS/OpenHarnesshttps://github.com/HKUDS/OpenHarness
https://camo.githubusercontent.com/53f55359f4c97e748a222c8d17a79ba8ac1e564f1bfb30862e5b9cac5c84571c/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f484b5544532f4f70656e4861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
OpenCodehttps://github.com/anomalyco/opencode
https://camo.githubusercontent.com/72d4e9f5cb2f27f4ca8d589771a9995ece3e15ec60d2440372b5ada9d8702682/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616e6f6d616c79636f2f6f70656e636f64653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Squadhttps://github.com/bradygaster/squad
https://camo.githubusercontent.com/a77ca1c2d413e9d5c7d649a0c4110f6c08345372162967cf24ac726eb706cf91/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f62726164796761737465722f73717561643f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
cuahttps://github.com/trycua/cua
https://camo.githubusercontent.com/9158f4c0f790848f9b05c8d142e4e78a310cc78c70a23ef22551aba2bbd1f7b3/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7472796375612f6375613f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
ClawGUIhttps://github.com/ZJU-REAL/ClawGUI
https://camo.githubusercontent.com/d5a105f36a4404a641ba363e30c526e8e0219af9c7e39a13523f99c0d1eebbf4/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5a4a552d5245414c2f436c61774755493f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
AOHPhttps://github.com/aohp-os/aohp
https://camo.githubusercontent.com/09af8ec0a648fbcaca235c86d18d858d90fc6190db30b5a2802afa21adcba077/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616f68702d6f732f616f68703f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
desloppifyhttps://github.com/peteromallet/desloppify
https://camo.githubusercontent.com/dd011f5829583b687bd314d3264948e0898acddc268ea30879234d838bf6f8c3/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f70657465726f6d616c6c65742f6465736c6f70706966793f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
DeepSeek-Reasonixhttps://github.com/esengine/DeepSeek-Reasonix
https://camo.githubusercontent.com/581ab255f3b788f96c83e3a7e5049bf9f1532bdf5256821e9d53484722f30115/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6573656e67696e652f446565705365656b2d526561736f6e69783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
SmallCodehttps://github.com/Doorman11991/smallcode
https://camo.githubusercontent.com/30a3337f5ca0c763845566bd46417845ea74be73ee7f5760a801a6d6d7ecb0bf/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f446f6f726d616e31313939312f736d616c6c636f64653f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
alibaba/open-code-reviewhttps://github.com/alibaba/open-code-review
https://camo.githubusercontent.com/81c3e53551d85164f14f6a503946b38aea843b4755537a3cd03d87a5941fc409/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616c69626162612f6f70656e2d636f64652d7265766965773f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
DeerFlowhttps://github.com/bytedance/deer-flow
https://camo.githubusercontent.com/19caa42c46bc68350e486a1f83c8c96ac67c10efac33f05dca31c2a933c51602/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6279746564616e63652f646565722d666c6f773f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Pihttps://github.com/earendil-works/pi
https://camo.githubusercontent.com/781eb361b3d98b7b0d7b54199a4c261bf68e9e4789965744cb8d71fea55a1af7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f656172656e64696c2d776f726b732f70693f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#adjacent-collections
EvoMap/awesome-agent-evolutionhttps://github.com/EvoMap/awesome-agent-evolution
https://camo.githubusercontent.com/03f2b0079ec043a3abecbc57cf89a90fc1c1e80a4d0ebea3ed981c277937cb39/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f45766f4d61702f617765736f6d652d6167656e742d65766f6c7574696f6e3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Picrew/awesome-agent-harnesshttps://github.com/Picrew/awesome-agent-harness
https://camo.githubusercontent.com/17b7788167131f2c9c5cabb665e731283bc5b5ac628edb372d5f786a59136cc8/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5069637265772f617765736f6d652d6167656e742d6861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
jiji262/awesome-harness-engineeringhttps://github.com/jiji262/awesome-harness-engineering
