AI Agent Testing and Evaluation

LangWatch is the open-source platform for AI in production: trace, test, route and govern every LLM call in your company, from the agents you build to the coding assistants your engineers use. LangWatch is Apache 2.0. View docs.

Get started

LangWatch Cloud

Track your coding agents

npx langwatch claude  # or codex, copilot, opencode, ...

Self-host

npx @langwatch/server

Only Node.js 24 or newer required (macOS or glibc Linux). For production, see Self-hosting LangWatch.

Demo

What you get

• LLM Ops: Observability · Agent Testing · Evaluations · Prompt Management
• Coding Agents: sessions, cost per pull request and per team, privacy controls
• AI Gateway: one OpenAI and Anthropic compatible endpoint, virtual keys, budgets, routing
• AI Governance: every AI tool in the company, who uses it, anomaly rules

Things you can do with LangWatch

1. Create simulation tests for evaluating or benchmarking your agents and voice agents
2. Measure the cost per PR and optimize your Claude Code usage to get your weekly limits to last twice as long
3. Create virtual keys with budgets to hand out to your customers or employees
4. Find out that 40% of the Copilot Studio subscriptions are not actually being used at your company and cancel them

Integrations

Coding assistants: Claude Code · Codex · GitHub Copilot · opencode · Cursor · MCP server · more

Frameworks: LangChain · LangGraph · Vercel AI SDK · Mastra · CrewAI · Google ADK · DSPy · OpenTelemetry · more

Model providers: OpenAI · Anthropic · Azure OpenAI · Vertex AI · Bedrock · more

Governance sources: Copilot Studio · Claude Cowork · Anthropic and OpenAI compliance APIs · Workato · Databricks Genie · OpenTelemetry and S3 audit feeds · more

No-code platforms: LangFlow · Flowise · n8n · more

Contributing

Read CONTRIBUTING.md, then make quickstart. Bugs and feature requests go in GitHub issues, questions in Discord.

License

Apache 2.0. The enterprise modules under enterprise/ need a commercial license in production, and the SDKs are MIT. See Editions and licensing and LICENSE.md.

Security

GDPR compliant and ISO 27001 certified. Report vulnerabilities to [email protected].