Memory & Knowledge MCP Servers for DeepSeek Harness

Biologically-inspired persistent memory engine for Claude Code MCP agents

Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.

Knowledge Graph CLI and MCP server - interact with knowledge graph systems

MCP server for enabling the named memory graphs to be persisted to a qdrant instance.

MCP bridge for Compy — let your AI agent search and read the highlights, notes & tasks you captured on the web.

Memory MCP server for Claude Code. Correct a fact and the old version stops being recalled.

MCP server for Obsidian-based second brain memory using PARA methodology

Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.

Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.

NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.

Multi-agent shared brain across Claude, Codex, Antigravity, Gemini, Copilot, and VS Code.

Provenance-first research memory with hash-bound evidence and a fail-closed eligibility gate.

Local YouTube memory: transcribe, embed and search videos, with summaries and highlights.

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.

MCP server for AI agent read/write access to Obsidian vaults via EVC Team Relay.

MCP server for Get Notes API integration - AI-powered knowledge base search and retrieval

SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.

Local Zotero, MinerU, Obsidian literature workflow with transactional Analysis notes.

Authority-weighted memory graph for AI agents with conflict detection and semantic search.

An MCP server for creating, reading and editing Obsidian Canvas files.

A Model Context Protocol server for accessing GitHub repositories containing Obsidian vaults