René's URL Explorer Experiment

{"@context":"https://schema.org","@graph":[{"@type":"Organization","name":"OneCLI","url":"https://onecli.sh","logo":"https://onecli.sh/icon.png","sameAs":["https://github.com/onecli/onecli","https://x.com/jonathanfishner"]},{"@type":"SoftwareApplication","name":"OneCLI","applicationCategory":"DeveloperApplication","operatingSystem":"Linux, macOS","url":"https://onecli.sh","description":"Open-source credential gateway and vault for AI agents. Agents talk to OneCLI, OneCLI talks to the service - keys never leave the vault.","offers":{"@type":"Offer","price":"0","priceCurrency":"USD"}},{"@type":"WebSite","name":"OneCLI","url":"https://onecli.sh"}]}

{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"What is OneCLI?","acceptedAnswer":{"@type":"Answer","text":"OneCLI is an open-source credential gateway for AI agents: a secure gateway, an encrypted vault, and a dashboard, installed with one command. Agents make API calls through OneCLI, and credentials are injected at the network layer, so keys never leave the vault."}},{"@type":"Question","name":"How does OneCLI keep API keys away from agents?","acceptedAnswer":{"@type":"Answer","text":"Credentials live in an encrypted vault (local KMS or OneCLI Cloud) and are injected per-request at the proxy boundary. The agent and the LLM never see a key: not in environment variables, not in prompts, not in logs."}},{"@type":"Question","name":"Does it work with my agent framework?","acceptedAnswer":{"@type":"Answer","text":"Yes. OneCLI is framework-agnostic: OpenClaw, NanoClaw, IronClaw, Dify, n8n, OpenHands, or any custom pipeline that makes HTTP calls. There are no code changes. Agents route through the gateway with one command."}},{"@type":"Question","name":"Is OneCLI an MCP gateway?","acceptedAnswer":{"@type":"Answer","text":"No, it covers more than MCP. An MCP gateway only governs MCP tool calls. OneCLI enforces at the network layer, so it secures every way an agent reaches a service: MCP tool calls, CLI commands, curl from a shell, or HTTP requests from code the agent writes. Same vault, same policies, same audit log for all of them."}},{"@type":"Question","name":"What can I enforce?","acceptedAnswer":{"@type":"Answer","text":"Block specific endpoints, rate-limit per agent, require human approval for sensitive operations, and scope credentials per project. Policies are enforced at the network layer, outside the agent and outside the LLM. They are rules, not suggestions."}},{"@type":"Question","name":"Is OneCLI open source?","acceptedAnswer":{"@type":"Answer","text":"Yes. OneCLI is Apache 2.0 licensed and developed in the open on GitHub. Self-host it for free with a one-line install, or use OneCLI Cloud if you want a managed vault and dashboard."}},{"@type":"Question","name":"How long does setup take?","acceptedAnswer":{"@type":"Answer","text":"One command: curl -fsSL https://onecli.sh/install | sh installs and starts the gateway, vault, and dashboard. The free tier covers 2 agents forever, with no credit card required."}}]}