개요
为 Claude Code、Cursor、Gemini CLI 等 AI 编码代理提供持久记忆。通过 hooks、MCP 或 REST API 集成，实现 95% 召回率并节省 92% 的 token。
README 미리보기
\n \n\n\n\n \n Your coding agent remembers everything. No more re-explaining.\n Built on iii engine\n \n Persistent memory for Claude Code, Cursor, Gemini CLI, Codex CLI, pi, OpenCode, and any MCP client.\n\n\n\n \n\n\n\n The gist extends Karpathy's LLM Wiki pattern with confidence scoring, lifecycle, knowledge graphs, and hybrid search. agentmemory is the implementation.\n\n\n\n \n \n \n \n\n\n\n \n \n \n \n \n \n\n\n\n \n\n\n\n Quick Start •\n Benchmarks •\n vs Competitors •\n Agents •\n How It Works •\n MCP •\n Viewer •\n iii Console •\n Powered by iii •\n Config •\n API\n\n\n---\n\n\n\nagentmemory works with any agent that supports hooks, MCP, or REST API. All agents share the same memory server.\n\n\n\n\n\nClaude Code\n12 hooks + MCP + skills\n\n\n\nOpenClaw\nMCP + plugin\n\n\n\nHermes\nMCP + plugin\n\n\n\nCursor\nMCP server\n\n\n\nGemini CLI\nMCP server\n\n\n\nOpenCode\nMCP server\n\n\n\nCodex CLI\nMCP server\n\n\n\nCline\nMCP server\n\n\n\n\n\nGoose\nMCP server\n\n\n\nKilo Code\nMCP server\n\n\n\nAider\nREST API\n\n\n\nClaude Desktop\nMCP server\n\n\n\nWindsurf\nMCP server\n\n\n\nRoo Code\nMCP server\n\n\n\nClaude SDK\nAgentSDKProvider\n\n\n\nAny agent\nREST API\n\n\n\n\n\n Works with any agent that speaks MCP or HTTP. One server, memories shared across all of them.\n\n\n---\n\nYou explain the same architecture every session. You re-discover the same bugs. You re-teach the same preferences. Built-in memory (CLAUDE.md, .cursorrules) caps out at 200 lines and goes stale. agentmemory fixes this. It silently captures what your agent does, compresses it into searchable memory, and injects the right context when the next session starts. One command. Works across agents.\n\n**What changes:** Session 1 you set up JWT auth. Session 2 you ask for rate limiting. The agent already knows your auth uses jose middleware in `src/middleware/auth.ts`, your tests cover token validation, and you