🧠 agentmem

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.

---

🚀 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.