{"name":"agentmemory: Persistent Memory for AI Coding Agents","description":"agentmemory provides persistent memory for AI coding agents, ensuring they remember past interactions and project context across sessions. This eliminates the need for re-explaining, significantly boosting agent efficiency and reducing token costs. Built on the `iii engine`, it offers high retrieval accuracy and multi-agent support without external databases.","github":"https://github.com/rohitg00/agentmemory","url":"https://osrepos.com/repo/rohitg00-agentmemory","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/rohitg00-agentmemory","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/rohitg00-agentmemory.md","json":"https://osrepos.com/repo/rohitg00-agentmemory.json","topics":["agentmemory","agents","ai","typescript","developer-tools","memory","genai","open-source"],"keywords":["agentmemory","agents","ai","typescript","developer-tools","memory","genai","open-source"],"stars":null,"summary":"agentmemory provides persistent memory for AI coding agents, ensuring they remember past interactions and project context across sessions. This eliminates the need for re-explaining, significantly boosting agent efficiency and reducing token costs. Built on the `iii engine`, it offers high retrieval accuracy and multi-agent support without external databases.","content":"## Introduction\n\nagentmemory is a groundbreaking open-source repository that provides persistent memory for AI coding agents. It addresses the common problem of agents forgetting context between sessions, which often leads to repetitive explanations and wasted time. By silently capturing agent actions, compressing them into searchable memory, and injecting relevant context, agentmemory ensures your coding agent remembers everything, from architectural decisions to specific code patterns.\n\nBuilt on the `iii engine`, agentmemory offers impressive retrieval accuracy (95.2% R@5), significant token savings (up to 92% fewer tokens), and supports a wide array of agents through MCP or REST API. It operates without external databases, relying on SQLite and the `iii engine` for its robust memory management.\n\n## Installation\n\nTo get started with agentmemory, you can install it globally via npm or use npx for a quick run. First, ensure you have Node.js (>= 20) and `iii-engine` or Docker installed.\n\nbash\nnpm install -g @agentmemory/agentmemory\nagentmemory # start the memory server on :3111\nagentmemory demo # seed sample sessions + prove recall\n\n\nAlternatively, for a quick start without global installation:\n\nbash\nnpx @agentmemory/agentmemory\n\n\nFor detailed agent-specific wiring and configuration, please refer to the [official documentation](https://github.com/rohitg00/agentmemory#install).\n\n## Examples\n\nTo see agentmemory in action, run the demo command:\n\nbash\nnpx @agentmemory/agentmemory demo\n\n\nThis command seeds three realistic sessions (e.g., JWT auth, N+1 query fix, rate limiting) and performs semantic searches against them. You'll see it find \"N+1 query fix\" when you search \"database performance optimization\", a capability beyond simple keyword matching. You can also open the real-time viewer at `http://localhost:3113` to watch memory build live and replay sessions. agentmemory supports integration with various agents like Claude Code, Cursor, and Codex CLI, allowing them to leverage its persistent memory capabilities.\n\n## Why Use agentmemory\n\nAI coding agents often forget context between sessions, leading to repetitive explanations and wasted time. agentmemory solves this by providing a robust, searchable memory system that silently captures and compresses agent interactions. Unlike built-in agent memory solutions, which often have limited capacity (e.g., 200-line caps) and basic search, agentmemory offers unlimited scale, advanced hybrid search (BM25, vector, and knowledge graph), and significant token savings (up to 92% fewer tokens).\n\nIt supports multi-agent coordination, ensuring that all your agents share a common, evolving understanding of your projects. Real-world benchmarks show 95.2% retrieval accuracy and a cost of approximately $10/year for token usage, making it a highly efficient and effective solution for enhancing your AI coding workflow. With agentmemory, your agent just *knows*, eliminating the need for constant re-explaining.\n\n## Links\n\nFor more information, examples, and detailed usage instructions, visit the official resources:\n\n*   [GitHub Repository](https://github.com/rohitg00/agentmemory \"agentmemory GitHub Repository\" target=\"_blank\")\n*   [npm Package](https://www.npmjs.com/package/@agentmemory/agentmemory \"agentmemory npm Package\" target=\"_blank\")","metrics":{"detailViews":8,"githubClicks":13},"dates":{"published":null,"modified":"2026-05-27T16:57:25.000Z"}}