traceroot-ai /traceroot
TraceRoot - Open Source AI Agent Improvement Platform. YC S25
★ 1,341⑂ 295👁 2▤ 51
+0
Daily
+0
Weekly
1,341
stars
295
forks
2
watchers
–
prs
–
issues
51
releases
README
traceroot: the open-source platform that continuously improves your ai agents.
[![Y Combinator][y-combinator-image]][y-combinator-url]
[![License][license-image]][license-url]
[![X (Twitter)][twitter-image]][twitter-url]
[![Discord][discord-image]][discord-url]
[![Documentation][docs-image]][docs-url]
[![PyPI SDK Downloads][pypi-sdk-downloads-image]][pypi-sdk-downloads-url]
Website ·
Cloud ·
Documentation ·
Community
⭐ Help us reach more developers and grow the traceroot community. Star this repo!
traceroot
Find the patterns in your agent's production issues. Ship verified fixes with your coding agent.
https://github.com/user-attachments/assets/2ecf21ce-93b3-41cb-8749-e02b77467357
Core Features
Turn production failures into tested improvements
Trace production runs, use detectors to evaluate behavior, and surface recurring patterns as improvement signals. Your coding agent uses the traceroot CLI to investigate those signals and make local changes, then verifies them with offline evals. After you ship, new production traces feed the next round of detection, signals, and verification—closing a continuous improvement loop.
| Step | Description |
| ---- | ----------- |
| Trace | See each model call, tool call, and response, with inputs, outputs, latency, and cost. |
| Detect | Define what good behavior looks like. Automatically flag production runs that miss the mark. |
| Signals | Cluster judge outputs into signals. A background coding agent investigates traces and connected GitHub code in a sandbox to suggest fixes. |
| Verify | Run evals against your datasets and compare versions to measure improvements and catch regressions. |
⭐ Star the Repository
If you like what we’re building, give traceroot a star ⭐ to help more developers discover it.
Setting up traceroot
Send your first trace to traceroot Cloud or your own traceroot instance: run one command and let your coding agent add the instrumentation, or configure an SDK manually.
With your coding agent
Run this from the root of the repository you want to trace:
bash
npx -y traceroot-cli@latest setup
The traceroot CLI signs you in through your browser (where you can create a free account), writes a project API key into your application's env file, has Claude Code or Codex add the SDK, and waits for your first trace. It needs Node.js 20.12 or later.
- Using another coding agent? Setup can write the change out as a task for it to run.
- Self-hosting? Point setup at your instance with --host (the API origin) and --auth-host (the web app origin).
See the setup guide for each step, self-hosting, and troubleshooting.
Manually with an SDK
Prefer to configure instrumentation yourself? Use the Python SDK or TypeScript SDK. The example below sends one traced model call from a TypeScript application.
Run a minimal TypeScript example
You need Node.js and npm, a traceroot project API key, and an OpenAI API key. For