One memory for every AI agent — self-hosted long-term memory over MCP/REST for Claude Code, Codex, Cursor, Gemini CLI, VS Code, OpenClaw, and more.
A self-hosted long-term memory layer shared by Claude Code, Codex CLI, Cursor, Gemini CLI, VS Code agents, OpenClaw, and any MCP-capable client.
Quick Start · Connect Agents · Architecture · Roadmap · Contributing · Discussions · 中文
[!TIP] If you use more than one AI coding agent, Agent Memory is for you. Star the repository if you want an open, self-hosted memory layer that stays with you instead of one vendor, IDE, or model.
Your agents should not have separate memories
Most AI tools remember in isolation. Claude Code learns something, Codex starts from zero. Cursor discovers a project convention, Gemini CLI never sees it. Switching tools means repeating yourself.
Agent Memory gives them one private, continuously maintained memory service:
Your agents call the memory service. The memory service—not a specific IDE or agent—owns the long-term memory.
Today With Agent Memory ------ Every agent starts with a different history Agents recall from one authoritative memory plane Important decisions live in chat transcripts Durable facts are extracted into retrievable memory Switching tools means repeating context Claude Code, Codex, Cursor, Gemini CLI, VS Code, and OpenClaw can share it Memory is tied to a vendor or local plugin Memory runs as your own MCP/REST service "Remember everything" becomes noisy over time Decay, reinforcement, deduplication, tiers, and scopes manage lifecycle
Who should try it now? Developers and small teams who already switch between multiple AI agents, prefer self-hosting, and want shared memory without maintaining a knowledge graph.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/Masikomoore--agent-memory.html)
Shared, persistent memory for your AI coding assistants (Claude Code, Copilot, Cursor, Gemini CLI, Codex…): a local MCP server and CLI that hand work over between tools automatically.
osaxyz/sepiaceLong-term memory for coding agents. The sepiace plugin for Claude Code and Codex.
Kerneta/daidocsOpen plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP serve
tinhien11/tdai-memory-mcpLocal-first MCP memory server — Memory + CodeGraph + Wiki in one SQLite file. Tree-sitter code indexing, markdown wiki, lifecycle hooks, auto-capture. No API key, no cloud.
batrapulkit/squidbrakeBrakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.
noteflowai/dsh-skills-anywhereReuse Agent Skills across DeepSeek Harness and MCP. Check local SKILL.md files in the browser or CI, with parser diagnostics, file hashes and clear exit codes. Try the Hugging Face playground.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.