Skip to main content
Glama
Josan88

agentmem

by Josan88

🧠 agentmem

PyPI Version License: MIT Python 3.10+ MCP Compliant

agentmem is a high-performance, local-first persistent contextual memory & knowledge-base engine designed specifically for AI coding agents (Claude Code, OpenAI Codex, Cursor, Antigravity) and Model Context Protocol (MCP) servers.


🌟 Why agentmem?

AI agents frequently forget critical architectural decisions, environment setup constraints, and session conclusions across chat restarts. agentmem acts as a zero-latency, local memory bank that seamlessly indexes and retrieves codebase knowledge without ballooning prompt token context.

Key Features

  • ⚡ Zero-Latency Local Storage: File-backed JSON key-value & structured memory store.

  • 🔌 Native MCP Integration: Plug directly into Claude Desktop, Cursor, or any MCP-compatible agent.

  • 🏷️ Context Tagging & Retrieval: Store memories tagged by scope (architecture, bugfix, decision, setup, todo).

  • 💻 Intuitive CLI: Query, insert, export, and manage context directly from the terminal.

  • 🛡️ Privacy First: 100% local execution — no external API calls required for storage.


Related MCP server: mcp-chest-memory

🚀 Quick Start

1. Installation

pip install agentmem

2. CLI Usage

# Remember an architectural decision
agentmem add "Used SQLite/JSON for agentmem storage to guarantee single-file zero-dependency portability" --tag architecture

# Query stored memories
agentmem search "SQLite"

# List all memories in the current workspace
agentmem list

# Clear memories
agentmem clear

🔌 Using as an MCP Server

agentmem includes support for Model Context Protocol integration. Add the following to your claude_desktop_config.json or editor settings:

{
  "mcpServers": {
    "agentmem": {
      "command": "agentmem",
      "args": ["mcp"]
    }
  }
}

🤝 Contributing

We welcome community contributions! Please check out CONTRIBUTING.md for setup instructions, coding conventions, and pull request workflows.

  1. Fork the Repository

  2. Create a Feature Branch (git checkout -b feature/amazing-feature)

  3. Commit your changes (git commit -m 'Add amazing feature')

  4. Push to Branch (git push origin feature/amazing-feature)

  5. Open a Pull Request


📄 License

Distributed under the MIT License. See LICENSE for more details.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides a persistent, local-first memory for coding agents over MCP, enabling automatic recall and recording of past work, failures, and decisions to reduce repetition and token usage.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Provides persistent memory for AI coding agents via MCP, enabling agents to store and semantically recall facts, events, and lessons across sessions, all running locally without cloud dependencies.
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides a persistent, cross-tool memory layer for AI coding agents via MCP, enabling storage and retrieval of decisions, preferences, and context across different tools and models.
    2 npm
    1
    MIT