{"data":{"slug":"langwatch-langwatch","name":"langwatch","tagline":"The platform for LLM evaluations and AI agent testing","github_url":"https://github.com/langwatch/langwatch","owner":"langwatch","repo":"langwatch","owner_avatar_url":"https://avatars.githubusercontent.com/u/146763322?v=4","primary_language":"TypeScript","stars":3479,"forks":340,"topics":["ai","analytics","datasets","dspy","evaluation","gpt","llm","llm-ops","llmops","low-code","observability","openai","prompt-engineering"],"archived":false,"github_pushed_at":"2026-08-07T21:03:52+00:00","maintenance_label":"Very active","stars_delta_30d":152,"url":"https://www.graphcanon.com/tools/langwatch-langwatch","markdown_url":"https://www.graphcanon.com/tools/langwatch-langwatch.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/langwatch-langwatch","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=langwatch-langwatch","description":"The platform for LLM evaluations and AI agent testing","homepage_url":"https://langwatch.ai","license":"Apache-2.0","open_issues":777,"watchers":13,"ai_summary":"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.","readme_excerpt":"### Deployment options ⚓️\n\nRun LangWatch on your own infrastructure:\n\n- [Docker Compose](https://docs.langwatch.ai/self-hosting/open-source#docker-compose) - Run LangWatch on your own machine.\n- [Kubernetes (Helm)](https://docs.langwatch.ai/self-hosting/open-source#helm-chart-for-langwatch) - Run LangWatch on a Kubernetes cluster using Helm.\n- [OnPrem](https://docs.langwatch.ai/self-hosting/onprem) - Cloud-specific setups for AWS, Google Cloud, and Azure.\n\n<details>\n<summary>Hybrid (OnPrem data) 🔀</summary>\n\nFor companies that have strict data residency and control requirements, without needing to go fully on-prem.\n\nRead more about it on our [docs](https://docs.langwatch.ai/self-hosting/hybrid).\n\n</details>\n\n<details>\n<summary>Local Development 👩‍💻</summary>\n\nYou can also run LangWatch locally without docker to develop and help contribute to the project.\n\nStart just the databases using docker and leave it running:\n\n```bash\ndocker compose up redis postgres opensearch\n```\n\nThen, on another terminal, install the dependencies and start LangWatch:\n\n```bash\nmake install\nmake start\n```\n\n</details>\n\n---\n\n## 🚀 Quick Start\n\nShip safer agents in minutes. [Create a free account](https://app.langwatch.ai), then dive into these guides:\n\n- **[Run your first agent simulation](https://langwatch.ai/scenario/introduction/getting-started)** - Test agents against realistic scenarios before production\n- **[Set up evaluations](https://docs.langwatch.ai/llm-evaluation/offline-evaluation)** - Measure quality, performance, and reliability\n- **[Send your first traces](https://docs.langwatch.ai/integration/overview)** - Integrate LangWatch with your stack\n- **[Get started with LangWatch MCP](https://langwatch.ai/docs/integration/mcp)** - Use LangWatch in Claude Desktop and other MCP clients\n\n---\n\n## ✍️ License: open-core split\n\nLangWatch 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/`](/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.\n\nSee [Editions and licensing](https://docs.langwatch.ai/self-hosting/licensing) for what a license adds, and [`LICENSE.md`](/LICENSE.md), [`NOTICE`](/NOTICE), [`platform/app/ee/LICENSE.md`](/platform/app/ee/LICENSE.md) for the full text and the per-folder breakdown.","github_created_at":"2023-09-09T11:33:18+00:00","created_at":"2026-07-07T17:42:19.508653+00:00","updated_at":"2026-08-08T00:01:07.559734+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"analytics","name":"analytics"},{"slug":"datasets","name":"datasets"},{"slug":"evaluation","name":"evaluation"},{"slug":"llm","name":"llm"},{"slug":"observability","name":"observability"},{"slug":"prompt-engineering","name":"prompt-engineering"}],"trust":{"provenance":{"is_fork":false,"github_id":689299900,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-08T00:01:06.291Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-08-07T17:22:02Z","stars_delta_30d":152,"open_issues_delta_30d":103},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:42:03.164Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-08T00:01:06.724Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-08T00:01:06.724Z"},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-08-08T00:01:06.724Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-08-08T00:01:06.724Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-08T00:01:06.724Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Open-source editions are free with restrictions on certain advanced features that require a commercial license."},"requirements":{},"constraints":{"pricing_model":"freemium"},"when_to_use":["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.","Your team uses TypeScript for development as LangWatch is primarily written in TypeScript."],"when_not_to_use":["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."],"source":"enrich:decision_facts","observed_at":"2026-07-12T15:58:18.586Z"},"constraint_facets":{"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - Open-source editions are free with restrictions on certain advanced features that require a commercial license."},{"label":"Adopt for","value":"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."},{"label":"License detail","value":"LangWatch is licensed under Apache-2.0 for its core functionalities, but enterprise modules such as SCIM and audit logging require a commercial license."}]}}