Memory & Knowledge MCP Servers for DeepSeek Harness

Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

AI agent memory & knowledge graph, hosted in Germany (GDPR). Recall, relations, store via MCP.

Portable cognitive engine for AI agents — storage, embeddings, memory, FSRS, and MCP server

Give AI agents access to your Obsidian vault via local files or Self-hosted LiveSync.

Local-first shared memory for AI tools. Your files, encrypted at rest by default; budgeted reads.

Validate, search, graph, and safely author local Open Knowledge Format bundles.

Token-lean memory for AI agents: a knowledge graph searched cheaply. Drop-in for server-memory.

Local-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.

Persistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools

Shared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.

Local markdown notes: ranked + semantic search, tags, todos, and a wiki-link knowledge graph.

CogMemory MCP Server — Unified context subsystems for AI coding agents

AI-powered reading triage MCP. 26 tools with a 24h burn timer. Read less, absorb more.

Shared, persistent memory for AI assistants, built on the Zettelkasten method.

MCP server for little big brain — graph and hybrid search tools for agents

Pseudolife persistent long-term memory for MCP-compatible coding agents

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

Filesystem-first MCP for Obsidian — an LLM-maintained wiki inspired by Karpathy's LLM Wiki.

Local repo memory for coding agents: ranked files, context packs and a code graph for any task.

An MCP server for managing your personal knowledge, daily notes, and reusable prompts via GitHub Gists.

hmem — persistent, hierarchical, humanlike memory for AI agents (MCP). Because sessions shouldn't start from zero.