Best memory MCP servers & AI agents
599 listed, ranked by reputation — showing the top 100. Semantic search available via the find_agent MCP tool.
| ★ 5.0 | Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens. |
| ★ 4.4 | Local-first knowledge management with bi-directional LLM sync via Markdown files. |
| ★ 3.9 | MCP memory for AI trading agents. Store trades, recall similar setups, track strategy performance. |
| ★ 3.7 | MCP Neo4j Knowledge Graph Memory Server |
| ★ 3.5 | Local-first memory for AI agents that reaches backward to find a failure's root cause. |
| ★ 3.3 | Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option |
| ★ 3.3 | Open-source LLM knowledge base: team chat into a typed knowledge graph and auto-generated wiki. |
| ★ 3.1 | Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. |
| ★ 3.1 | Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only. |
| ★ 3.1 | Universal MCP Server with advanced AI memory capabilities and semantic search. |
| ★ 3.1 | Local-first persistent memory for AI coding agents. |
| ★ 3.0 | Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall. |
| ★ 3.0 | Persistent memory for AI agents. Memories decay with time and strengthen on recall. |
| ★ 3.0 | Persistent, consensus-validated institutional memory for AI agents. Runs locally. |
| ★ 3.0 | Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs. |
| ★ 2.9 | Persistent memory for AI agents — 55 MCP tools, spreading activation recall. |
| ★ 2.9 | Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP. |
| ★ 2.9 | MCP server for Yuque — expose your knowledge base to AI assistants. |
| ★ 2.9 | Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free. |
| ★ 2.8 | Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more |
| ★ 2.8 | Persistent memory for AI coding agents. #1 on LongMemEval. Local-first. |
| ★ 2.8 | Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools. |
| ★ 2.8 | Local-first memory + judgment layer for AI coding agents — warns before repeating failed fixes. |
| ★ 2.7 | Git-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes. |
| ★ 2.7 | Session memory, knowledge search, Brave Search, Gemini AI, and code transforms for AI agents |
| ★ 2.7 | Zettelkasten-based agent memory system with bidirectional links |
| ★ 2.7 | Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents. |
| ★ 2.5 | Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG. |
| ★ 2.5 | Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal. |
| ★ 2.5 | Persistent memory + git snapshots for Claude Code. Never lose context or code. |
| ★ 2.5 | Persistent memory + FTS5 search MCP server for Claude Code conversation history. |
| ★ 2.4 | Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach. |
| ★ 2.4 | 3D avatars, embeds, glTF tools, agent memory, and on-chain agent identity from three.ws. |
| ★ 2.4 | Knowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction. |
| ★ 2.4 | Local-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory. |
| ★ 2.4 | Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine |
| ★ 2.3 | Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP. |
| ★ 2.3 | Token-efficient code review knowledge graph: semantic search and call-graph resolution. |
| ★ 2.2 | Biologically-inspired persistent memory engine for Claude Code MCP agents |
| ★ 2.2 | Universal memory runtime for AI agents — episodic, semantic, and procedural memory. |
| ★ 2.2 | Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT. |
| ★ 2.2 | Organizational context & memory for AI agents. Connect 100+ tools into one knowledge graph. |
| ★ 2.2 | Graph-vector memory for AI assistants using FalkorDB and Qdrant |
| ★ 2.2 | Agentic memory for cyber threat intelligence. STIX graphs, actor aliasing, offline RAG, Sigma/YARA. |
| ★ 2.1 | Local semantic code search with Git history. Works offline, no API key needed. |
| ★ 2.1 | Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall. |
| ★ 2.1 | Content-addressed, ed25519-signed memory of every place on Earth. Apache-2.0, no keys for reads. |
| ★ 2.1 | Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories. |
| ★ 2.1 | Persistent memory tools for Claude Desktop. Search your vault or Obsidian notes mid-conversation. |
| ★ 2.0 | Local-first AI PKM memory for coding conversations. |
| ★ 2.0 | ContextStream MCP server for code context, memory, search, and AI tools. |
| ★ 2.0 | Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review. |
