fpytloun/mnemory
A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.
Implements the Model Context Protocol (MCP) as a stateless HTTP server compatible with 10+ AI clients, using a unified LLM pipeline for single-call fact extraction and deduplication. Pairs fast vector-based semantic search with an artifact store (Qdrant + S3/MinIO) for detailed content, includes built-in consistency checking (fsck) for contradiction resolution, and offers a management dashboard plus REST API alongside native MCP tools for flexible integration.
5 stars and 1,328 monthly downloads. Available on PyPI.
Stars
5
Forks
—
Language
Python
License
—
Category
Last pushed
Mar 05, 2026
Monthly downloads
1,328
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/fpytloun/mnemory"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
kayba-ai/agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
MemMachine/MemMachine
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory...
knowns-dev/knowns
The memory layer for AI-native development — giving AI persistent understanding of your software...
Dicklesworthstone/cass_memory_system
Procedural memory for AI coding agents: transforms scattered session history into persistent,...
rexdivakar/HippocampAI
HippocampAI — Autonomous Memory Engine for LLM Agents