GraphCanon updated 1w · GitHub synced 1w · 26 views this month
Decision brief
LangWatch is a comprehensive tool for evaluating large language models (LLM) and testing AI agents. It supports self-hosting with flexible deployment options including Docker, Kubernetes, and cloud-specific setups.
Good fit when
- You need to evaluate LLMs and test AI agents in a controlled environment.
- You prefer self-hosted solutions for better control over data residency and compliance requirements.
Avoid when
- If you are looking for an out-of-the-box service without the complexity of setting up your own infrastructure, since LangWatch heavily leans towards self-hosting.
- You do not require advanced enterprise features like SCIM, audit logs, license management, as these features require a commercial license.
- Pricing:
- freemium - Open-source editions are free with restrictions on certain advanced features that require a commercial license.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Adoption
Package downloads where a registry match exists. GitHub stars (3,479) are secondary evidence.
- npm downloads (30d)
- 1,102·npm downloads API·1w
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of 1w
- Provenance
- Not a fork · Organization account
- As of 1w
- Security (OSV)
- No criticals
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
npm install langwatchHow it fits your stack(11)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Related
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
LangWatch provides tools to evaluate large language models (LLM), test AI agents, measure quality, performance and reliability. It uses TypeScript and supports self-hosting on various infrastructure options including Docker, Kubernetes, and cloud-specific setups.
Capability facts
- CLI
- CLI entrypoint
Source: package.json:bin|scripts · Aug 8, 2026
- MCP server
- No MCP server detected
Source: repo_scan · Aug 8, 2026
- Languages
- typescript, javascript
Source: github.language+package.json · Aug 8, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 8, 2026)
art that needs a commercial license in production. The SDKs (`typescript-sdk`, `python-sdk`, `mcp-server`) are MIT.Source link
Source: README excerpt (regex_v1, Aug 8, 2026)
LangWatch MCP](https://langwatch.ai/docs/integration/mcp)** - Use LangWatch in Claude Desktop and other MCP clientsSource link
Tags
README
Deployment options ⚓️
Run LangWatch on your own infrastructure:
- Docker Compose - Run LangWatch on your own machine.
- Kubernetes (Helm) - Run LangWatch on a Kubernetes cluster using Helm.
- OnPrem - Cloud-specific setups for AWS, Google Cloud, and Azure.
Hybrid (OnPrem data) 🔀
For companies that have strict data residency and control requirements, without needing to go fully on-prem.
Read more about it on our docs.
Local Development 👩💻
You can also run LangWatch locally without docker to develop and help contribute to the project.
Start just the databases using docker and leave it running:
docker compose up redis postgres opensearch
Then, on another terminal, install the dependencies and start LangWatch:
make install
make start
🚀 Quick Start
Ship safer agents in minutes. Create a free account, then dive into these guides:
- Run your first agent simulation - Test agents against realistic scenarios before production
- Set up evaluations - Measure quality, performance, and reliability
- Send your first traces - Integrate LangWatch with your stack
- Get started with LangWatch MCP - Use LangWatch in Claude Desktop and other MCP clients
✍️ License: open-core split
LangWatch is Apache 2.0 and free to use, for individuals and for companies, self-hosted or not. The enterprise modules (SSO, SCIM provisioning, audit logs, gateway webhooks, billing, back-office) live under platform/app/ee/ and are the one part that needs a commercial license in production. The SDKs (typescript-sdk, python-sdk, mcp-server) are MIT.
See Editions and licensing for what a license adds, and LICENSE.md, NOTICE, platform/app/ee/LICENSE.md for the full text and the per-folder breakdown.
For agents
This page has a .md twin and JSON over the API.