[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72353":3},{"id":4,"name":5,"fullName":6,"owner":5,"repo":5,"description":7,"homepage":8,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":17,"compositeScore":19,"rankGlobal":9,"rankLanguage":9,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":23,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":44,"readmeContent":45,"aiSummary":46,"trendingCount":15,"starSnapshotCount":15,"syncStatus":16,"lastSyncTime":47,"discoverSource":48},72353,"MemMachine","MemMachine\u002FMemMachine","Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.","https:\u002F\u002Fmemmachine.ai",null,"Python",3108,180,15,42,0,2,6,35,69.27,"Apache License 2.0",false,"main",true,[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"agent","agentic-ai","agents","agents-sdk","ai","ai-agents","chatbots","conversational-agents","conversational-ai","genai","knowledge-graph","llm","long-short-term-memory","memory","memory-management","persistent-memory","personalization","python","strands-agents","2026-06-12 04:01:04","# MemMachine\n\n\u003Cdiv align=\"center\">\n\n![MemMachine: Long Term Memory for AI Agents](https:\u002F\u002Fraw.githubusercontent.com\u002FMemMachine\u002FMemMachine\u002Fmain\u002Fassets\u002Fimg\u002FMemMachine_Hero_Banner.png)\n\n**The open-source memory layer for AI agents.**\n\n*Stop building stateless agents. Give your AI persistent memory with just 5 lines of code.*\n\n\u003Cbr\u002F>\n\n![GitHub Release Version](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fmemmachine\u002Fmemmachine?display_name=release)\n![GitHub License](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002FMemMachine\u002FMemMachine)\n[![Ask DeepWiki](https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg)](https:\u002F\u002Fdeepwiki.com\u002FMemMachine\u002FMemMachine)\n![Discord](https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1412878659479666810)\n\u003Cbr\u002F>\n![Docker Pulls](https:\u002F\u002Fimg.shields.io\u002Fdocker\u002Fpulls\u002Fmemmachine\u002Fmemmachine)\n![GitHub Downloads](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fmemmachine\u002Fmemmachine\u002Ftotal?label=GitHub%20Downloads)\n\u003Cbr\u002F>\n![PyPI Downloads - memmachine-client](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fdm\u002Fmemmachine-client?label=PyPI%20Downloads%3A%20memmachine-client)\n![PyPI Downloads - memmachine-server](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fdm\u002Fmemmachine-server?label=PyPI%20Downloads%3A%20memmachine-server)\n\n\u003C\u002Fdiv>\n\n## What is MemMachine?\n\nMemMachine is an open-source **long-term memory layer** for AI agents and LLM-powered applications. It enables your AI to **learn, store, and recall** information from past sessions—transforming stateless chatbots into personalized, context-aware assistants.\n\n### Key Capabilities\n\n- **Episodic Memory**: Graph-based conversational context that persists across sessions\n- **Profile Memory**: Long-term user facts and preferences stored in SQL\n- **Working Memory**: Short-term context for the current session\n- **Agent Memory Persistence**: Memory that survives restarts, sessions, and even model changes\n\n## Quick Start\n\nGet up and running in under 5 minutes:\n\n> **Prerequisites:** This code requires a running MemMachine Server.\n> [Start a server locally](https:\u002F\u002Fdocs.memmachine.ai\u002Fgetting_started\u002Fquickstart) or create a free account on the [MemMachine Platform](https:\u002F\u002Fconsole.memmachine.ai\u002F).