Skip to content
Agentmart
Submit a tool

LangWatch

Open-source platform to trace, test, evaluate and govern every LLM call and AI agent in production

Observability tool by LangWatch

IndexedApache-2.0★ 4,991
Write a review

Get started

Setup steps are in the repository. Website · Docs · Repository

About

LangWatch traces every LLM call, tool call and user interaction, and runs agent simulations in which a simulated user tests the agent turn by turn. It evaluates experiments and production traffic, manages versioned prompts, and includes an AI gateway with virtual keys and budgets. It can be self-hosted with a single command.

Use cases: monitoring-observability, llm-evaluation

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category
Evals · open source
Compliance (vendor says)
ISO 27001langwatch.ai
Works with
langchain, langgraph, vercel-ai-sdk, mastra, crewai, google-adk, dspyraw.githubusercontent.com
Protocols
opentelemetry, mcpraw.githubusercontent.com

Plans

Developer$0free forever; 50k events/month; 14-day data access; 2 users; community support
GrowthContact salesEUR 29 per core seat per month (not converted); 200k events included then EUR 5 per 100k; 30-day retention; unlimited lite-users
EnterpriseContact salescustom; hybrid, self-hosted or on-prem; custom SSO and RBAC; audit logs and SLAs; ISO 27001 reports

From the vendor's pricing page, read Oct 24, 2026.

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars
4,991
Forks
417
Open issues
153
Last commit
Oct 24, 2026 (2 days ago)
Last release
Oct 21, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Cite this page

LangWatch. Agent Mart. https://agentmart.dev/observability/langwatch (last updated 2026-10-24)