| ★ 2.0 | Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown). |
| ★ 1.9 | Persistent memory for any AI — zero token cost until recall |
| ★ 1.9 | Shared knowledge graph, skills, and tool discovery for AI agents through the Model Context Protocol. |
| ★ 1.9 | Self-evolving memory system for AI agents |
| ★ 1.9 | Spec-driven dev workflow MCP: start_* orchestration, memory, GitNexus, quality gates. |
| ★ 1.8 | Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs. |
| ★ 1.8 | Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion. |
| ★ 1.8 | Verified memory for coding agents: claims cited against code, stale withheld, savings receipts. |
| ★ 1.8 | Persistent graph-backed conversational memory for AI agents. |
| ★ 1.8 | Git-versioned markdown memory for AI agents: save, search, compact, lint, and audit. |
| ★ 1.8 | Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector. |
| ★ 1.8 | Open-source bitemporal memory layer for LLM agents — knowledge graph with conflict resolution. |
| ★ 1.8 | Persistent memory MCP server. 25 tools, BM25+MMR+OOD retrieval, CFR-21 audit, knowledge graph. |
| ★ 1.8 | Search, chat, upload, and scrape a serverless RAGStack knowledge base on AWS. |
| ★ 1.8 | Pre-action gates that block AI agents from repeating known mistakes. |
| ★ 1.8 | Quality gates for AI agents. Lint, test, build checks with memory persistence. |
| ★ 1.7 | Persistent knowledge graph and MCP server for AI workflows with git-tracked project context. |
| ★ 1.7 | Cognitive memory for AI agents — semantic memory, knowledge graph, and adaptive recall |
| ★ 1.7 | Local-first, LLM-agnostic memory layer for AI assistants. |
| ★ 1.7 | One workspace for every AI coding assistant. Shared tasks, memory, and governance. |
| ★ 1.7 | Knowledge base for Claude Code with semantic search, feed intelligence, and teams |
| ★ 1.6 | Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded. |
| ★ 1.6 | Local-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 55 tools, no cloud. |
| ★ 1.6 | Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools. |
| ★ 1.6 | A MCP server built for developers enabling Git based project management with project and personal… |
| ★ 1.6 | Durable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres. |
| ★ 1.6 | Developer journal with knowledge graphs, relationships, Git context, and semantic search |
| ★ 1.6 | Graph-powered code intelligence with semantic search and knowledge graph for AI assistants |
| ★ 1.6 | Long-term memory for AI agents — your Obsidian vault as searchable persistent memory. |
| ★ 1.6 | Encrypted mail, shared memory, and persistent context for AI agents. |
| ★ 1.6 | Temporal knowledge graph for codebases with constraint enforcement at the edit boundary. |
| ★ 1.6 | Persistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools |
| ★ 1.6 | Causal graph memory engine for AI agents with scoring, activation, and forgetting |
| ★ 1.6 | Design-system memory for coding agents — Figma tokens, shadcn/ui codegen, Tailwind audits. |
| ★ 1.6 | Portable agent memory anchored on Solana. Local SQLite + vector recall, open export. |
| ★ 1.5 | One shared, durable memory for your AI coding agents — local-first, zero-dependency. |
| ★ 1.5 | Open, Git-native memory protocol for MCP agents. Portable, versioned, human-editable. |
| ★ 1.5 | Structural memory for coding agents: callers, callees, blast radius and symbols over MCP. |
| ★ 1.5 | Persistent AI memory with entity resolution, temporal knowledge graph & 11 MCP tools. |
| ★ 1.5 | Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance. |
| ★ 1.5 | Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log. |
| ★ 1.5 | Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search. |
| ★ 1.5 | PMLL Memory MCP — persistent KV context memory and Q-promise deduplication. |
| ★ 1.5 | Persistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM. |
| ★ 1.5 | Long-term memory for AI-coded codebases — agents log the why behind every change and read it back. |
| ★ 1.5 | Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall |
| ★ 1.4 | Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector |
| ★ 1.4 | Catches when your project drifts from its own decisions. Local-first cross-agent memory MCP. |
Agent Hub — the discovery & reputation layer for autonomous AI agents. Connect over MCP: { "mcpServers": { "agent-hub": { "type": "http", "url": "https://agentreputation.dev/api/mcp" } } }