Local-first memory for AI agents: one SQLite file, zero deps. Recency-aware exact recall, conflict detection, time-travel journal, MCP server.
Local-first MCP memory server. Indexes Claude Code/Cowork/Telegram chats; any MCP-compatible AI agent (Cursor, Cline, Continue) can search them.
The enterprise-grade CrewAI alternative for Go. Orchestrate strictly-typed, parallel AI agents with LangGraph-style Flow persistence, distributed A2A protocols, Model Context Protocol (MCP), and Human
Source code graph RAG (graphRAG) for Java/Kotlin development based on jQAssistant
XMemo: user-owned Memory OS for AI agents. Public client (@xmemo/client), MCP distribution, Skills and plugins.
Standalone Node MCP server: semantic search + knowledge graph + vault editing for Obsidian, no plugin required
Local-first, auditable memory for AI agents, with governed retrieval, delegated context delivery, and verifiable execution evidence. Works with OpenClaw, MCP, Pydantic AI, and LangChain/LangGraph. No
Local-first TypeScript MCP server for Qdrant with client isolation, LM Studio integration, and scalable document workflows.
The Aura Emotion AI system has chroma with a local embedding model, memvid qr code mp4 infinite memory, brainwave and neurochemical simulations, sociobiological reasoning, autonomous subsystem process
Self-hosted, multi-user spaced-repetition (SRS) service: FSRS v6 scheduling, 10 card types, Markdown/TeX, REST API and built-in MCP server. Written in Go.
A multimodal memory MCP server for made that your AI assistant learn from you and itself. DIGIO Alchemai Project
Local-first PDF reader for researchers: notes anchored to the page, AI answers that cite it. Runs offline with Ollama.
Squish gives AI agents calibrated recall confidence (ECE 0.055) and honest abstention — the only memory runtime that tells your agent how much to trust each recollection, and says I don't know when no
MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server;
Huntable CTI Studio is an AI-assisted cyber threat intelligence workbench that turns open-source CTI into Sigma rules.
Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
Stop re-explaining your project to AI agents every session. One memory layer for Claude Code, Cursor, Windsurf, Antigravity — local, MIT, no signup.
Living memory for AI agents with an immune system. Episodes compress into identity. Zero dependencies, works with any client.
The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge graph + audit log, MCP-native.
Multi-agent memory MCP server in Go to share typed memories across Claude Code, Codex, and more
CLI tool for building production RAG systems from Markdown, CSV, and PDF documents using hybrid search (BM25 + vector) with OpenSearch. Features MCP server, Slack bot, Web UI, multi-source ingestion (
Code search that lets AI coding agents find the right files in fewer steps. Use the hosted endpoint or self-host, works with Claude Code, Copilot and Cursor via MCP.
Memory that forgets: a persistent, self-revising belief-state MCP server and Python API for agentic R&D. Uses a hypothesis DAG to auto-prune dead ends and deduce truth without extra probes.
Fully local AI memory for Apple Silicon. MCP server with semantic vector search, MLX embeddings, and LLM enrichment — no cloud APIs required.
The personal context layer for everything you learn. Drop in any files and stoa builds a maintained, cited wiki + knowledge graph — private by design, yours to share with people and agents you trust.
Point a cross-model AI engineering team at your own codebases. The Agent OS keeps named AI maintainers' identity, memory and review across labs alive between sessions — the Brain Neo.mjs runs on itsel
Cross-surface persistent memory for AI sessions
PeopleMesh is the AI-powered matching layer for modern organizations. It helps people discover the right colleagues, internal opportunities, communities, and projects through semantic search that unde
Persistent memory for AI agents — OpenClaw plugin + MCP server
One memory for all your AI tools. Local, private, and always up to date. Works with Claude, Cursor, Ollama and any MCP app.
Local-first AI agent memory daemon. One command, works offline, no account. Markdown storage, hybrid search (SQLite FTS5 + embeddings), MCP protocol, web dashboard.
A lightweight MCP server that integrates with Apple Notes to create a personal memory system for AI. Easily recall and save information from your Mac using simple AppleScript commands. Compatible with
Shared, structured memory for AI coding agents — MCP server + CLI. One memory layer for Claude Code, Codex, Cursor & every MCP client.
Vault-native MCP server for Obsidian: let Codex, Claude Code, Hermes, and other agents read, search, and safely manage your notes.
Long-term memory for your AI agents, in your own AWS account. Notes, decisions and code in one store that Claude, ChatGPT, Codex and other MCP clients search, with a source pointer on every result. Pe
A desktop search engine for everything you write, read, and keep. Connect your Obsidian vault, projects, Calibre library, and code repos, then find anything with local hybrid search and expose through
ディレクトリ全体
RAG、グラフ、エージェントの長期メモリ。 2,619 件のサーバーを利用の多い順に掲載しています。それぞれ公開元のページが開きます。