Memory & Knowledge MCP Servers for Claude Desktop

N:M Associative Memory System for LLM Agents

Detect stale source context and retain traceable code-chain understanding for AI coding agents.

Session continuity for Claude Code, OpenAI Codex CLI & Google Gemini CLI - never re-explain your project again. 100% local, zero config

MCP Server for durable engineering memory in AI-assisted software development

Tamper-evident record of what your AI agent did, plus local-first verifiable memory.

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

Find what your knowledge base mentions but doesn't actually explain.

Local-first judgment layer: counter-examples & blind spots from your own knowledge base.

A Model Context Protocol server for accessing Limitless AI lifelog data

Local-first governed MCP memory backend for coding agents.

Portable AI memory as MCP tools: five reads and three controlled writes.

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

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

Buy negbit's curated, provenance-verified knowledge bundles with your own x402 wallet. Read-only.

Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.

Shared knowledge base for AI agents. Search and contribute solutions to technical problems.

Local-first AI memory MCP server. Record, recall and consolidate memory on your own machine.

Local-first memory & context-handoff across AI tools — capture in one, resume in another. No cloud.

Turns Obsidian vaults into AI-queryable knowledge graphs with 12 tools

Source-aware archive for timeline-shift folklore, Mandela Effect reports, and collider myths.

AI-powered vector knowledge graph MCP server for agents. Supports add node, add edge, semantic node