{"id":"0d1534e5-f586-4ea1-9aba-73541cd62b9e","slug":"crewai-chirpz-ai-pandaprobe","name":"pandaprobe","description":"🐼 open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.","canonicalUrl":"https://www.xpersona.co/skill/crewai-chirpz-ai-pandaprobe","sourceUrl":"https://github.com/chirpz-ai/pandaprobe","homepage":null,"source":"GITHUB_OPENCLEW","vendor":{"slug":"chirpz-ai","label":"Chirpz Ai","url":"https://github.com/chirpz-ai/pandaprobe"},"protocols":["OPENCLEW"],"capabilities":["crewai","multi-agent"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-05-18T06:44:49.938Z","freshnessLabel":"May 18, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"May 18, 2026"},{"label":"Vendor","value":"Chirpz Ai"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","label":"Vendor","value":"Chirpz Ai","category":"vendor","href":"https://github.com/chirpz-ai/pandaprobe","sourceUrl":"https://github.com/chirpz-ai/pandaprobe","sourceType":"profile","confidence":"medium","observedAt":"2026-05-11T06:21:51.194Z","isPublic":true,"metadata":{}},{"factKey":"protocols","label":"Protocol compatibility","value":"OpenClaw","category":"compatibility","href":"https://www.xpersona.co/api/v1/agents/crewai-chirpz-ai-pandaprobe/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/crewai-chirpz-ai-pandaprobe/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-05-11T06:21:51.194Z","isPublic":true,"metadata":{}},{"factKey":"traction","label":"Adoption signal","value":"41 GitHub stars","category":"adoption","href":"https://github.com/chirpz-ai/pandaprobe","sourceUrl":"https://github.com/chirpz-ai/pandaprobe","sourceType":"profile","confidence":"medium","observedAt":"2026-05-11T06:21:51.194Z","isPublic":true,"metadata":{}},{"factKey":"docs_crawl","label":"Crawlable docs","value":"6 indexed pages on the official domain","category":"integration","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true,"metadata":{}},{"factKey":"handshake_status","label":"Handshake status","value":"UNKNOWN","category":"security","href":"https://www.xpersona.co/api/v1/agents/crewai-chirpz-ai-pandaprobe/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/crewai-chirpz-ai-pandaprobe/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true,"metadata":{}}],"highlights":["97 GitHub stars","Trust evidence available"],"agentCard":{"name":"pandaprobe","description":"🐼 open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.","source":"GITHUB_OPENCLEW","sourceId":"crewai:1117298172","repository":"https://github.com/chirpz-ai/pandaprobe","documentation":"https://www.xpersona.co/skill/crewai-chirpz-ai-pandaprobe/agent/crewai-chirpz-ai-pandaprobe","protocols":["OPENCLEW"],"capabilities":["crewai","multi-agent"],"languages":["python"],"install":{"command":"git clone https://github.com/chirpz-ai/pandaprobe.git","ecosystem":"git"},"examples":[{"kind":"example","language":"bash","snippet":"git clone https://github.com/chirpz-ai/pandaprobe.git\ncd pandaprobe\n./start.sh"},{"kind":"example","language":"mermaid","snippet":"sequenceDiagram\n    participant Client as 📡 SDK / HTTP Client\n    participant API as ⚡ FastAPI\n    participant Auth as 🔐 Auth Service\n    participant IdP as 🌐 Supabase / Firebase\n    participant Identity as 👥 Identity Service\n    participant Trace as 🫆 Trace Service\n    participant Eval as 🧪 Eval Service\n    participant DB as 🗄️ PostgreSQL\n    participant Redis as 📮 Redis\n    participant Worker as ⚙️ Celery Worker\n    participant LLM as 🤖 LLM Engine (LiteLLM)\n\n    Note over Client,API: Management Plane (Bearer token)\n    Client->>API: Authorization: Bearer <idp_token>\n    API->>Auth: Verify token\n    Auth->>IdP: Validate with provider\n    IdP-->>Auth: User identity\n    Auth-->>API: Authenticated user\n    API->>Identity: /user, /organizations, /projects\n    Identity->>DB: Read / write\n    DB-->>Identity: Result\n    Identity-->>Client: Response\n\n    Note over Client,API: Data Plane (API key)\n    Client->>API: X-API-Key + X-Project-Name\n    API->>Identity: Resolve org & project\n    Identity-->>API: Project context\n\n    API->>Trace: POST /traces\n    Trace->>Redis: Enqueue ingestion job\n    Redis-->>Client: 202 Accepted\n    Redis->>Worker: Pick up job\n    Worker->>DB: Persist trace + spans\n\n    API->>Trace: GET /traces, /sessions\n    Trace->>DB: Query with filters\n    DB-->>Trace: Rows\n    Trace-->>Client: Paginated response\n\n    API->>Eval: POST /evaluations\n    Eval->>Redis: Enqueue eval job\n    Redis-->>Client: 202 Accepted\n    Redis->>Worker: Pick up job\n    Worker->>LLM: LLM-as-a-judge call\n    LLM-->>Worker: Verdict + score\n    Worker->>DB: Persist evaluation result"}]}}