traceroot

TraceRoot is an open-source observability platform for AI agents — Capture traces, monitors production issues, and debug with AI that sees your source code and Github history.

Features

Why TraceRoot?

• Traces alone don't scale.

  As AI agent systems grow more complex, manually sifting through every trace is unsustainable. TraceRoot's Detectors selectively screen incoming traces — flagging hallucinations, tool failures, logic errors, and safety issues automatically, so you spend time fixing problems, not hunting for them.

• Debugging AI agent systems is painful.

  Root-causing failures across agent hallucinations, tool call instabilities, and version changes is hard. TraceRoot's AI connects to a sandbox running your production source code, identifies the exact failing line, and cross-references your GitHub history — commits, PRs, open issues and creates PR to fix it.

• Fully open source, no vendor lock-in.

  Both the observability platform and the AI debugging layer are open source. BYOK support for any model provider — OpenAI, Anthropic, Gemini, xAI, DeepSeek, OpenRouter, Kimi, GLM and more.

Documentation

Full documentation available at traceroot.ai/docs.

Getting Started

TraceRoot Cloud

The fastest way to get started. Ample storages and LLM tokens for testing, no credit card needed. Sign up here!

Self-Hosting

• Developer mode: Run TraceRoot locally to contribute.

  # Get a copy of the latest repo
  git clone https://github.com/traceroot-ai/traceroot.git
  cd traceroot
  
  # Hosted the infras in docker and app itself locally
  make dev

  For more details, see CONTRIBUTING.md.

• Local docker mode: Run TraceRoot locally to test.

  # Get a copy of the latest repo
  git clone https://github.com/traceroot-ai/traceroot.git
  cd traceroot
  
  # Hosted everything in docker
  make prod

• Terraform (AWS): Run TraceRoot on k8s with Helm and Terraform. This is for production hosting. Still in experimental stage.

Integrations

Native SDKs

Agent Frameworks

Model Providers

Don't see your framework or provider? Request an integration.

Python SDK Quickstart

pip install traceroot openai

import traceroot
from traceroot import Integration, observe
from openai import OpenAI

traceroot.initialize(integrations=[Integration.OPENAI])
client = OpenAI()

@observe(name="my_agent", type="agent")
def my_agent(query: str) -> str:
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": query}],
    )
    return response.choices[0].message.content

if __name__ == "__main__":
    my_agent("What's the weather in SF?")

TypeScript SDK Quickstart

npm install @traceroot-ai/traceroot openai

import OpenAI from 'openai';
import { TraceRoot, observe } from '@traceroot-ai/traceroot';

TraceRoot.initialize({ instrumentModules: { openAI: OpenAI } });
const openai = new OpenAI();

const myAgent = observe({ name: 'my_agent', type: 'agent' }, async (query: string) => {
  const response = await openai.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: query }],
  });
  return response.choices[0].message.content;
});

async function main() {
  try {
    await myAgent("What's the weather in SF?");
  } finally {
    await TraceRoot.shutdown();
  }
}

main().catch(console.error);

Security & Privacy

Your data security and privacy are our top priorities. Learn more in our Security and Privacy documentation.

Community

Special Thanks for pi-mono project, which powers the foundation of our agentic debugging runtime!

Contributing 🤝: If you're interested in contributing, you can check out our guide here. All types of help are appreciated :)

Support 💬: If you need any type of support, we're typically most responsive on our Discord channel, but feel free to email us [email protected] too!

License

This project is licensed under Apache 2.0 with additional Enterprise features.

Contributors