[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72269":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":28,"readmeContent":29,"aiSummary":30,"trendingCount":16,"starSnapshotCount":16,"syncStatus":31,"lastSyncTime":32,"discoverSource":33},72269,"MIRIX","Mirix-AI\u002FMIRIX","Mirix-AI","Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.","https:\u002F\u002Fmirix.io\u002F",null,"Python",3547,287,12,32,0,3,16,29.38,"Apache License 2.0",false,"main",[24,25,26,27],"llm-agents","llm-memory","memory-agents","personal-assistant","2026-06-12 02:03:00","![Mirix Logo](https:\u002F\u002Fgithub.com\u002FRenKoya1\u002FMIRIX\u002Fraw\u002Fmain\u002Fassets\u002Flogo.png)\n\n## MIRIX - Multi-Agent Personal Assistant with an Advanced Memory System\n\nYour personal AI that builds memory through screen observation and natural conversation\n\n| 🌐 [Website](https:\u002F\u002Fmirix.io) | 📚 [Documentation](https:\u002F\u002Fdocs.mirix.io) | 📄 [Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2507.07957) | 💬 [Discord](https:\u002F\u002Fdiscord.gg\u002FS6CeHNrJ) \n\u003C!-- | [Twitter\u002FX](https:\u002F\u002Ftwitter.com\u002Fmirix_ai) | [Discord](https:\u002F\u002Fdiscord.gg\u002FS6CeHNrJ) | -->\n\n---\n\n### Key Features 🔥\n\n- **Multi-Agent Memory System:** Six specialized memory components (Core, Episodic, Semantic, Procedural, Resource, Knowledge Vault) managed by dedicated agents\n- **Screen Activity Tracking:** Continuous visual data capture and intelligent consolidation into structured memories  \n- **Privacy-First Design:** All long-term data stored locally with user-controlled privacy settings\n- **Advanced Search:** PostgreSQL-native BM25 full-text search with vector similarity support\n- **Multi-Modal Input:** Text, images, voice, and screen captures processed seamlessly\n\n### Quick Start\n**Step 1: Backend & Dashboard (Docker):**\n```\ndocker compose up -d --pull always\n```\n- Dashboard: http:\u002F\u002Flocalhost:5173  \n- API: http:\u002F\u002Flocalhost:8531  \n\n**Step 2: Create an API key in the dashboard (http:\u002F\u002Flocalhost:5173) and set as the environmental variable `MIRIX_API_KEY`.**\n\n**Step 3: Client (Python, `mirix-client`, https:\u002F\u002Fpypi.org\u002Fproject\u002Fmirix-client\u002F):**\n```\npip install mirix-client\n```\n\nNow you are ready to go! See the example below:\n```python\nfrom mirix import MirixClient\n\nclient = MirixClient(\n    api_key=\"your-api-key\",\n    base_url=\"http:\u002F\u002Flocalhost:8531\",\n)\n\nclient.initialize_meta_agent(\n    config={\n        \"llm_config\": {\n            \"model\": \"gemini-2.0-flash\",\n            \"model_endpoint_type\": \"google_ai\",\n            \"api_key\": \"your-api-key-here\",\n            \"model_endpoint\": \"https:\u002F\u002Fgenerativelanguage.googleapis.com\",\n            \"context_window\": 1_000_000,\n        },\n        \"embedding_config\": {\n            \"embedding_model\": \"text-embedding-004\",\n            \"embedding_endpoint_type\": \"google_ai\",\n            \"api_key\": \"your-api-key-here\",\n            \"embedding_endpoint\": \"https:\u002F\u002Fgenerativelanguage.googleapis.com\",\n            \"embedding_dim\": 768,\n        },\n        \"meta_agent_config\": {\n            \"agents\": [\n                {\n                    \"core_memory_agent\": {\n                        \"blocks\": [\n                            {\"label\": \"human\", \"value\": \"\"},\n                            {\"label\": \"persona\", \"value\": \"I am a helpful assistant.\"},\n                        ]\n                    }\n                },\n                \"resource_memory_agent\",\n                \"semantic_memory_agent\",\n                \"episodic_memory_agent\",\n                \"procedural_memory_agent\",\n                \"knowledge_vault_memory_agent\",\n            ],\n        },\n    }\n)\n\nclient.add(\n    user_id=\"demo-user\",\n    messages=[\n        {\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"The moon now has a president.\"}]},\n        {\"role\": \"assistant\", \"content\": [{\"type\": \"text\", \"text\": \"Noted.\"}]},\n    ],\n)\n\nmemories = client.retrieve_with_conversation(\n    user_id=\"demo-user\",\n    messages=[\n        {\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"What did we discuss on MirixDB in last 4 days?\"}]},\n    ],\n    limit=5,\n)\nprint(memories)\n```\nFor more API examples, see `samples\u002Frun_client.py`.\n\n## License\n\nMirix is released under the Apache License 2.0. See the [LICENSE](LICENSE) file for more details.\n\n## Contact\n\nFor questions, suggestions, or issues, please open an issue on the GitHub repository or contact us at `founders@mirix.io`\n\n## Join Our Community\n\nConnect with other Mirix users, share your thoughts, and get support:\n\n### 💬 Discord Community\nJoin our Discord server for real-time discussions, support, and community updates:\n**[https:\u002F\u002Fdiscord.gg\u002FS6CeHNrJ](https:\u002F\u002Fdiscord.gg\u002FS6CeHNrJ)**\n\n### 🎯 Weekly Discussion Sessions\nWe host weekly discussion sessions where you can:\n- Discuss issues and bugs\n- Share ideas about future directions\n- Get general consultations and support\n- Connect with the development team and community\n\n**📅 Schedule:** Friday nights, 8-9 PM PST  \n**🔗 Zoom Link:** [https:\u002F\u002Fucsd.zoom.us\u002Fj\u002F96278791276](https:\u002F\u002Fucsd.zoom.us\u002Fj\u002F96278791276)\n\n### 📱 WeChat Group\nYou can add the account `ari_asm` so that I can add you to the group chat.\n\n## Acknowledgement\nWe would like to thank [Letta](https:\u002F\u002Fgithub.com\u002Fletta-ai\u002Fletta) for open-sourcing their framework, which served as the foundation for the memory system in this project.\n","Mirix是一款多代理个人助手，旨在通过屏幕活动跟踪和智能回答用户问题来构建记忆。它利用六个专门的记忆组件（核心、情景、语义、程序、资源、知识库），由专门的代理管理，能够持续捕获视觉数据并将其整合为结构化记忆。Mirix采用隐私优先设计，所有长期数据本地存储，并支持用户控制隐私设置；同时具备先进的全文搜索功能，支持BM25算法与向量相似度查询。此外，该系统能够无缝处理文本、图像、语音及屏幕截图等多种输入形式。适用于需要高度定制化信息管理和个性化辅助服务的场景，如个人日常事务管理、专业工作流程优化等。",2,"2026-06-11 03:41:07","high_star"]