Skip to main content
Back to all repositories

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

44stars6forks0watchers/subscribers4issues
ai-toolsbm25claude-codeclaude-code-plugincontext-compressioncontext-optimizationcost-optimizationdeveloper-productivityembeddingshybrid-retrievalllmllm-toolslocal-firstopen-sourcepythonragsemantic-searchsqlitetoken-reductiontree-sitter
Language
Python
License
MIT License
Size
473 KB
Created
Apr 1, 2026
Last Updated
Sep 3, 2026
Last Pushed
May 2, 2026

Available Plugins

Loading plugins...

Evaluate before installing

  1. Review the source repository, recent maintenance, and license on GitHub.
  2. Read the marketplace manifest and plugin source files before running commands.
  3. Start with the smallest required permission set and validate behavior in a safe environment.