\n\n```bash\npip install memmachine-client\n```\n\n```python\nfrom memmachine_client import import MemMachineClient\n\n# Initialize the client\nclient = MemMachineClient(base_url=\"http:\u002F\u002Flocalhost:8080\")\n\n# Get or create a project\nproject = client.get_or_create_project(org_id=\"my_org\", project_id=\"my_project\")\n\n# Create a memory instance for a user session\nmemory = project.memory(\n    group_id=\"default\",\n    agent_id=\"travel_agent\",\n    user_id=\"alice\",\n    session_id=\"session_001\"\n)\n\n# Add a memory\nmemory.add(\"I prefer aisle seats on flights\", metadata={\"category\": \"travel\"})\n# => [AddMemoryResult(uid='...')]\n\n# Search memories\nresults = memory.search(\"What are my flight preferences?\")\nprint(results.content.episodic_memory.long_term_memory.episodes[0].content)\n# => \"I prefer aisle seats on flights\"\n```\n\nFor full installation options (Docker, self-hosted, cloud), visit the\n[Quick Start Guide](https:\u002F\u002Fdocs.memmachine.ai\u002Fgetting_started\u002Fquickstart).\n\n## Integrations\n\nMemMachine works seamlessly with your favorite AI frameworks:\n\n\u003Cdiv align=\"center\">\n\n| Framework | Description |\n|-----------|-------------|\n| [**LangChain**](integrations\u002Flangchain\u002F) | Memory provider for LangChain agents |\n| [**LangGraph**](integrations\u002Flanggraph\u002F) | Stateful memory for LangGraph workflows |\n| [**CrewAI**](integrations\u002Fcrewai\u002F) | Persistent memory for CrewAI multi-agent systems |\n| [**LlamaIndex**](integrations\u002Fllamaindex\u002F) | Memory integration for LlamaIndex applications |\n| [**AWS Strands**](integrations\u002Faws_strands_agent_sdk\u002F) | Memory for AWS Strands Agent SDK |\n| [**n8n**](integrations\u002Fn8n\u002F) | No-code workflow automation integration |\n| [**Dify**](integrations\u002Fdify\u002F) | Memory backend for Dify AI applications |\n| [**FastGPT**](integrations\u002Ffastgpt\u002F) | Integration with FastGPT platform |\n\n\u003C\u002Fdiv>\n\n## MCP Server Support\n\nMemMachine includes a native **Model Context Protocol (MCP)** server for seamless integration with Claude Desktop, Cursor, and other MCP-compatible clients:\n\n```bash\n# Stdio mode (for Claude Desktop)\nmemmachine-mcp-stdio\n\n# HTTP mode (for web clients)\nmemmachine-mcp-http\n```\n\nSee the [MCP documentation](https:\u002F\u002Fdocs.memmachine.ai\u002Fintegrations\u002Fmcp) for setup instructions.\n\n## Who Is MemMachine For?\n\n- **Developers** building AI agents, assistants, or autonomous workflows\n- **Researchers** experimenting with agent architectures and cognitive models\n- **Teams** who need persistent, cross-session memory for their LLM applications\n\n## Key Features\n\n- **Multiple Memory Types**: Working (short-term), Episodic (long-term conversational), and Profile (user facts) memory\n- **Developer-Friendly APIs**: Python SDK, RESTful API, TypeScript SDK, and MCP server interfaces\n- **Flexible Storage**: Graph database (Neo4j) for episodic memory, SQL for profiles\n- **LLM Agnostic**: Works with OpenAI, Anthropic, Bedrock, Ollama, and any LLM provider\n- **Self-Hosted or Cloud**: Run locally, in Docker, or use our managed service\n\nFor more information, refer to the [API Reference Guide](https:\u002F\u002Fdocs.memmachine.ai\u002Fapi_reference).