Knowledge & Memory

Secure, fragment-based long-term memory for MCP-compatible AI agents.

Two-layer memory for AI agents with an immune system. Zero dependencies.

Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.

Local-first persistent memory for AI coding agents.

Persistent memory for AI agents with rollback, audit trails, and semantic search.

Microsoft Graph MCP server — 85 tools for mail, calendar, Teams, files, SharePoint, and Entra ID

Cross-machine, file-first memory for Claude Code: markdown + SQLite FTS5, synced with git

Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.

An MCP server that provides visual memory and context storage with knowledge graph capabilities

Persistent coding memory for AI assistants. MCP stdio, hybrid search, graph, context.

Local knowledge graph memory MCP server for AI assistants.

Neo4j MCP Canary — The canary goes first so the rest of us know what's coming

Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

Token-efficient code review knowledge graph: semantic search and call-graph resolution.

Shared workspace your AI agent writes to. 184 tools, persistent memory, semantic search.

Local-first durable AI memory with policy-bound recall and a typed project graph.

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.

Persistent cross-project memory for Cursor and Claude Code using local semantic search.

Project knowledge graph with history-checked belief staleness, changeset proposals, cost reporting

Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)