ai-memory
AIOpen-source, self-hosted long-term memory server that lets Claude Code, Codex, Cursor and other agent CLIs share context and hand off sessions.
ai-memory
Open-source, self-hosted long-term memory server that lets Claude Code, Codex, Cursor and other agent CLIs share context and hand off sessions.
About ai-memory
ai-memory is an open-source memory server written in Rust that gives AI coding agents long-term memory shared across tools. Its goal is to let you stop a session in one agent, such as Claude Code, and continue in another like OpenAI Codex without re-explaining the project. Lifecycle hooks automatically capture prompts, tool calls and session boundaries, sanitize them, and consolidate them at session end into a git-backed wiki of plain markdown files, with a rebuildable database serving as a derived index. The next session receives a brief and can search through full-text, entity and graph search, plus optional vector search. You run the server yourself on a laptop, homelab or LAN host, and it supports multi-user authentication, per-person attribution, an audit log and per-project team sharing. The default path makes zero LLM calls, so capture and search work without an API key. It integrates with Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Kiro CLI, Grok Build CLI and others via MCP and hooks, and is MIT licensed.
Key Features
Use Cases
Frequently asked questions about ai-memory
What is ai-memory?
Open-source, self-hosted long-term memory server that lets Claude Code, Codex, Cursor and other agent CLIs share context and hand off sessions.
How does ai-memory work?
ai-memory works by combining Cross-Agent Handoffs: Typed, claim-once handoffs let you continue a session in a different agent CLI., Automatic Capture: Lifecycle hooks record prompts, tool calls and session boundaries, sanitized before storage., Markdown Wiki Storage: Git-backed wiki of .md files is the source of truth, with a rebuildable derived database index., Multi-Mode Search: Full-text, entity and graph search plus optional vector search., Team Sharing: Per-project knowledge sharing with multi-user auth, per-person attribution and an audit log. to help users with A developer starts a feature in Claude Code and continues it in Codex without re-explaining the project., A team shares project knowledge across members' coding agents with an audit trail., An engineer keeps memory on a homelab server so every laptop and agent sees the same context., A privacy-focused user runs fully local memory capture with no LLM calls or cloud service., A maintainer browses and edits agent memories as plain markdown in a git repository..
What are the main features of ai-memory?
Key features include Cross-Agent Handoffs: Typed, claim-once handoffs let you continue a session in a different agent CLI., Automatic Capture: Lifecycle hooks record prompts, tool calls and session boundaries, sanitized before storage., Markdown Wiki Storage: Git-backed wiki of .md files is the source of truth, with a rebuildable derived database index., Multi-Mode Search: Full-text, entity and graph search plus optional vector search., Team Sharing: Per-project knowledge sharing with multi-user auth, per-person attribution and an audit log..
Who is ai-memory for?
ai-memory is useful for anyone interested in A developer starts a feature in Claude Code and continues it in Codex without re-explaining the project., A team shares project knowledge across members' coding agents with an audit trail., An engineer keeps memory on a homelab server so every laptop and agent sees the same context., A privacy-focused user runs fully local memory capture with no LLM calls or cloud service., A maintainer browses and edits agent memories as plain markdown in a git repository..
How much does ai-memory cost?
ai-memory is free to use.
How do I get started with ai-memory?
Visit https://github.com/akitaonrails/ai-memory to sign up and explore ai-memory.
Explore more AI Mcps tools
Browse all Mcps tools →Compare ai-memory: vs CrawlForge MCP · vs Popcraft · vs Pomerado · vs Manifold MCP