https://camo.githubusercontent.com/64474911cb2e17f15bb6d8ed27d4c35eba5347d8649814527cab1c3078d565cc/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6a696a693236322f617765736f6d652d6861726e6573732d656e67696e656572696e673f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
VoltAgent/awesome-ai-agent-papershttps://github.com/VoltAgent/awesome-ai-agent-papers
https://camo.githubusercontent.com/93a569ee86c7b0ef1a98448ec7c3e86f549129dffdc2d1c1359edc8c12db931a/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f566f6c744167656e742f617765736f6d652d61692d6167656e742d7061706572733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
bradAGI/awesome-cli-coding-agentshttps://github.com/bradAGI/awesome-cli-coding-agents
danielrosehill/AI-Harnesseshttps://github.com/danielrosehill/AI-Harnesses
https://camo.githubusercontent.com/3000966a161b53d9f476cc79acdbe8fd21a06e76a79bf78d9940ffb7e9a3ce95/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f627261644147492f617765736f6d652d636c692d636f64696e672d6167656e74733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#security-sandbox--permissions
Beyond Permission Promptshttps://www.anthropic.com/engineering/beyond-permission-prompts
How we contain Claude across productshttps://www.anthropic.com/engineering/how-we-contain-claude
Model Context Protocol — Authorizationhttps://modelcontextprotocol.io/specification/2025-11-05/basic/authorization
AI Harness Scorecardhttps://github.com/anthropics/ai-harness-scorecard
E2Bhttps://github.com/e2b-dev/E2B
https://camo.githubusercontent.com/419e078e63994bd6fea43aa2e057abe5ae2d5e114b9af4fc68a40dfe0ce47d89/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6532622d6465762f4532423f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
tldrsec/prompt-injection-defenseshttps://github.com/tldrsec/prompt-injection-defenses
https://camo.githubusercontent.com/a85a2bccaff41645dcd4c136abc8d388a42c903f55ba62dec24074ead959c0b3/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f746c64727365632f70726f6d70742d696e6a656374696f6e2d646566656e7365733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Prompt Injection — Simon Willison's Serieshttps://simonwillison.net/series/prompt-injection/
OWASP LLM01:2025 — Prompt Injectionhttps://genai.owasp.org/llmrisk/llm01-prompt-injection/
StackOne Defenderhttps://github.com/stackoneHQ/defender
https://camo.githubusercontent.com/f2c34014cb081403b91e59be5535a7e6e9f2e3658e09e4ea373025a6a82b81b3/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f737461636b6f6e6548512f646566656e6465723f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Daytonahttps://github.com/daytonaio/daytona
https://camo.githubusercontent.com/cc0393fd0bcc7b27db6007acc09262959a433e50e72800f7183d7b42d3b84034/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f646179746f6e61696f2f646179746f6e613f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
NeMo Guardrailshttps://github.com/NVIDIA-NeMo/Guardrails
https://camo.githubusercontent.com/51ce49eb9fdb6fc6f1e9b5a9b272bc51c7fe01289e82ad3767e650e43129cf3d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4e56494449412d4e654d6f2f47756172647261696c733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
LangSmith Sandboxes: Secure Code Execution for Agentshttps://blog.langchain.com/introducing-langsmith-sandboxes-secure-code-execution-for-agents/
Implementing a Secure Sandbox for Local Agentshttps://cursor.com/blog/agent-sandboxing
Practical Security Guidance for Sandboxing Agentic Workflowshttps://developer.nvidia.com/blog/practical-security-guidance-for-sandboxing-agentic-workflows-and-managing-execution-risk/
Under the Hood: Security Architecture of GitHub Agentic Workflowshttps://github.blog/ai-and-ml/generative-ai/under-the-hood-security-architecture-of-github-agentic-workflows/
Community-Powered Security with AI: An Open Source Framework for Security Researchhttps://github.blog/security/community-powered-security-with-ai-an-open-source-framework-for-security-research/
AnonymAI: Integrating Differential Privacy with LLM Agentshttps://www.mdpi.com/1999-5903/18/1/41
Fault Tolerance Patterns: OpenClaw Journey Six—Core Retry Loop and Seven-Layer Fault-Tolerancehttps://tonylixu.medium.com/openclaw-journey-six-core-retry-loop-and-seven-layer-fault-tolerance-7a9ce03147e2
deepsechttps://github.com/vercel-labs/deepsec
