MCP servers for long-term-memory

Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP serve

Typed long-term memory for AI agents. One core, an MCP server, and a Hermes plugin.

Long-term memory for AI coding agents (Claude Code, Codex, opencode) as a tree of plain files

蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.

Epistemic belief state updater and contradiction detector resolving knowledge graph assertion conflicts

Epistemic belief state updater and contradiction detector resolving knowledge graph assertion conflicts

Continual few-shot exemplar distiller mining high-scoring execution trajectories into prompt demonstrations

Ebbinghaus forgetting curve auditor calculating retention probabilities and executing garbage collection

Two-tier memory consolidation engine distilling ephemeral working memory into persistent episodic knowledge

Ebbinghaus forgetting curve auditor calculating retention probabilities and executing garbage collection

Continual few-shot exemplar distiller mining high-scoring execution trajectories into prompt demonstrations

Two-tier memory consolidation engine distilling ephemeral working memory into persistent episodic knowledge

Hierarchical semantic chunk re-ranker evaluating hybrid keyword and dense relevance scores for agentic RAG

Hierarchical semantic chunk re-ranker evaluating hybrid keyword and dense relevance scores for agentic RAG

Long-term memory for CLI agents — cross-CLI, cross-project, cross-session. OKF Wiki + MCP server, model-agnostic.

Turbovec MCP Server: A local Retrieval-Augmented Generation (RAG) tool that allows AI to seamlessly read, chunk, remember, and semantically search through large project codebases.

Local-first long-term memory for AI agents - plain Markdown vault + thin MCP server. CJK-aware BM25, token-efficient by design.

Persistent long-term memory for Claude — an MCP server with an associative memory bank, a canonical-fact cortex, sleep-like dream consolidation, and a web console. Not quite alive.

Turbovec MCP Server: A local Retrieval-Augmented Generation (RAG) tool that allows AI to seamlessly read, chunk, remember, and semantically search through large project codebases.

Local-first MCP memory server — Memory + CodeGraph + Wiki in one SQLite file. Tree-sitter code indexing, markdown wiki, lifecycle hooks, auto-capture. No API key, no cloud.

🧠 Mnema — Long-term memory for AI via MCP × Vector DB. Pluggable backends, hybrid search, Auto Dream consolidation, CLI + REST API + SDK.

Long-term memory MCP server for AI coding agents. SQLite + FTS5 + vector search, CodeGraph, error learning, compaction survival. Beats Mem0 on benchmarks. No cloud, no API key.

Local-first AI brain for personal relationships and communication, powered by MCP｜多平台身份图谱、关系记忆、回复策略与受控自动回复

One memory for every AI agent — self-hosted long-term memory over MCP/REST for Claude Code, Codex, Cursor, Gemini CLI, VS Code, OpenClaw, and more.

Long-term memory for coding agents. The sepiace plugin for Claude Code and Codex.