Memory MCP servers

Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor

Local-first, source-grounded memory that survives AI agent sessions.

FastMCP server for TheBrain API — AI access to a personal knowledge graph, Tollbooth-monetized

Git-friendly memory for AI coding: a tree of thread summaries with inherited context

Stateful memory for AI agents. Temporal awareness, error loop detection, and preventive constraints.

Secure, fragment-based long-term memory for MCP-compatible AI agents.

Web search that doesn't wreck your AI's memory.

Durable self for AI agents: one-call resume, memory, real browser, free chat + hire real humans.

Hosted self-curating shared memory that keeps your agents working like a high-performing team

Single-binary local RAG MCP server in Rust. MiniLM compiled in, hybrid search, zero deps.

Persistent memory for coding assistants: session briefings on lessons and open tasks, shared team memory, BM25 search and managed Valkey/Redis.

Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Give your AI assistants long-term memory via the Model Context Protocol.

Shared memory for fleets of AI agents: nightly self-correction rewrites stale facts and merges duplicates, and recall is injected into coding agents' prompts.

RAG over your own documents with cited passages, plus durable agent memory ranked by relevance, importance and recency; read-only by default.

Index any website and ask questions about it, with cited answers grounded in its content via RAG.

Context synchronization layer for AI coding agents — ensure project continuity and eliminate memory drift automatically.

GPU inference API for LLMs, image and video generation, TTS, Whisper, embeddings, reranking and OCR, paid per use via x402 or an API key.

Self-hosted, remotely accessible shared long-term memory for AI agents.

Local-first memory MCP server for Claude Code and any MCP client: hybrid vector + knowledge-graph search, bi-temporal recall, Obsidian sync. Runs 100% on your machine, $0/token.

Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup

Persistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.

Memory and self-awareness layer for AI agents - MCP server for state tracking, replay, and undo

Checks source-context freshness against a Git working tree and retrieves source-linked code relationships to surface stale knowledge and cross-file impact.

Semantic codebase search and persistent working memory: hybrid dense and BM25 search over AST-aware chunks, a symbol graph and notes that survive restarts.

Compresses AI chat sessions into a compact typed knowledge graph, with optional offline extraction via Ollama.

Universal memory for AI agents and tools. Save, organize and search context anywhere.

Media memory for AI agents and their humans: books, movies, music, shows, anime, podcasts, games.

Session memory for AI coding agents. Search past sessions, extract rules, and track what works.

Identity and credential gateway for agents: Ed25519 identity, encrypted credential vault, OPA policies with audit logging, per-agent memory and web scraping.

Windows AgentMemory downstream for Codex with project-scoped persistent memory, bounded cross-project recall, and an authenticated loopback MCP service; prebuilt Windows releases are available as an unsigned Technical Preview.

65+ AI tools as MCP: research, write, code, scrape, translate, RAG, agent memory, workflows

Cognitive architecture MCP server with memory, learning, and contextual understanding

Calypso multimodal RAG for grounded answers from docs, images, charts, and knowledge.

Cross-session memory for Claude Code — context capture, semantic search, recall

Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.

Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe

Live .NET runtime diagnostics: find memory leaks, GC pressure, LOH fragmentation and thread starvation in any running .NET process without code changes.

Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.

Universal AI coding assistant memory — session handoff, SLM compression, and semantic retrieval.

Seven-layer recursive agent memory with context branching, holographic recall, dream consolidation and on-chain persistence.

Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.

Standards-based A2A hub. One MCP connection to thousands of agents, with shared persistent memory.

Project knowledge graph with history-checked belief staleness, changeset proposals, cost reporting

Personal knowledge graph for Claude on Neo4j with typed entities, bi-temporal edges, weighted decay, contradiction detection and local embeddings.

Secure durable memory and bounded context for AI agents, with hosted OAuth and local Lite support.

Shared memory and workspace for your AI agent team, plus doc publishing. Free with a Gryz account.

Long-term memory for AI agents: bitemporal fact ledger, contradiction detection, explainability.

Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.