# TraceRoot

> TraceRoot is a self-hosted, open-source platform for tracing AI agents, detecting issues with LLM judges, and verifying fixes via offline evals.

- **Category:** Monitoring & observability
- **Licence:** Other
- **Latest version:** v1.3.3
- **Open source:** open_core
- **Languages:** Typescript, Python
- **Platforms:** Docker Compose, Kubernetes
- **Tags:** Analytics, Llm Observability, Observability, Developer Tools, Opentelemetry, Open Source, Tracing, Self Hosted, Ai Agent, Agentic, Ai Observability, Coding agent, Agent Observability, Evals, Detectors, Signals

## Description

TraceRoot helps developers find patterns in production AI agent failures and ship verified fixes. It captures model and tool calls with their inputs, outputs, latency, and cost; runs detectors with LLM judges to evaluate behavior; clusters judge outputs into recurring signals investigated by background coding agents in sandboxes; and runs offline evaluations to compare versions and catch regressions. A command-line interface gives coding agents read/write access to traces, detectors, datasets, evaluations, dashboards, and alerts. Native Python and TypeScript SDKs plus many integrations cover frameworks like LangGraph, CrewAI, AutoGen, and Vercel AI SDK, plus model providers including OpenAI, Anthropic, Gemini, and Mistral. Self-hosting uses Docker Compose with PostgreSQL, ClickHouse, Redis, and MinIO. Core code is Apache 2.0; enterprise features need a separate license.

## Links

- [Homepage](https://github.com/traceroot-ai/traceroot)
- [Website](https://traceroot.ai)
- [Documentation](https://traceroot.ai/docs)
- [GitHub Repository](https://github.com/traceroot-ai/traceroot)
- [Discord Community](https://discord.gg/TM2m3CtKuC)
- [Twitter/X](https://x.com/TraceRootAI)
- [LinkedIn](https://www.linkedin.com/company/traceroot-ai)
- [Blog](https://traceroot.ai/blog)
- [Changelog](https://traceroot.ai/changelog)
- [Security & Trust Center](https://trust.traceroot.ai)

---
Source: https://selfhost.directory/project/traceroot