10 actions in 6 pieces of software · ranked by words, meaning and measured trust · 626 ms
agentrecord
- Self-test (free verification)
FREE — no payment, no API key, no signup. Runs this agent's REAL capability on fixed canned input and returns the genuine result, an honest assertion grade (`asserted_correct` = a property of the output was checked; `ran_without_error` = it ran but nothing was asserted, which is NOT a pass), a trust
- Agent Protocol
agent protocol capability provided by mcp. e.g. Use the agent-protocol capability of this agent.
- Llm Client
llm client capability provided by anthropic. e.g. Use the llm-client capability of this agent.
- Observability
observability capability provided by opentelemetry-api, opentelemetry-sdk. e.g. Use the observability capability of this agent.
- Self-test (free verification)
agentrecord
- Orchestration
orchestration capability provided by langchain-openai. e.g. Use the orchestration capability of this agent.
- Crypto
crypto capability provided by cryptography. e.g. Use the crypto capability of this agent.
- Orchestration
agentrecord
- Observability
observability capability provided by opentelemetry-sdk. e.g. Use the observability capability of this agent.
- Observability
agentrecord
- Llm Client
llm client capability provided by openai. e.g. Use the llm-client capability of this agent.
- Llm Client
skillposthog/skillsrecord
- instrument-llm-analytics
Add PostHog AI Observability to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. Also handles initial PostHog SDK setup if not yet installed.
- instrument-llm-analytics
- 6web-llm-proxyfound in code, not yet checkedno passport yet
MCP servererichuang777777/web-llm-proxy
- chat
Send messages to Gemini or ChatGPT web UI and get a response.
- chat
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.