mem9

by luuhung93 · ai-ml · mcp-server, glama

Easy setupBest for experimentalTrust score 8/100

Mem9 is an open-source, project-scoped memory service for Codex, Claude, and other MCP-compatible coding agents. It keeps durable project knowledge and CLI session metadata available across tools and conversations.

Source: https://github.com/luuhung93/mem9

Install

git clone https://github.com/luuhung93/mem9

Use this forAI-extracted

  • Maintain persistent project context across multiple AI agent sessions without re-explaining code structure
  • Track conversation history and decisions made during coding tasks to enable coherent multi-turn interactions
  • Store and retrieve project-specific metadata (dependencies, architecture notes, naming conventions) for consistent agent behavior

Works with

CodexClaude CodeClaude Desktop

Tags: mcp-server, glama

Source: glama

About ai-ml MCP servers and Claude skills

ai-ml MCP servers extend what AI agents can do inside Claude Code, Cursor, Copilot, Codex, and Windsurf. The Skiln directory indexes 16,000+ such integrations across 22 categories.

mem9 is one of hundreds of ai-ml entries indexed on Skiln. Browse the full ai-ml category or the complete directory of Claude skills, MCP servers, agents, commands, and hooks.

Related ai-ml MCPs and skills

  • Stonks by priyanshu-liveflow

    Automates stock analysis and news updates in Google Sheets using AI-powered insights, enabling users to manage stock data and generate comprehensive analysis through natural language.

  • hotcopper-mcp by mKlus

    Unofficial MCP server for HotCopper, enabling AI agents to search, read, and reply to ASX share-trading forum posts via reverse-engineered HTML parsing.

  • Invoice MCP Server by suriya-narayanan-2526

    Allows AI clients like Claude and Cursor to authenticate and interact with an invoice generator backend, enabling login, invoice creation, and invoice download.

  • langfuse-observability-mcp by Sesame2

    A read-only MCP server that enables agents to query and analyze Langfuse observability data, including traces, sessions, observations, scores, and metrics.

  • Blender MCP NextGen by Mehulpatel05

    Connects AI assistants to Blender 3D for natural language 3D modeling, scene inspection, material creation, and rendering.

  • multicomp-mcp by cameroncoats

    Enables control of the Multicomp Pro MP711134 bench power supply and multimeter over USB serial, allowing an LLM agent to power-cycle boards, measure current profiles during boot, run custom voltage/current profiles, and wait for conditions without polling.

  • echo-cache by SanjoyDat1

    Semantic caching MCP server for AI agent tool calls, providing exact and similarity-based cache lookup, store, invalidation, and metrics via MCP tools.

  • ac-infinity-mcp by RohanSan1

    Control and monitor your AC Infinity grow environment through Claude and any MCP-compatible AI assistant. It provides live sensor data, analytics, and the ability to adjust fan speeds or port states using natural language.

Frequently asked questions

How do I install mem9?

Add the install command above to your Claude Code, Cursor, or Windsurf MCP configuration. Most servers register via npx, a local command, or a Docker image. Refer to the source repository for environment variables and credential requirements.

Which clients support mem9?

Any MCP-compatible client works: Claude Desktop, Claude Code CLI, Cursor, Windsurf, Zed, and VS Code with the official MCP extension. OpenAI Codex and GitHub Copilot increasingly support MCP via adapter bridges.

Is mem9 free?

The server itself is typically open source. Any upstream service (API keys, paid tiers, hosted infrastructure) may have its own pricing. Check the source repository for details.