GraphCanon updated 3w · GitHub synced 3w
Decision brief
A specialized benchmarking suite for optimizing chunking strategies in RAG corpora, offering a comprehensive toolkit inclusive of CLI and server components.
Good fit when
- - You are working specifically with retrieval-augmented generation (RAG) systems which require tailored optimization and evaluation.
- - The need arises to evaluate different chunk sizes and configurations for your RAG corpus using an automated recommendation system.
Avoid when
- - If you do not deal with RAG systems or if the nature of your workflow does not benefit from specific optimizations in text chunking strategies across a corpus.
- - You are working on projects that don't necessitate evaluation and optimization at the level provided by 'chunktuner', such as simpler tasks that can be managed without extensive configuration tools.
- Pricing:
- freemium - Open source with an MIT license, offering free use for both personal and commercial projects. No costs beyond typical computing resources are implied by its usage.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (41d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- 2 low (2 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install chunktunerSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Provides a benchmarking suite to evaluate different chunking strategies on a retrieval-augmented generation (RAG) corpus. Includes tools for recommendation, evaluation, and optimization of configurations.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 1, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 1, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
Install (pick one)
uv tool install chunktuner pip install chunktuner
See cost estimate before running anything
chunk-tune estimate ./my_docs --use-case rag_qa
Installation options
pip install chunktuner # CLI + library
uv add chunktuner # library
uv tool install chunktuner # global CLI
uvx --from chunktuner chunk-tune … # ephemeral CLI (no install)
For agents
This page has a .md twin and JSON over the API.