← Open Source
chirpz-ai

pandaprobe

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.

AI EngineeringTest & guardBuild agent workflow (SDK)Python
Open on GitHub
Momentum
+0stars in 24 hours0.0%
790
Stars
122
Forks
+5
This week
2
Contributors
Created 2025-12-16 · Updated 2026-10-13 · #13797 today
Top developers

chirpz-ai/pandaprobe is ranked 13,797 with 790 stars.

Same-category comparison

chirpz-ai/pandaprobe is ranked 13,797 among these 8 peers; RobustBench/robustbench is ranked 13,796.

Same-category comparison
NameRankMetrics
ECNU-SII/MIA13,782
Language:
Python
Stars:
791
Forks:
85
Description:
Memory Intelligence Agent.
Microck/opencode-studio13,784
Language:
TypeScript
Stars:
791
Forks:
61
Description:
web GUI for securely managing local OpenCode configuration.
syedazharmbnr1/claude-chatgpt-mcp13,792
Language:
JavaScript
Stars:
791
Forks:
103
Description:
A Claude MCP tool to interact with the ChatGPT desktop app on macOS.
RobustBench/robustbench13,796
Language:
Python
Stars:
790
Forks:
106
Description:
RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track].
hyperbrowserai/mcp13,804
Language:
TypeScript
Stars:
789
Forks:
75
Description:
A MCP server implementation for hyperbrowser.
line/line-bot-mcp-server13,805
Language:
TypeScript
Stars:
789
Forks:
160
Description:
MCP server that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.
google-research/long-range-arena13,816
Language:
Python
Stars:
788
Forks:
86
Description:
Long Range Arena for Benchmarking Efficient Transformers.
xiaopu-ai/web-design13,821
Language:
Python
Stars:
788
Forks:
80
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryAI Engineering
SubcategoryTest & guard, Build agent workflow (SDK)
KeywordsAgent-ready APIs, Client integration, Evals, Experiment tracking
Stars790
Forks122
Contributors2
Created date2025-12-16
Updated date2026-10-13
Stars in 1 day0
Stars in 7 days5
Rank13,797
Previous rank13,691
Rank change-106
7-day stars rank5,703
Previous 7-day stars rank5,710
7-day stars rank change7
Total stars rank13,497
Previous total stars rank13,475
Total stars rank change-22
README summary

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 . PandaProbe Cloud Managed deployment by the PandaProbe team, generous free-tier, no credit card required. Self-host PandaProbe **Prerequisites:** Docker must be installed and running. Please read the Contributing Guide for instructions on setting up your development environment, building

from source, running tests, and submitting pull requests. License PandaProbe is licensed under Apache 2.

Frequently asked questions

How many stars and forks are recorded?

chirpz-ai/pandaprobe has 790 stars and 122 forks.

What is the repository rank?

chirpz-ai/pandaprobe is ranked 13,797.

What language and category are recorded?

chirpz-ai/pandaprobe has 790 stars, uses Python and belongs to AI Engineering.

Which repository is closest in rank?

chirpz-ai/pandaprobe is compared with RobustBench/robustbench, ranked 13,796 with 790 stars.

README

![](https://img.shields.io/badge/made by-Chirpz AI-blue)

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.

PandaProbe Cloud

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

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 
    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 sina@pandaprobe.com for enquiries.

License

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

Nearby in the ranking
Similar items