https://camo.githubusercontent.com/fab9258b29aa50bf95575c2052a711dd20df84e28e849d5ccd01debafd46e485/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f76657263656c2d6c6162732f646565707365633f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Sandbox Agents | OpenAI API Docshttps://developers.openai.com/api/docs/guides/agents/sandboxes
NVIDIA OpenShellhttps://github.com/NVIDIA/OpenShell
https://camo.githubusercontent.com/98b0beeba1d0c4df571ca129a50fe36db0de5eb06fdd526ba6a115621232e822/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f4e56494449412f4f70656e5368656c6c3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
IronClawhttps://github.com/nearai/ironclaw
https://camo.githubusercontent.com/d1cc3f903d741e18131dc1cce8743693303ffa975927048f3abfab717c94d57b/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6e65617261692f69726f6e636c61773f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Microsoft Agent Governance Toolkithttps://github.com/microsoft/agent-governance-toolkit
https://camo.githubusercontent.com/2c9b9877dca12c873a38ef459d6ad618aa752dd6ec669d12bc265def28253893/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f6167656e742d676f7665726e616e63652d746f6f6c6b69743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
mcpguard-dynamichttps://github.com/facebook/mcpguard-dynamic
https://camo.githubusercontent.com/fbdff9f0098bdce768ec2372abff9a941ae8c014edd039f19cef64087a3f0ec0/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f66616365626f6f6b2f6d637067756172642d64796e616d69633f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Grimlock: Guarding High-Agency Systems with eBPF and Attested Channelshttps://arxiv.org/abs/2605.27488
Cloudflare Dynamic Workershttps://blog.cloudflare.com/dynamic-workers/
Kubernetes Agent Sandboxhttps://github.com/kubernetes-sigs/agent-sandbox
https://camo.githubusercontent.com/771d6296d4affbde0e397be22bb6bfc42c7162de465bb558264fe4c227dcb71e/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6b756265726e657465732d736967732f6167656e742d73616e64626f783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Alibaba OpenSandboxhttps://github.com/alibaba/OpenSandbox
https://camo.githubusercontent.com/7cd5cae998b4cf856f27193ea9130304ca04df8b4ab9bba9e6367f9dcdf79ba7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f616c69626162612f4f70656e53616e64626f783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
CubeSandboxhttps://github.com/TencentCloud/CubeSandbox
https://camo.githubusercontent.com/2ea469dcdc1a89e3285dc150d12bed30d3f4234f898f3537f77cfd9d581a8bf0/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f54656e63656e74436c6f75642f4375626553616e64626f783f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
zeroboothttps://github.com/zerobootdev/zeroboot
https://camo.githubusercontent.com/8e604460c41298c9ec42a944521da000214cb21ba5aa7a5840f5d03c17b548ca/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7a65726f626f6f746465762f7a65726f626f6f743f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
forkdhttps://github.com/deeplethe/forkd
https://camo.githubusercontent.com/fa898ce180ec911f6d2298fc56ef0022099e92ba8ee016fc0fedfd93f8585dff/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f646565706c657468652f666f726b643f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
The Attack and Defense Landscape of Agentic AI: A Comprehensive Surveyhttps://arxiv.org/abs/2603.11088
Trustworthy agents in practicehttps://www.anthropic.com/research/trustworthy-agents
RAMPARThttps://github.com/microsoft/RAMPART
https://camo.githubusercontent.com/7482f620499f6804c73cf0896eb9c73de439415392823e9ab677b4f7100435d2/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f52414d504152543f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
aiming-lab/AutoHarnesshttps://github.com/aiming-lab/AutoHarness
https://camo.githubusercontent.com/14f0a5ead9da4a7b57bd59be10678df5ffcd353909042272aee93527421ede76/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f61696d696e672d6c61622f4175746f4861726e6573733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#evals--verification
Demystifying Evals for AI Agentshttps://www.anthropic.com/engineering/demystifying-evals-for-ai-agents
DeepEvalhttps://github.com/confident-ai/deepeval
https://camo.githubusercontent.com/80ae7c8b24bc7d5dfdba1623d50219a1ac5eec884fa299739631f1f515df912c/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f636f6e666964656e742d61692f646565706576616c3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Claw-Evalhttps://github.com/claw-eval/claw-eval
