[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-83032":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":8,"languages":8,"totalLinesOfCode":8,"stars":9,"forks":10,"watchers":11,"openIssues":12,"contributorsCount":13,"subscribersCount":13,"size":13,"stars1d":10,"stars7d":14,"stars30d":15,"stars90d":13,"forks30d":13,"starsTrendScore":16,"compositeScore":17,"rankGlobal":8,"rankLanguage":8,"license":8,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":20,"hasPages":18,"topics":21,"createdAt":8,"pushedAt":8,"updatedAt":22,"readmeContent":23,"aiSummary":24,"trendingCount":13,"starSnapshotCount":13,"syncStatus":25,"lastSyncTime":26,"discoverSource":27},83032,"MiniMax-M3","MiniMax-AI\u002FMiniMax-M3","MiniMax-AI",null,218,19,16,13,0,92,112,80,87.84,false,"main",true,[],"2026-06-12 04:01:40","\u003Cdiv align=\"center\">\n  \u003Cpicture>\n    \u003Csource srcset=\"figures\u002FMiniMaxLogo-Dark.png\" media=\"(prefers-color-scheme: dark)\">\n      \u003Cimg src=\"figures\u002FMiniMaxLogo-Light.png\" width=\"60%\" alt=\"MiniMax\">\n    \u003C\u002Fsource>\n  \u003C\u002Fpicture>\n\u003C\u002Fdiv>\n\u003Chr>\n\n\u003Cdiv align=\"center\" style=\"line-height: 1.4; font-size:16px; margin-top: 30px;\">\n  Join Our\n  \u003Ca href=\"https:\u002F\u002Fplatform.minimaxi.com\u002Fdocs\u002Ffaq\u002Fcontact-us\" target=\"_blank\" style=\"font-size:17px; margin: 2px;\">\n    💬 WeChat\n  \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdiscord.com\u002Finvite\u002FDPC4AHFCBw\" target=\"_blank\" style=\"font-size:17px; margin: 2px;\">\n    🧩 Discord\n  \u003C\u002Fa>\n  community.\n\u003C\u002Fdiv>\n\u003Cdiv align=\"center\" style=\"line-height: 1.2; font-size:16px;\">\n  \u003Ca href=\"https:\u002F\u002Fagent.minimax.io\u002F\" target=\"_blank\" style=\"display: inline-block; margin: 4px;\">\n    MiniMax Agent\n  \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fplatform.minimax.io\u002Fdocs\u002Fguides\u002Ftext-generation\" target=\"_blank\" style=\"display: inline-block; margin: 4px;\">\n    ⚡️ API\n  \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-MCP\" style=\"display: inline-block; margin: 4px;\">\n    MCP\n  \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fwww.minimax.io\" target=\"_blank\" style=\"display: inline-block; margin: 4px;\">\n    MiniMax Website\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\u003Cdiv align=\"center\" style=\"line-height: 1.2; font-size:16px; margin-bottom: 30px;\">\n  \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FMiniMaxAI\" target=\"_blank\" style=\"margin: 2px;\">\n    🤗 Hugging Face\n  \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-M3\" target=\"_blank\" style=\"margin: 2px;\">\n    🐙 GitHub\n  \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fwww.modelscope.cn\u002Forganization\u002FMiniMax\" target=\"_blank\" style=\"margin: 2px;\">\n    🤖️ ModelScope\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n# MiniMax-M3 is Coming\n\n**MiniMax-M3** is the next generation of the MiniMax series, building on the agent harness, software engineering, and professional-work foundations established by [MiniMax-M2.7](https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-M2.7). The model is not yet released — this repository exists so the community can share what they need next.\n\n## We Want Your Feedback\n\nBefore M3 lands, we are listening. If you are using **MiniMax-M2.7** (via the API, Agent, or locally) and have something to say about it, please tell us — every report directly shapes M3.\n\nWe are especially interested in:\n\n- 🐛 **Bugs and regressions** — anything that broke, hallucinated, or behaved unexpectedly in M2.7.\n- 💡 **Capability requests** — what M2.7 still can't do well for your workload (agent harnesses, SWE, professional work, entertainment, multilingual, long context, tool use, …).\n- 📊 **Benchmark gaps** — public or internal evals where you would like to see M3 improve.\n- 🧰 **Deployment pain points** — issues with SGLang, vLLM, Transformers, ModelScope, NIM, or the API.\n- 🧠 **Agent \u002F skill feedback** — anything you observed while building Agent Teams, Skills, or dynamic tool search on top of M2.7.\n\n### How to send feedback\n\n| Channel | Use for |\n|---|---|\n| [📮 Open an Issue](https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-M3\u002Fissues\u002Fnew\u002Fchoose) | Bugs, capability requests, M2.7 → M3 comparisons. Pick a template. |\n| [💬 WeChat](https:\u002F\u002Fplatform.minimaxi.com\u002Fdocs\u002Ffaq\u002Fcontact-us) | Chinese-speaking community discussion. |\n| [🧩 Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FDPC4AHFCBw) | English-speaking community discussion. |\n| [✉️ model@minimax.io](mailto:model@minimax.io) | Private feedback, partnership, or evaluation requests. |\n\nIf you are reporting a bug from M2.7, please include:\n1. Which inference path you used (MiniMax API \u002F Agent \u002F SGLang \u002F vLLM \u002F Transformers \u002F NIM \u002F ModelScope).\n2. Inference parameters (`temperature`, `top_p`, `top_k`, system prompt).\n3. A minimal reproduction — prompt, expected output, actual output.\n\n## In the Meantime — Use M2.7\n\nWhile M3 is in development, M2.7 remains our latest released model:\n\n- **MiniMax Agent**: https:\u002F\u002Fagent.minimax.io\u002F\n- **MiniMax API**: https:\u002F\u002Fplatform.minimax.io\u002F\n- **Token Plan**: https:\u002F\u002Fplatform.minimax.io\u002Fsubscribe\u002Ftoken-plan\n- **Weights & deployment guides**: [MiniMax-M2.7](https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-M2.7) (SGLang \u002F vLLM \u002F Transformers \u002F ModelScope \u002F NVIDIA NIM)\n- **Model card**: https:\u002F\u002Fhuggingface.co\u002FMiniMaxAI\u002FMiniMax-M2.7\n\nRecommended inference parameters for M2.7: `temperature=1.0`, `top_p=0.95`, `top_k=40`.\n\n## Stay Updated\n\nWatch this repository for the M3 announcement, release notes, weights, and deployment guides.\n\n## Contact Us\n\nContact us at [model@minimax.io](mailto:model@minimax.io).\n","MiniMax-M3是MiniMax系列的下一代模型，基于先前版本MiniMax-M2.7在代理框架、软件工程和专业工作基础上进一步发展。该项目的核心功能和技术特点包括对现有模型能力的增强以及对用户反馈的高度关注，旨在通过收集关于M2.7版本的使用体验来指导M3的研发方向。特别地，项目团队希望获得关于错误修复、功能需求、性能基准差距、部署难题及代理\u002F技能构建方面的反馈。此项目适用于正在使用或计划使用AI技术改进其应用程序、服务或研究项目的开发者与研究人员，尤其是在需要高度定制化AI解决方案的场景下。",2,"2026-06-11 04:09:58","CREATED_QUERY"]