agentmemory is a persistent memory server for AI coding agents that captures project context, past decisions, bugs, preferences, and implementation details so users do not have to re-explain the same information in every session. It works across tools such as Claude Code, Cursor, Gemini CLI, Codex CLI, OpenCode, Cline, and any client that supports MCP or REST APIs. The system automatically records what agents do, compresses that activity into searchable memory, and injects relevant context when a new coding session begins. It combines keyword search, vector search, confidence scoring, lifecycle management, and knowledge graph querying to retrieve useful memories without overloading the context window. The project also includes hooks, an API, import and export support, audit trails, and team sharing workflows. Overall, agentmemory is designed to make AI coding assistants more continuous, context-aware, and useful across long-running software projects.

Features

  • Persistent memory for AI coding agents
  • MCP and REST API compatibility
  • Automatic capture through agent hooks
  • Hybrid search with graph-based retrieval
  • Import, export, audit, and team sharing tools
  • Support for multiple coding assistant environments

Project Samples

Project Activity

See All Activity >

Categories

Agentic AI

License

Apache License V2.0

Follow agentmemory

agentmemory Web Site

Other Useful Business Software
Go From AI Idea to AI App Fast Icon
Go From AI Idea to AI App Fast

One platform to build, fine-tune, and deploy ML models. No MLOps team required.

Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
Try Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of agentmemory!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

TypeScript

Related Categories

TypeScript Agentic AI Tool

Registered

2026-05-11