OSS TanbouOn this page
Overview
LangWatch combines LLM tracing, evaluations, simulation testing, prompt management, an AI Gateway, and coding-agent monitoring. It also integrates with OpenTelemetry and major LLM frameworks and providers.
Features and best fit
Based on official documentation; not hands-on tested · Content checked:
Key features
Trace LLM calls and evaluate cost and quality
Observability and evaluation workflows track requests, latency, cost, and quality metrics across production AI applications.
Sources: [2]
Test agent simulations and analyze coding-agent sessions
The platform supports agent simulation testing plus session and cost tracking for tools such as Claude Code, Codex, and Copilot.
Sources: [2]
Best fit
Fits teams consolidating AI evaluation and observability
It is useful when prompt or model evaluation, production traces, and gateway routing should live in one operational workflow.
Sources: [2]
Before adoption
Self-hosting requires Node.js 20 or newer
Package metadata requires Node.js 20+, while the README documents local startup through npx @langwatch/server.
Sources: [2]
Official sources
- [1]langwatch/langwatch repository(2026-09-30)
- [2]LangWatch README(2026-09-30)
- [3]LangWatch Apache 2.0 license(2026-09-30)
- [4]LangWatch v3.18.1 release(2026-09-30)
Supplemental curator note
LangWatch combines LLM observability, evaluations, agent testing, an AI Gateway, and governance. The core is Apache-2.0, while the README states that enterprise modules under platform/app/ee/ require a commercial license for production use.
Try it in 3 steps
- 1
Check Node.js 20+
Verify the runtime requirement for the LangWatch server package.
node --version - 2
Start LangWatch locally
Run the version-pinned self-hostable stack with one command.
npx @langwatch/server@3.18.1 - 3
Try coding-agent tracking
Launch a supported coding agent through LangWatch and inspect session and cost tracking.
npx langwatch claude
Growth
Growth trends · Last 30 days
4,891 Stars
Trend data is still being collected.
Built with
Categories and tags
GitHub data
GitHub dataView detailed GitHub data
GitHub Topics
- agent-testing
- ai
- analytics
- datasets
- dspy
- evaluation
- gpt
- llm
- llm-ops
- llmops
- low-code
- observability
- Stars
- 4,891
- Forks
- 402
- Watchers
- 16
- Open issues
- 250
- Owner type
- Organization
- Primary language
- TypeScript
- License
- Apache-2.0
- Repository last updated
- Sep 30, 2026
Related information
Write a related articleShare a guide or use case for this OSS in Markdown. Articles are published after administrator approval.
Explore next
- Frontman707 Stars
3 shared tag(s) · 1 shared category(s)
Trace selected browser UI through live DOM, CSS, and source maps and let an AI agent edit the owning source
ReScript - CodexMonitor4,338 Stars
3 shared tag(s) · Same language
Orchestrate Codex app-server threads, worktrees, Git diffs, and reviews across multiple workspaces in one desktop UI
TypeScript - Heliox-OS65 Stars
3 shared tag(s)
Control an existing OS through natural language, voice, and gestures while routing real actions through permissions, approvals, and verification
Python - Langfuse35,212 Stars
2 shared tag(s) · 2 shared category(s) · Same language
connect LLM application tracing, evaluation, and prompt improvement
TypeScript - OpenLIT2,804 Stars
2 shared tag(s) · 2 shared category(s) · Same language
OpenTelemetry observability and evaluation for LLM, tool, and coding-agent workflows
TypeScript - Bifrost8,459 Stars
2 shared tag(s) · 2 shared category(s)
centralize multiple LLM providers behind one high-performance gateway
Go
Report incorrect information
Tell us if any listing information is incorrect or outdated.