{"data":{"slug":"helicone-helicone","name":"helicone","tagline":"Open source LLM observability platform","github_url":"https://github.com/Helicone/helicone","owner":"Helicone","repo":"helicone","owner_avatar_url":"https://avatars.githubusercontent.com/u/114524975?v=4","primary_language":"TypeScript","stars":6162,"forks":670,"topics":["agent-monitoring","analytics","evaluation","gpt","langchain","large-language-models","llama-index","llm","llm-cost","llm-evaluation","llm-observability","llmops","monitoring","open-source","openai","playground","prompt-engineering","prompt-management","ycombinator"],"archived":false,"github_pushed_at":"2026-09-16T19:29:27+00:00","maintenance_label":"Very active","stars_delta_30d":89,"url":"https://www.graphcanon.com/tools/helicone-helicone","markdown_url":"https://www.graphcanon.com/tools/helicone-helicone.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/helicone-helicone","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=helicone-helicone","description":"🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓","homepage_url":"https://www.helicone.ai","license":"Apache-2.0","open_issues":155,"watchers":58,"ai_summary":"Helicone is an open-source platform for monitoring, evaluating, and experimenting with large language models. It supports various LLMs and provides tools for prompt engineering and management.","readme_excerpt":"## Quick Start ⚡️\n\n1. Get your API key by signing up [here](https://helicone.ai/signup) and add credits at [helicone.ai/credits](https://us.helicone.ai/credits)\n\n2. Update the `baseURL` in your code and add your API key.\n\n   ```typescript\n   import OpenAI from \"openai\";\n\n   const client = new OpenAI({\n     baseURL: \"https://ai-gateway.helicone.ai\",\n     apiKey: process.env.HELICONE_API_KEY,\n   });\n\n   const response = await client.chat.completions.create({\n     model: \"gpt-4o-mini\",  // claude-sonnet-4, gemini-2.0-flash or any model from https://www.helicone.ai/models\n     messages: [{ role: \"user\", content: \"Hello!\" }]\n   });\n   ```\n\n3. 🎉 You're all set! View your logs at [Helicone](https://us.helicone.ai/dashboard) and access 100+ models through one API.\n\n---\n\n### Self-Hosting Open Source LLM Observability\n\n#### Docker\n\nHelicone is simple to self-host and update. To get started locally, just use our [docker-compose](https://docs.helicone.ai/getting-started/self-deploy-docker) file.\n\n```bash\n\n---\n\n## License\n\nHelicone is licensed under the [Apache v2.0 License](LICENSE).","github_created_at":"2023-01-31T22:34:44+00:00","created_at":"2026-07-07T17:34:46.215082+00:00","updated_at":"2026-09-20T04:30:22.226834+00:00","categories":[{"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":"agent-monitoring","name":"agent-monitoring"},{"slug":"analytics","name":"analytics"},{"slug":"evaluation","name":"evaluation"},{"slug":"gpt","name":"gpt"},{"slug":"langchain","name":"langchain"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"llama-index","name":"llama-index"},{"slug":"llm-cost","name":"llm-cost"}],"trust":{"provenance":{"is_fork":false,"github_id":595832198,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:22:58.085Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1,"last_release_at":"2025-08-21T18:47:38Z","stars_delta_30d":89,"open_issues_delta_30d":-15},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:22:59.698Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-18T08:22:57.030Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:22:57.030Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-18T08:22:57.030Z","managed_saas":false},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-18T08:22:57.030Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-18T08:22:57.030Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:22:57.030Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to monitor and evaluate the performance of large language models in real-time.","If you are working with multiple LLMs and require a centralized platform for prompt engineering and management.","For teams that want to experiment with over 100 models through a single API endpoint.","If you prefer an open-source solution that can be self-hosted using Docker."],"when_not_to_use":["If your project requires proprietary or closed-source tools, as Helicone is open-source and can be self-hosted.","When you need a platform that does not require setting up an API key and modifying your codebase to integrate monitoring.","If you are looking for a solution that does not support a wide range of models through a single API, and you prefer platform-specific tools.","For users who do not want to manage their own infrastructure, as Helicone offers self-hosting options which require local setup and maintenance."],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:25:13.712Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Helicone is an open-source platform for monitoring and evaluating large language models, offering tools for prompt engineering and management."}]}}