Repository Index

[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

• ai
• faiss
• langchain
• llama-index

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

• agent
• llm
• memory
• long-term-memory

TranslatedA context-compression plugin for month-long single sessions (billions of tokens) ,small context windows (a 100K context is enough) and token savings (5x fewer tokens) . Context compression plugin for month-long sessions, balancing small windows (a 100k context is enough) and saving tokens (5x fewer tokens). billion-context is all you need

• dsh-plugin

Translated🍟 McD Saver (麦麦省钱助手, "McDonald's money-saving assistant") — a money-saving ordering Agent Skill built on McDonald's China's official MCP: real-time price verification via the official calculate-price, coupon combination optimization, sunk-cost check-up and multi-order coupon scheduling, and final prices calculated on the same basis across four channels: official coupons, set meals, group-buy vouchers, and points. Online price estimation without login.

• agent-skill
• mcdonalds
• mcp
• python

MCP server for Git with local Ollama — zero tokens for git operations

• ai-agents
• claude-code
• conventional-commits
• developer-tools

MCP server for SuperScalar — Bitcoin Lightning channel factories. Query protocol specs, estimate UTXO savings, and explore factory architectures.

• bitcoin
• channel-factory
• layer2
• lightning