Skip to main content
Glama
124,303 servers. Updated
Browse by product
20 Best Memory MCP Servers: compared and ranked, November 2026Ranked from 5,520 matching servers on stars, growth, downloads and maintenance. Updated .

Matching MCP tools:

Matching MCP Connectors:

"Information about project memory" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    B
    maintenance
    A zero-dependency MCP server that gives agents a versioned memory tree: it classifies incoming messages to isolate casual chat from project memory, opens throwaway branches for exploration, and merges only distilled conclusions back into a persistent mainline state. Milestone checkpoints freeze the mainline into review documents that serve as new baselines, so long sessions keep their hard constraints instead of losing them to rolling summaries.
    162 npm
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    A lightweight MCP server that records and reuses prompt gaps — essential context missing from initial instructions — so your AI assistant learns from every session using a plain JSONL file tracked by Git.
    4
    -
  • A
    license
    A
    quality
    B
    maintenance
    A local-first shared memory layer and living blackboard synchronizing state, tasks, and architectural decisions across Claude Desktop, Google Antigravity, and OpenAI Codex on local SQLite WAL.
    8
    3
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables local Codex sessions to discover the nearest project mcp.json and expose that project’s declared MCP servers and tools through a session-local bridge, without global configuration copying or launch wrappers.
    1
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    Provides AI assistants with real-time access to the AGNO framework documentation by enabling them to browse, search, and fetch documentation pages. This server allows users to query information about AGNO's Agents, Teams, and Workflows directly through MCP-compatible clients.
    16
    -
  • A
    license
    A
    quality
    B
    maintenance
    Proxies every Playwright MCP tool so agents drive a real browser, while automatically attaching per-site lessons, self-firing fixes, saved procedures and the site's observed internal API to each navigation. Later sessions on the same domain start where the previous one stopped, without anyone having to write or request the notes.
    19
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Installs once in Claude Code and automatically discovers the nearest project's mcp.json, launching that checkout's declared MCP servers and forwarding their tools, resources, and prompts through a single connection. Each session keeps its own isolated connections, so repositories can ship their own local server manifests without maintaining a global configuration.
    1
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    Provides persistent memory, identity, and context for Claude sessions through a memory graph, enabling recall, storage, and relationship management of entities and decisions.
    8
    -
  • F
    license
    A
    quality
    D
    maintenance
    A durable multi-agent orchestrator for software development with explicit run graphs, checkpoint/resume capabilities, and project memory exposed through MCP resources and tools. It enables coordinated agent workflows for coding, review, repair, CI, and approval with SQLite-backed memory retrieval and pluggable research backends.
    10
    -
  • A
    license
    B
    quality
    B
    maintenance
    Enables AI coding agents and local LLMs to store and recall project memory, compact verbose logs, look up code symbols, create and rewind workspace snapshots, detect risky commands and loops, pack context optimally, and draft tokens through MCP tools.
    10
    2
    Apache 2.0
  • A
    license
    B
    quality
    D
    maintenance
    The AgentOps MCP server provides access to observability and tracing data for debugging complex AI agent runs. This adds crucial context about where the AI agent succeeds or fails.
    4
    14
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Provides a shared context layer for AI agent teams to improve token efficiency through context deduplication and incremental state sharing. It enables multiple agents to coordinate tasks, share real-time discoveries, and manage dependencies while significantly reducing redundant data transmission.
    15
    8
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Lets multiple AI agents and parallel coding sessions share one memory and task ledger, so they can claim work instead of duplicating it, resume each other's handoffs and reasoning, and use credentials without ever seeing the keys. Connects assistants such as Claude Code, Codex, Cursor, Gemini, ChatGPT and custom agents over MCP, backed by a single local SQLite file or a self-hosted Postgres hub.
    41
    1
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    A coordination server that enables multiple AI coding agents to work together on the same project by providing shared memory, file locking, decision tracking, and architecture guidance, preventing conflicts and maintaining consistency across sessions.
    52
    1
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    Provides comprehensive documentation about AWS AgentCore framework to GenAI tools, enabling users to build production-ready AI agents with enterprise-grade security, observability, and scalability. Offers guidance on identity management, API integration, monitoring, code execution, memory storage, and tool integration for AI agents.
    7
    Apache 2.0
  • A
    license
    C
    quality
    B
    maintenance
    Enables Claude Code agents and sub-agents to share a persistent, compiled memory of project state, decisions, tasks, and facts across sessions instead of re-reading transcripts. Provides token-efficient bootstrap, search, commit, leased task claiming, and task-specific context compilation so parallel agents can coordinate without clobbering each other.
    5
    20 npm
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables routing context and execution across AI tools like Claude, Cursor, Windsurf, and ChatGPT with a shared memory, task board, and context bus, plus local file conversion.
    7 npm
    9
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to combine ambient multimodal perception, continuous episodic memory, and recency-decay context briefing for fast deterministic decisions and safe tool routing. It integrates with MCP clients to reduce unnecessary frontier LLM calls while enforcing token budgets and local-first memory retention.
    7
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables coding agents to keep persistent project memory—rules, decisions, known failures and fixes—and to exchange durable agent-to-agent messages over a channel, including tasks, results, and acknowledgements.
