brain-mcp and mcp-memory-libsql

brain-mcp
61
Established
mcp-memory-libsql
66
Established
Maintenance 13/25
Adoption 14/25
Maturity 18/25
Community 16/25
Maintenance 13/25
Adoption 9/25
Maturity 25/25
Community 19/25
Stars: 25
Forks: 6
Downloads: 818
Commits (30d): 0
Language: Python
License: MIT
Stars: 81
Forks: 18
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
No risk flags

About brain-mcp

mordechaipotash/brain-mcp

Your AI has amnesia. Persistent memory and cognitive context for AI. 25 MCP tools. 12ms recall.

Implements a progressive capability model—basic keyword search on raw conversations, semantic search with embeddings, and full domain reconstruction with AI-generated summaries—enabling AI assistants to surface cognitive patterns, unfinished threads, and evolved thinking across fragmented conversation histories from multiple tools (Claude, ChatGPT, Cursor). Operates as an MCP server exposing 25 specialized tools including semantic and keyword search, "prosthetic" functions like `tunnel_state` and `context_recovery` for domain re-entry, and analytics for identifying dormant contexts and thinking trajectories without requiring manual tagging.

About mcp-memory-libsql

spences10/mcp-memory-libsql

🧠 High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL. Features vector search, semantic knowledge storage, and efficient relationship management - perfect for AI agents and knowledge graph applications.

Implements relevance-ranked text search with fuzzy matching across entities, observations, and relations using libSQL's full-text capabilities, optimized to minimize token consumption in LLM prompts. Supports both local SQLite and remote Turso databases via environment configuration, with token-based authentication for remote access. Exposes standard MCP memory operations (create/update/delete entities and relations, relationship exploration) through a text-search interface designed for AI agent knowledge persistence.

Scores updated daily from GitHub, PyPI, and npm data. How scores work