\n\n## Architecture\n\n\u003Cdiv align=\"center\">\n\n![MemMachine Architecture](https:\u002F\u002Fraw.githubusercontent.com\u002FMemMachine\u002FMemMachine\u002Fmain\u002Fassets\u002Fimg\u002FMemMachine_Architecture.png)\n\n\u003C\u002Fdiv>\n\n1. **Agents interact via the API Layer**: Users interact with an agent, which connects to MemMachine through a RESTful API, Python SDK, or MCP Server.\n2. **MemMachine manages memory**: Processes interactions and stores them as Episodic Memory (conversational context) and Profile Memory (long-term user facts).\n3. **Data is persisted**: Episodic memory is stored in a graph database; profile memory is stored in SQL.\n\n## Use Cases & Example Agents\n\nMemMachine's versatile memory architecture can be applied across any domain. Explore our [examples](examples\u002FREADME.md) to see memory-powered agents in action:\n\n| Agent | Description |\n|-------|-------------|\n| **CRM Agent** | Recalls client history and deal stages to help sales teams close faster |\n| **Healthcare Navigator** | Remembers medical history and tracks treatment progress |\n| **Personal Finance Advisor** | Stores portfolio preferences and risk tolerance for personalized insights |\n| **Writing Assistant** | Learns your style guide and terminology for consistent content |\n\n## Built with MemMachine\n\nAre you using MemMachine in your project? We'd love to feature you!\n\n- Share your project in [GitHub Discussions → Showcase](https:\u002F\u002Fgithub.com\u002FMemMachine\u002FMemMachine\u002Fdiscussions\u002Fcategories\u002Fshowcase)\n- Drop a message in our [Discord #showcase channel](https:\u002F\u002Fdiscord.gg\u002FusydANvKqD)\n\n## Growing Community\n\nMemMachine is a growing community of builders and developers. Help us grow by clicking the ⭐ **Star** button above!\n\n\u003Cimg src=\"https:\u002F\u002Fstarchart.cc\u002FMemMachine\u002FMemMachine.svg?variant=light\" alt=\"MemMachine Star History\" height=\"300\"\u002F>\n\n## Documentation\n\n- **[Main Website](https:\u002F\u002Fmemmachine.ai)** – Learn about MemMachine\n- **[Docs & API Reference](https:\u002F\u002Fdocs.memmachine.ai)** – Full documentation\n- **[Quick Start Guide](https:\u002F\u002Fdocs.memmachine.ai\u002Fgetting_started\u002Fquickstart)** – Get started in minutes\n\n## Community & Support\n\n- **Discord**: Join our community for support, updates, and discussions:\n    [https:\u002F\u002Fdiscord.gg\u002FusydANvKqD](https:\u002F\u002Fdiscord.gg\u002FusydANvKqD)\n- **Issues & Feature Requests**: Use GitHub\n    [Issues](https:\u002F\u002Fgithub.com\u002FMemMachine\u002FMemMachine\u002Fissues)\n\n## Contributing\n\nWe welcome contributions! Please see our [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n## References\n\n```bibtex\n@misc{luo2025agentlightningtrainai,\n  title={Agent Lightning: Train ANY AI Agents with Reinforcement Learning},\n  author={Xufang Luo and Yuge Zhang and Zhiyuan He and Zilong Wang and Siyun Zhao and Dongsheng Li and Luna K. Qiu and Yuqing Yang},\n  year={2025},\n  eprint={2508.03680},\n  archivePrefix={arXiv},\n  primaryClass={cs.AI},\n  url={https:\u002F\u002Farxiv.org\u002Fabs\u002F2508.03680},\n}\n```\n\n## License\n\nMemMachine is released under the [Apache 2.0 License](LICENSE).\n","MemMachine 是一个为 AI 代理设计的通用记忆层，旨在提供可扩展、可扩展且互操作的记忆存储与检索功能，以简化下一代自主系统的状态管理。其核心功能包括基于图的会话上下文（情景记忆）、长期用户事实和偏好存储（个人资料记忆）、短期会话上下文（工作记忆）以及跨重启、会话甚至模型变更时仍能保持的记忆持久性。MemMachine 适用于需要构建具有持久记忆能力的聊天机器人或对话式 AI 应用场景，如客户服务、虚拟助手等，使这些应用能够学习并记住与用户的交互历史，从而提供更加个性化和连贯的服务体验。通过简单的 Python API，开发者可以轻松地将 MemMachine 集成到自己的项目中。","2026-06-11 03:41:27","high_star"]