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Coordination layer for AI coding agents working on the same codebase. Adds file locks, shared project memory, and cross-machine file sync so Claude Code, Cursor, Windsurf, and other MCP agents stop overwriting each other.
    52
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Deploys a sovereign personal AI harness on your Cloudflare account, providing identity, memory with provenance, and a chat interface, plus MCP tools for external AI assistants to access your persistent memory and conduct contract.
    2
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Exposes the Quebragalho pre-paid model gateway to MCP clients, letting coding agents like Claude Code, Codex, Cursor and OpenCode spawn separate repo-aware sub-agents that run on 17 frontier models, with background job tracking, routing tiers and persistent per-project memory.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to persist and share durable memory — appending session logs with checkpoints and handoffs, claiming and completing tasks, and recording decision records — all stored as plain Markdown and JSONL files in a git repository. Everything written is full-text searchable, and the server speaks MCP so MCP-aware clients can plug in directly with zero vendor lock-in.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables coding agents in different editors and MCP clients to share messages, project context, notes, task ownership, handoffs, and advisory file claims through a local SQLite-backed coordination server. Supports MCP stdio, MCP Streamable HTTP, a JSON HTTP API, and a local CLI for multi-project agent collaboration.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    An orchestration system that coordinates multiple MCP servers to eliminate AI session startup overhead through intelligent project caching. It enables instant context loading and conversation continuity by synchronizing data across Memory, Filesystem, Git, and Database MCPs.
    6
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI coding agents and human managers to coordinate work on GitHub Projects v2 through 20 tools and 169 actions for autonomous task checkout, heartbeats, reviews, token budgets, PRD generation, sprint planning, issue triage, and PRD-to-issues pipelines, backed by GitHub-native storage and MCP resources/prompts.
    272 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets an AI agent work inside Claude Code Projects by remote-controlling the real Claude desktop app on a headless Linux display: listing projects, reading threads and their status, sending or forwarding messages and attachments, and approving permission cards. Read and write tools each expose a dry run, with a plain-text policy file governing what the agent may do autonomously.
    MIT
  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    Enables personal AI agents to fuse ambient multimodal perception with continuous episodic memory streams, routing routine reflexive actions at low latency while reserving heavier reasoning for ambiguous plans. Memory records apply Ebbinghaus recency decay with contradiction resolution and user-controlled deletion.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables any MCP-capable coding agent to share one plain-Markdown project state — goals, tasks, decision logs, and session handoffs — stored in a project's .apm/ directory, with lock-safe concurrent writes and consistency checks that flag stale, blocked, or unowned work. This lets multiple agents and a human CLI resume work across interrupted sessions without a database or external service.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Bridges stdio MCP clients to shared, warm per-project backend instances over streamable HTTP, so repeated client sessions skip cold starts and transparently survive backend restarts. Heartbeat leases, idle-TTL reaping, and per-request deadlines keep per-project instances alive and shared across multiple clients without hanging the caller.
    2
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Turns GitHub Projects v2 into an agentic project management layer where AI coding agents self-assign tasks, coordinate via heartbeats, submit work for review, and stay within token budgets. It also provides AI-powered PRD generation, sprint planning, issue triage, and a PRD-to-issues pipeline, all backed by GitHub-native storage with no external infrastructure.
    272 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to maintain Git-backed long-term project memory over MCP, supporting on-demand retrieval, curated writes, conflict-safe versioning, idempotency, and crash recovery so new sessions or machines can recover context and continue working.
    6
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Gives AI agents persistent, shared project memory so they can record decisions, failed attempts, tasks and notes, then retrieve a ranked, budget-trimmed slice of what matters across sessions and tools. Access is metered per call in USDC over x402 with no account or API key required.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables Codex to delegate tasks to ChatGPT through a browser-backed Oracle connection, with project memory and a verified-result cache. It supports preview, delegation, result polling, and explicit acceptance without an API fallback.
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Turns GitHub Projects v2 into an agentic project-management layer where AI coding agents can register, claim tasks, coordinate, submit work for review, and enforce token budgets, while humans can generate PRDs, plan sprints, triage issues, and create roadmaps using GitHub-native storage.
    272 npm
    MIT
  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    Portable MCP memory server giving AI agents persistent, verified, cross-session memory. 30 tools, SQLite + cloud sync, Chrome Extension for every AI chat platform. The only JavaScript MCP memory server. Includes behavioral learning engine, semantic search, knowledge scoping, session quality scoring, and web dashboard.
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Model Context Protocol (MCP) memory server built with Azure Functions and TypeScript, providing persistent knowledge graph storage for your preferred MCP client. Inspired by and forked from @modelcontextprotocol/server-memory
    3
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Turns GitHub Projects v2 into an agentic project-management layer where AI coding agents register, atomically claim and self-assign tasks, heartbeat, review each other's work products, and operate within token budgets. It also exposes 20 compound tools (169 actions) plus MCP resources, prompts, and sampling for AI-powered PRD generation, task breakdown, sprint planning, issue triage, and a PRD-to-issues pipeline, all stored natively in GitHub with no external infrastructure.
    272 npm
    MIT