{"data":{"slug":"parea-ai-parea-sdk-py","name":"parea-sdk-py","tagline":"Python SDK for experimenting, testing, evaluating and monitoring LLM-powered applications.","github_url":"https://github.com/parea-ai/parea-sdk-py","owner":"parea-ai","repo":"parea-sdk-py","owner_avatar_url":"https://avatars.githubusercontent.com/u/135163833?v=4","primary_language":"Python","stars":82,"forks":13,"topics":["generative-ai","good-first-issue","llm","llm-eval","llm-evaluation","llm-evaluation-framework","llm-evaluation-toolkit","llm-tools","llmops","llms-benchmarking","metrics","prompt-engineering"],"archived":false,"github_pushed_at":"2025-02-13T14:48:37+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/parea-ai-parea-sdk-py","markdown_url":"https://www.graphcanon.com/tools/parea-ai-parea-sdk-py.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/parea-ai-parea-sdk-py","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=parea-ai-parea-sdk-py","description":"Python SDK for experimenting, testing, evaluating & monitoring LLM-powered applications - Parea AI (YC S23)","homepage_url":"https://docs.parea.ai/sdk/python","license":"Apache-2.0","open_issues":59,"watchers":1,"ai_summary":"Parea AI's Python SDK provides tools for the development cycle of large language model (LLM) applications including evaluation, experimentation, and monitoring. It supports prompt engineering and metrics-driven benchmarking to facilitate robust development practices.","readme_excerpt":"## Installation\n\n```bash\npip install -U parea-ai\n```\n\nor install with `Poetry`\n\n```bash\npoetry add parea-ai\n```\n\n---\n\n## 🛡 License\n\n\n\nThis project is licensed under the terms of the `Apache Software License 2.0` license.\nSee [LICENSE](https://github.com/parea-ai/parea-sdk/blob/master/LICENSE) for more details.","github_created_at":"2023-07-24T02:57:39+00:00","created_at":"2026-07-15T10:39:40.229341+00:00","updated_at":"2026-10-18T06:00:29.552499+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"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"llm-eval","name":"llm-eval"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"prompt-engineering","name":"prompt-engineering"}],"trust":{"provenance":{"is_fork":false,"github_id":669978952,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-10-18T06:00:28.201Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":611,"last_release_at":"2025-02-13T14:48:37Z","stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"last_scan_at":"2026-07-15T10:39:42.62562+00:00","scan_profile":"deps","status":"no_lockfile","critical_count":0,"high_count":0,"medium_count":0,"low_count":0,"scanner":"osv@v1","scan_id":"6ce8d286-c787-4b31-999e-96409009f27d","pending_review_count":0}},"capability_facts":{"mcp":{"method":"github-tree-and-contents@2","reason":"No explicit MCP server declaration was found in the inspected manifests. Other layouts and implementations were not tested.","source":"repo_scan","status":"unknown","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","observed_at":"2026-10-18T06:00:28.526Z","server_manifest":null},"scan":{"method":"github-tree-and-contents@2","source":"repo_scan","status":"complete","version":2,"coverage":{"scope":"bounded-repository-manifests","tree_complete":true,"selected_files":1,"candidate_files":1},"revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","observed_at":"2026-10-18T06:00:28.526Z","observations":[{"path":"@revision","bytes":4834,"status":"present","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/commit/968486f9bf7aa4741bb307739f9dec573b30bc95","http_status":200,"observed_at":"2026-10-18T06:00:28.695Z"},{"path":"@tree","bytes":53659,"status":"present","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","http_status":200,"observed_at":"2026-10-18T06:00:28.890Z"},{"path":"docker-compose.yml","reason":"not-listed-in-complete-tree","status":"not-found","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","observed_at":"2026-10-18T06:00:28.891Z"},{"path":"Dockerfile","reason":"not-listed-in-complete-tree","status":"not-found","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","observed_at":"2026-10-18T06:00:28.891Z"},{"path":"mcp.json","reason":"not-listed-in-complete-tree","status":"not-found","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","observed_at":"2026-10-18T06:00:28.891Z"},{"path":"package.json","reason":"not-listed-in-complete-tree","status":"not-found","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","observed_at":"2026-10-18T06:00:28.891Z"},{"path":"pyproject.toml","bytes":4162,"status":"present","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/blob/968486f9bf7aa4741bb307739f9dec573b30bc95/pyproject.toml","http_status":200,"observed_at":"2026-10-18T06:00:29.108Z"},{"path":"server.json","reason":"not-listed-in-complete-tree","status":"not-found","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","observed_at":"2026-10-18T06:00:28.891Z"}]},"has_cli":{"value":true,"method":"repository-declaration@2","source":"pyproject.toml:[tool.poetry.scripts]","status":"declared","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/blob/968486f9bf7aa4741bb307739f9dec573b30bc95/pyproject.toml","observed_at":"2026-10-18T06:00:28.526Z"},"languages":{"value":["python"],"method":"github-tree-and-contents@2","source":"github.language+pyproject.toml","revision":"968486f9bf7aa4741bb307739f9dec573b30bc95","source_url":"https://github.com/parea-ai/parea-sdk-py/tree/968486f9bf7aa4741bb307739f9dec573b30bc95","observed_at":"2026-10-18T06:00:28.526Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-10-18T06:00:28.526Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["For teams prioritizing metrics-driven benchmarking of prompt-engineered applications","When needing integrated tools for the entire lifecycle of large language model projects"],"when_not_to_use":["If requiring a tool focused solely on model training without evaluation and monitoring features","Teams that prefer frameworks exclusively tailored to non-LLM AI application development might find Parea SDK Py less suitable as it focuses heavily on LLM applications"],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:06:56.187Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Unverified catalog guidance: Parea SDK Py is a Python library specializing in LLM app development tasks such as experimentation, testing, evaluation, and monitoring."}]}}