{"data":{"slug":"shantanu-deshmukh-chunktuner","name":"chunktuner","tagline":"Benchmark and optimize chunking strategies for RAG corpus","github_url":"https://github.com/shantanu-deshmukh/chunktuner","owner":"shantanu-deshmukh","repo":"chunktuner","owner_avatar_url":"https://avatars.githubusercontent.com/u/2664513?v=4","primary_language":"Python","stars":2,"forks":0,"topics":["chunking","embedding","evaluation","langchain","litellm","llamaindex","llm","mcp","optimization","rag","ragas","retrieval","text-splitting","vector-database"],"archived":false,"github_pushed_at":"2026-06-21T06:26:13+00:00","maintenance_label":"Steady","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/shantanu-deshmukh-chunktuner","markdown_url":"https://www.graphcanon.com/tools/shantanu-deshmukh-chunktuner.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/shantanu-deshmukh-chunktuner","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=shantanu-deshmukh-chunktuner","description":"Benchmark chunking strategies for your RAG corpus. Get a recommended config. CLI, Python library, and MCP server.","homepage_url":"https://shantanu-deshmukh.github.io/chunktuner/","license":"MIT","open_issues":0,"watchers":0,"ai_summary":"Provides tools for evaluating and optimizing chunking strategies for Retrieval-Augmented Generation (RAG) systems, including a CLI, Python library, and MCP server.","readme_excerpt":"# Install (pick one)\nuv tool install chunktuner\npip install chunktuner\n\n---\n\n# See cost estimate before running anything\nchunk-tune estimate ./my_docs --use-case rag_qa\n\n---\n\n## Installation options\n\n```bash\npip install chunktuner                 # CLI + library\nuv add chunktuner                      # library\nuv tool install chunktuner             # global CLI\nuvx --from chunktuner chunk-tune …     # ephemeral CLI (no install)","github_created_at":"2026-05-02T06:35:01+00:00","created_at":"2026-07-11T23:05:12.5387+00:00","updated_at":"2026-09-20T04:28:50.023629+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"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":"chunking","name":"chunking"},{"slug":"embedding","name":"embedding"},{"slug":"evaluation","name":"evaluation"},{"slug":"langchain","name":"langchain"},{"slug":"litellm","name":"litellm"},{"slug":"llamaindex","name":"llamaindex"},{"slug":"llm","name":"llm"},{"slug":"mcp","name":"mcp"}],"trust":{"provenance":{"is_fork":false,"github_id":1227063460,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:10:40.263Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":89,"last_release_at":"2026-05-10T18:41:13Z","stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"mcp_manifest@v1","low_count":2,"high_count":0,"last_scan_at":"2026-09-18T08:10:42.537Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:10:39.065Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-18T08:10:39.065Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:10:39.065Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:10:39.065Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to benchmark and optimize chunking strategies specifically for Retrieval-Augmented Generation (RAG) systems.","If you are working with a RAG corpus and require a recommended configuration for chunking strategies.","When you want to estimate costs before running evaluations on your corpus."],"when_not_to_use":["If your project does not involve Retrieval-Augmented Generation (RAG) systems, as Chunktuner is specialized for RAG.","If you do not require a Python-based solution or do not wish to use a tool that provides both a CLI and a Python library.","When you are looking for a tool that does not offer a cost estimation feature before running evaluations."],"source":"enrich:decision_facts","observed_at":"2026-09-18T12:02:11.375Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Chunktuner is a Python-based tool for benchmarking and optimizing chunking strategies in Retrieval-Augmented Generation (RAG) systems. It offers a CLI, Python library, and MCP server to evaluate and optimize text-split,朱"}]}}