Memory MCP servers

Local-first persistent memory for AI coding agents.

Persistent agent memory with Ebbinghaus-style decay, hybrid BM25/vector retrieval, entity graph for multi-hop reasoning, auto-pruning and a browser dashboard.

Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.

Self-hosted AI studio exposing local image, video and music-video generation, upscaling, RAG and code intelligence, with renders queued on your own GPU.

Local institutional memory for agents where BFT consensus among validators approves every memory before it is committed.

Persistent memory for AI agents — 55 MCP tools, spreading activation recall.

Free, open-source memory for Claude Code. Remembers why decisions were made and maps your code. Your own database (SQLite, Postgres or MongoDB), no cloud, no subscription.

Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.

Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.

x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.

IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.

3D avatars, embeds, glTF tools, agent memory, and on-chain agent identity from three.ws.

Read, write and scan process memory, Cheat Engine style, on Windows, Linux and macOS.

Local-first persistent memory for coding agents with semantic search, auto-capture, cross-session learning and intelligent forgetting.

Reusable project context and specialist workflows for the AI tools you already use. AIWG places agents, skills, commands, and rules in provider-readable locations, with optional utilities for artifact memory, workflow orchestration, recovery, and discover

On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.

Agent memory with semantic, episodic and procedural types, a knowledge graph, Claude Code auto-save/recall hooks, smart triggers and multi-user isolation.

Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.

Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more

Cumulative memory and pattern learning for coding assistants, with local SQLite/SurrealDB storage for semantic codebase analysis.

Use Weaviate collections as a knowledge base and as a chat memory store.

Stateful layer over real language servers: persistent sessions keep indexes warm, and speculative execution simulates edits in memory before writing to disk.

Session memory for coding agents: local-first recall, drift detection, on-device inference.

Local SQLite agent memory with a web dashboard, session rewind/replay, cross-client memory sharing, morning briefings and progressive context loading.

Alibaba Cloud Tablestore: add documents and search them semantically by vectors and scalars, suited to serverless RAG.

LLM-driven context and memory management: short- and long-term memory with vector, timeline and knowledge graph retrieval plus reranking.

Private-by-default memory and context layer for agents with staged retrieval across fused data backends and long-horizon context continuity.

Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.

Ghidra plugin for binary analysis: function inspection, decompilation, memory exploration and import/export analysis.

Zettelkasten-based agent memory system with bidirectional links

Cross-session memory for AI coding agents via six tools; local-first SQLite store.

Primitive RAG-like web search that runs locally, without external APIs.

Local-only MCP server for source-attributed Markdown memory and documentation retrieval.

Persistent local memory for coding agents that retires replaced facts at write time, so agents read the current answer; facts are typed with provenance.

Automatic project memory for Claude Code. Also works with Cursor and Codex.

Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients

Mem0-compatible persistent memory for AI agents: write facts once, recall them semantically.

Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.

Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.

Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.

Self-hosted mem0 for Claude Code: Qdrant vector search, Neo4j knowledge graph, Ollama embeddings and session hooks for automatic cross-session memory.

Production-ready RAG out of the box to search and retrieve data from your own documents.

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.

Persistent memory + git snapshots for Claude Code. Never lose context or code.

Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine

Persistent memory and full-text search over Claude Code conversation history indexed into SQLite, with session summaries and a web UI for exploration.

Universal memory runtime for AI agents — episodic, semantic, and procedural memory.