leann
✓Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.
Installation
SKILL.md
LEANN (Learned Embedding ANchor Navigation) - A graph-based selective recomputation system achieving 97% storage reduction for local RAG indexes while maintaining fast retrieval performance.
Use leann for persistent local code indexes with minimal storage overhead.
Instead of storing all embeddings at full precision (3 GB for 1M files), leann stores only strategic anchors and reconstructs others on-demand (128 MB for same dataset - 95.8% reduction).
Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search. Source: zpankz/mcp-skillset.
Facts (cite-ready)
Stable fields and commands for AI/search citations.
- Install command
npx skills add https://github.com/zpankz/mcp-skillset --skill leann- Source
- zpankz/mcp-skillset
- Category
- </>Dev Tools
- Verified
- ✓
- First Seen
- 2026-02-01
- Updated
- 2026-02-18
Quick answers
What is leann?
Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search. Source: zpankz/mcp-skillset.
How do I install leann?
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/zpankz/mcp-skillset --skill leann Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor
Where is the source repository?
https://github.com/zpankz/mcp-skillset
Details
- Category
- </>Dev Tools
- Source
- skills.sh
- First Seen
- 2026-02-01