{"data":{"slug":"comet-ml-opik","name":"opik","tagline":"Debug, evaluate, and monitor your LLM applications with comprehensive tracing and production-ready dashboards","github_url":"https://github.com/comet-ml/opik","owner":"comet-ml","repo":"opik","owner_avatar_url":"https://avatars.githubusercontent.com/u/31487821?v=4","primary_language":"Python","stars":21177,"forks":1681,"topics":["evaluation","hacktoberfest","hacktoberfest2025","langchain","llama-index","llm","llm-evaluation","llm-observability","llmops","open-source","openai","playground","prompt-engineering"],"archived":false,"github_pushed_at":"2026-08-07T11:46:34+00:00","maintenance_label":"Very active","stars_delta_30d":767,"url":"https://www.graphcanon.com/tools/comet-ml-opik","markdown_url":"https://www.graphcanon.com/tools/comet-ml-opik.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/comet-ml-opik","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=comet-ml-opik","description":"Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.","homepage_url":"https://www.comet.com/docs/opik/","license":"Apache-2.0","open_issues":172,"watchers":128,"ai_summary":"Opik Server provides tools for the evaluation, observability, and monitoring of LLM applications and workflows. It supports deployment through Docker or Kubernetes.","readme_excerpt":"## ⚡ Quick Start\n\nInstall the Python SDK and configure it:\n\n```bash\npip install opik\nopik configure\n```\n\nWrap any function with the `@track` decorator to start logging traces:\n\n```python\nfrom opik import track\n\n@track\ndef my_function(input: str) -> str:\n    return input\n```\n\nEvery call to `my_function` is now logged to Opik, including nested calls, so this works for full agent and pipeline traces, not just single LLM calls. See the [Quickstart guide](https://www.comet.com/docs/opik/quickstart?from=llm&utm_source=opik&utm_medium=github&utm_content=quickstart_hero_link&utm_campaign=opik) for the TypeScript SDK and other setup options.\n\n<br>\n\n<a id=\"-how-opik-compares\"></a>\n\n---\n\n## 🛠️ Opik Server Installation\n\nGet your Opik server running in minutes. Choose the option that best suits your needs:\n\n---\n\n### Option 2: Self-Host Opik for Full Control\n\nDeploy Opik in your own environment. Choose between Docker for local setups or Kubernetes for scalability.\n\n#### Self-Hosting with Docker Compose (for Local Development & Testing)\n\nThis is the simplest way to get a local Opik instance running. Note the new `./opik.sh` installation script:\n\nOn Linux or Mac Environment:\n\n```bash\n\n---\n\n# Start only infrastructure services (databases, caches etc.)\n./opik.sh --infra\n\n---\n\n# Start infrastructure + backend services\n./opik.sh --backend\n\n---\n\n### Python SDK Quick Start\n\nTo get started with the Python SDK:\n\nInstall the package:\n\n```bash\n\n---\n\n# or install with uv\nuv pip install opik\n```\n\nConfigure the python SDK by running the `opik configure` command, which will prompt you for your Opik server address (for self-hosted instances) or your API key and workspace (for Comet.com):\n\n```bash\nopik configure\n```\n\n> [!TIP]\n> You can also call `opik.configure(use_local=True)` from your Python code to configure the SDK to run on a local self-hosted installation, or provide API key and workspace details directly for Comet.com. Refer to the [Python SDK documentation](https://www.comet.com/docs/opik/python-sdk-reference/?from=llm&utm_source=opik&utm_medium=github&utm_content=python_sdk_docs_link&utm_campaign=opik) for more configuration options.\n\nYou are now ready to start logging traces using the [Python SDK](https://www.comet.com/docs/opik/python-sdk-reference/?from=llm&utm_source=opik&utm_medium=github&utm_content=sdk_link2&utm_campaign=opik).\n\n<a id=\"-logging-traces-with-integrations\"></a>","github_created_at":"2023-05-10T12:57:13+00:00","created_at":"2026-07-07T17:41:32.83204+00:00","updated_at":"2026-08-07T12:01:23.511643+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":"evaluation","name":"evaluation"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"llm-observability","name":"llm-observability"}],"trust":{"provenance":{"is_fork":false,"github_id":638951438,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-07T12:01:22.737Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":23,"days_since_push":0,"last_release_at":"2026-08-07T10:00:49Z","stars_delta_30d":767,"open_issues_delta_30d":23},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:39:26.857Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-07T12:01:23.208Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-07T12:01:23.208Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-07T12:01:23.208Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Opik is available under the Apache-2.0 license and can be deployed freely using Docker or Kubernetes, with no explicit mention of premium cloud-based services."},"requirements":{"notes":["Compatible with Python environments.","Can be deployed via Docker for local use or Kubernetes for scalable installations."]},"constraints":{"pricing_model":"freemium"},"when_to_use":["- Use Opik when you need to deploy a self-hosted solution that offers granular control over your LLM monitoring setup.","- Deploy Opik if you are working with RAG systems or other complex agentic workflows requiring detailed evaluation and monitoring tools.","- Opt for Opik when comprehensive tracing capabilities are required, allowing robust post-deployment analysis of application behavior."],"when_not_to_use":["- Avoid using Opik if you prefer cloud-based deployment options where extensive self-hosting management may be less preferable or feasible.","- Do not use Opik if your project does not involve LLM applications or RAG systems, as its specific features will offer little benefit in a narrower context."],"source":"enrich:decision_facts","observed_at":"2026-07-11T14:16:18.723Z"},"constraint_facets":{"pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - Opik is available under the Apache-2.0 license and can be deployed freely using Docker or Kubernetes, with no explicit mention of premium cloud-based services."},{"label":"Requirements","value":"Compatible with Python environments.; Can be deployed via Docker for local use or Kubernetes for scalable installations."},{"label":"Adopt for","value":"Opik is designed for evaluating and monitoring LLM applications, offering comprehensive tracing and dashboards."}]}}