https://camo.githubusercontent.com/c381e17feb9966472bff87fba8beb3d8fc6c1a215ee61f4fd84dd4ff6b397e46/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f636c61772d6576616c2f636c61772d6576616c3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
SWE-benchhttps://www.swebench.com
Inspect AIhttps://github.com/UKGovernmentBEIS/inspect_ai
https://camo.githubusercontent.com/2b767fce0bf0e75640d9bd1aa9ab1014f9b066ac35f01fe549b99394e43b0315/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f554b476f7665726e6d656e74424549532f696e73706563745f61693f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Quantifying Infrastructure Noise in Agentic Coding Evalshttps://www.anthropic.com/engineering/infrastructure-noise
AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluationhttps://arxiv.org/abs/2605.12925
StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turnshttps://arxiv.org/abs/2606.19613
Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflowshttps://arxiv.org/abs/2605.27922
tau-benchhttps://github.com/sierra-research/tau-bench
https://camo.githubusercontent.com/08cf8ceed008f1a18f4028c6c047e2c292beaf7e1d175656f3f104b481fa5e9d/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f7369657272612d72657365617263682f7461752d62656e63683f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
Towards a Science of AI Agent Reliabilityhttps://arxiv.org/abs/2602.16666
Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causeshttps://arxiv.org/abs/2603.06847
VeRO: An Evaluation Harness for Agents to Optimize Agentshttps://arxiv.org/abs/2602.22480
Eval Awareness in Claude Opus 4.6's BrowseComp Performancehttps://www.anthropic.com/engineering/eval-awareness-browsecomp
Designing AI-Resistant Technical Evaluationshttps://www.anthropic.com/engineering/AI-resistant-technical-evaluations
Amazon Bedrock AgentCore Evaluations Is Now Generally Availablehttps://aws.amazon.com/about-aws/whats-new/2026/03/agentcore-evaluations-generally-available/
Live-SWE-agent: First Live Software Agent with Self-Evolving Scaffoldhttps://arxiv.org/html/2511.13646v3
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Modelshttps://arxiv.org/abs/2604.10866
STATE-Benchhttps://github.com/microsoft/STATE-Bench
https://camo.githubusercontent.com/7fb6cfd617c2a0142cf23f2ffda6f684ad29a83e7400a91f51be9bee653ee980/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6d6963726f736f66742f53544154452d42656e63683f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#templates
templates/AGENTS.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/templates/AGENTS.md
templates/PLAN.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/templates/PLAN.md
templates/IMPLEMENT.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/templates/IMPLEMENT.md
templates/HARNESS_CHECKLIST.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/templates/HARNESS_CHECKLIST.md
https://github.com/web3-engineer/awesome-harness-engineering#production-infrastructure--operations
Claude Managed Agents: Self-Hosted Sandboxes and MCP Tunnelshttps://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes
MCP tunnelshttps://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/overview
AgentCgroup: Understanding and Controlling OS Resources of AI Agentshttps://arxiv.org/abs/2602.09345
AI Agent Scaling Gap: Pilot to Production (March 2026)https://www.digitalapplied.com/blog/ai-agent-scaling-gap-march-2026-pilot-to-production
builderz-labs/mission-controlhttps://github.com/builderz-labs/mission-control
https://camo.githubusercontent.com/3b8226dff608c8eef12e4387ce21e95a85af055c0bf35802ec9a7ecfc6e2fd01/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6275696c6465727a2d6c6162732f6d697373696f6e2d636f6e74726f6c3f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
5 Production Scaling Challenges for Agentic AI in 2026https://machinelearningmastery.com/5-production-scaling-challenges-for-agentic-ai-in-2026/
AI Agent Cost Optimization Guide 2026: Reduce Spend by 60-80%https://moltbook-ai.com/posts/ai-agent-cost-optimization-2026
KernelEvolve: How Meta's Ranking Engineer Agent Optimizes AI Infrastructurehttps://engineering.fb.com/2026/04/02/developer-tools/kernelevolve-how-metas-ranking-engineer-agent-optimizes-ai-infrastructure/
State of Agent Engineering 2026https://www.langchain.com/state-of-agent-engineering
