agent-memory
A long-term memory runtime for AI agents using Markdown as the data source.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 3.7k
- Source
- mcp-github
- Repository
- github.com/tigerless-labs/agent-memory
Overview
agent-memory is a long-term memory runtime designed for AI agents. It uses Markdown files as a single data source and provides information through local ranking retrieval. Supports tools like Claude Code, Codex CLI, sharing the same storage. No API key required. This capability enables AI agents to retain learned knowledge beyond sessions, suitable for scenarios requiring persistent memory.
Capabilities
- ▪Uses Markdown files as a data source
- ▪Local ranking retrieval
- ▪Independent sleep time management
- ▪Multiple tools share the same storage
Use cases
Setup
Clone the repository from GitHub and install dependencies: `git clone https://github.com/tigerless-labs/agent-memory && cd agent-memory && pip install -r requirements.txt`
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Do I need an API key?
No API key is required.
Which tools are supported?
Supports Claude Code, Codex CLI, and others.
Related skills
coop-anything
An MCP server that converts single-player games into cooperative multiplayer experiences.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.