pandaprobe

开源代理工程平台：用于调试和改进人工智能代理的跟踪、评估和指标。与LangGraph、CrewAI、Claude Agent SDK等集成。

  • 语言Python
  • 默认分支main
  • 大小15.3 MB
  • 更新3 天前
在 GitHub 打开

README

open source agent engineering platform. By Chirpz AI

PandaProbe Cloud Docs Follow on X

License Discord
Build Lint Unit Tests Integration Tests CodeQL

What is PandaProbe?

PandaProbe is an open source agent engineering platform. It helps teams collaboratively trace, evaluate, monitor, and debug AI agents. You can use PandaProbe cloud or self host the service.

Documentation

Visit our client library documentation for quickstart and explore advance integrations.

Documentation

PandaProbe Cloud

Managed deployment by the PandaProbe team, generous free-tier, no credit card required.

Sign up for PandaProbe Cloud

Self-host PandaProbe

Prerequisites: Docker must be installed and running.

git clone https://github.com/chirpz-ai/pandaprobe.git
cd pandaprobe
./start.sh

Once running, open:

Architecture

sequenceDiagram participant Client as 📡 SDK / HTTP Client participant API as ⚡ FastAPI participant Auth as 🔐 Auth Service participant IdP as 🌐 Supabase / Firebase participant Identity as 👥 Identity Service participant Trace as 🫆 Trace Service participant Eval as 🧪 Eval Service participant DB as 🗄️ PostgreSQL participant Redis as 📮 Redis participant Worker as ⚙️ Celery Worker participant LLM as 🤖 LLM Engine (LiteLLM) Note over Client,API: Management Plane (Bearer token) Client->>API: Authorization: Bearer <idp_token> API->>Auth: Verify token Auth->>IdP: Validate with provider IdP-->>Auth: User identity Auth-->>API: Authenticated user API->>Identity: /user, /organizations, /projects Identity->>DB: Read / write DB-->>Identity: Result Identity-->>Client: Response Note over Client,API: Data Plane (API key) Client->>API: X-API-Key + X-Project-Name API->>Identity: Resolve org & project Identity-->>API: Project context API->>Trace: POST /traces Trace->>Redis: Enqueue ingestion job Redis-->>Client: 202 Accepted Redis->>Worker: Pick up job Worker->>DB: Persist trace + spans API->>Trace: GET /traces, /sessions Trace->>DB: Query with filters DB-->>Trace: Rows Trace-->>Client: Paginated response API->>Eval: POST /evaluations Eval->>Redis: Enqueue eval job Redis-->>Client: 202 Accepted Redis->>Worker: Pick up job Worker->>LLM: LLM-as-a-judge call LLM-->>Worker: Verdict + score Worker->>DB: Persist evaluation result

Services

Service Description Port
frontend Next.js dashboard 3000
app FastAPI application server 8000
worker Celery background worker —
beat Celery Beat scheduler —
postgres PostgreSQL 16 5432
redis Redis 7 (broker + cache) 6379

Contributing

We welcome contributions! Please read the Contributing Guide for instructions on setting up your development environment, building from source, running tests, and submitting pull requests.

Authors

Built by the Chirpz AI team. Contact [email protected] for enquiries.

License

PandaProbe is licensed under Apache 2.0 — see LICENSE for details.

评论

暂无评论