sl4m3/ledgermind
LedgerMind — an autonomous living memory for AI agents. It self-heals, resolves conflicts, distills experience into rules, and evolves without human intervention. SQLite + Git + reasoning layer. Perfect for multi-agent systems and on-device deployment.
Implements autonomous knowledge lifecycle management through a hybrid SQLite + Git storage layer with background reasoning workers that run every 5 minutes, continuously detecting conflicts, distilling experience into structured rules, and self-healing corruption via cryptographic audit trails. Exposes 15 MCP-compatible tools with multi-agent namespacing, vector semantic search via GGUF embeddings, and transparent hook injection into Claude Code/Cursor/Gemini CLI for zero-touch memory operations without explicit tool calls.
Available on PyPI.
Stars
9
Forks
—
Language
Python
License
—
Category
Last pushed
Mar 11, 2026
Monthly downloads
816
Commits (30d)
0
Dependencies
17
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/sl4m3/ledgermind"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
doobidoo/mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude....
Dataojitori/nocturne_memory
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to...
mnemox-ai/tradememory-protocol
MCP server for AI trading memory — outcome-weighted cognitive memory with 10 tools, 399 tests.
spences10/mcp-memory-libsql
🧠 High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL....
gannonh/memento-mcp
Memento MCP: A Knowledge Graph Memory System for LLMs