Agentic Development: What It Means for Engineering Infrastructure in 2026https://www.bunnyshell.com/guides/agentic-development/
FinOps for Agents: Loop Limits, Tool-Call Caps, and the New Unit Economics of Agentic SaaShttps://www.infoworld.com/article/4138748/finops-for-agents-loop-limits-tool-call-caps-and-the-new-unit-economics-of-agentic-saas.html
Backtesting AI Agents: How SRE Teams Prove Reliability Before Productionhttps://drdroid.io/blog/backtesting-ai-agents-how-sre-teams-prove-reliability-before-production
How My Agents Self-Heal in Productionhttps://blog.langchain.com/production-agents-self-heal/
Minions: Stripe's one-shot, end-to-end coding agents—Part 2https://stripe.dev/blog/minions-stripes-one-shot-end-to-end-coding-agents-part-2
Amazon Bedrock AgentCorehttps://aws.amazon.com/bedrock/agentcore/
AWS Agent Registry for Centralized Agent Discovery and Governancehttps://aws.amazon.com/about-aws/whats-new/2026/04/aws-agent-registry-in-agentcore-preview/
A Dev's Guide to Production-Ready AI Agentshttps://cloud.google.com/blog/products/ai-machine-learning/a-devs-guide-to-production-ready-ai-agents
Enhanced Tool Governance in Vertex AI Agent Builderhttps://cloud.google.com/blog/products/ai-machine-learning/new-enhanced-tool-governance-in-vertex-ai-agent-builder
https://github.com/web3-engineer/awesome-harness-engineering#related-awesome-lists
Awesome Context Engineeringhttps://github.com/Meirtz/Awesome-Context-Engineering
awesome-claude-codehttps://github.com/hesreallyhim/awesome-claude-code
awesome-mcp-servershttps://github.com/appcypher/awesome-mcp-servers
https://camo.githubusercontent.com/d2038bf441764030ad263af1cbd042369d0054d3c887a505f4085d0b44372ba6/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6170706379706865722f617765736f6d652d6d63702d736572766572733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
awesome-ai-agentshttps://github.com/e2b-dev/awesome-ai-agents
https://camo.githubusercontent.com/8ecb99cfd76f4df8fb5dcbeac8c98d2ce783469c452f05d2e34b41727e3b469c/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f6532622d6465762f617765736f6d652d61692d6167656e74733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
awesome-llm-appshttps://github.com/Shubhamsaboo/awesome-llm-apps
https://camo.githubusercontent.com/ca961f3261b10cd5d255e8b869fb65b8761629963c0aea23c053ad43f960019f/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f5368756268616d7361626f6f2f617765736f6d652d6c6c6d2d617070733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
ICLR 2026 MemAgents Workshophttps://sites.google.com/view/memagent-iclr26/
Awesome Code as Agent Harness Papershttps://github.com/YennNing/Awesome-Code-as-Agent-Harness-Papers
https://camo.githubusercontent.com/60502720a67a529e86eba99e8d73e82c6847d41e7bd96fcf747ce77acc5928fd/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f73746172732f59656e6e4e696e672f417765736f6d652d436f64652d61732d4167656e742d4861726e6573732d5061706572733f7374796c653d666c61742d737175617265266c6162656c3d25453225393825383526636f6c6f723d79656c6c6f77
https://github.com/web3-engineer/awesome-harness-engineering#contributing
CONTRIBUTING.mdhttps://github.com/web3-engineer/awesome-harness-engineering/blob/main/CONTRIBUTING.md
https://github.com/web3-engineer/awesome-harness-engineering#license
CC0https://github.com/web3-engineer/awesome-harness-engineering/blob/main/LICENSE
https://github.com/web3-engineer/awesome-harness-engineering#acknowledgments
linux.dohttps://linux.do
github.com/ai-boost/awesome-harness-engineeringhttps://github.com/ai-boost/awesome-harness-engineering
Readmehttps://github.com/web3-engineer/awesome-harness-engineering#readme-ov-file
Licensehttps://github.com/web3-engineer/awesome-harness-engineering#License-1-ov-file
Contributinghttps://github.com/web3-engineer/awesome-harness-engineering#contributing-ov-file
Activityhttps://github.com/web3-engineer/awesome-harness-engineering/activity
0 starshttps://github.com/web3-engineer/awesome-harness-engineering/stargazers
0 watchinghttps://github.com/web3-engineer/awesome-harness-engineering/watchers
0 forkshttps://github.com/web3-engineer/awesome-harness-engineering/forks
Report repositoryhttps://github.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2Fweb3-engineer%2Fawesome-harness-engineering&report=web3-engineer+%28user%29
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.