[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-82874":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":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":19,"hasPages":21,"topics":22,"createdAt":10,"pushedAt":10,"updatedAt":28,"readmeContent":29,"aiSummary":30,"trendingCount":15,"starSnapshotCount":15,"syncStatus":16,"lastSyncTime":31,"discoverSource":32},82874,"skyclaw","SkyworkAI\u002Fskyclaw","SkyworkAI","SkyClaw-v1.0: A Million-Context Agent Model at Ultra-Low Cost","https:\u002F\u002Fskyworkai.github.io\u002Fskyclaw\u002F",null,"HTML",139,13,5,0,2,16,43.04,false,"main",true,[23,24,25,26,27],"agent","codex","deepseek","hermes","openclaw","2026-06-12 04:01:39","\u003Cdiv align=\"center\">\n\n# SkyClaw-v1.0\n\n### A Million-Context Agent Model at Ultra-Low Cost\n\n**[Online Page](https:\u002F\u002Fskyworkai.github.io\u002Fskyclaw\u002F)** | **[Try API](https:\u002F\u002Fwww.apifree.ai\u002Fmodel\u002Fskywork-ai\u002Fskyclaw-v1?tab=api)** | **[Lite Version](https:\u002F\u002Fwww.apifree.ai\u002Fmodel\u002Fskywork-ai\u002Fskyclaw-v1-lite?tab=info)**\n\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green.svg)](LICENSE)\n[![Context](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FContext-1M%20tokens-brightgreen)](https:\u002F\u002Fskyworkai.github.io\u002Fskyclaw\u002F)\n[![Price](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FInput-0.5%20CNY\u002FM%20tokens-blue)](https:\u002F\u002Fskyworkai.github.io\u002Fskyclaw\u002F)\n[![API](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAPI-OpenAI%20Compatible-orange)](https:\u002F\u002Fwww.apifree.ai\u002Fmodel\u002Fskywork-ai\u002Fskyclaw-v1?tab=api)\n\n\u003C\u002Fdiv>\n\n---\n\nSkyClaw-v1.0 is a high-performance agent model by [Skywork AI](https:\u002F\u002Fhuggingface.co\u002FSkywork), optimized for complex tool use, multi-turn agent workflows, and cost-sensitive production tasks. Available in two variants:\n\n| Model | Input (CNY\u002FM) | Output (CNY\u002FM) | Best For |\n| :--- | :---: | :---: | :--- |\n| **SkyClaw-v1.0** | 0.5 | 4.0 | Strongest agent performance |\n| **SkyClaw-v1.0-lite** | 0.3 | 2.0 | Speed & cost-sensitive tasks |\n\n🎉 Free for a limited time: Both SkyClaw-v1.0 and SkyClaw-v1.0-lite are currently free to use. \n\n## Benchmarks\n\nSkyClaw-v1.0 outperforms Minimax 2.7, DeepSeek V4 Flash, and Qwen 3.6 series across all major agent benchmarks, while approaching larger proprietary models on Claw-related tasks.\n\n![SkyClaw benchmark chart](https:\u002F\u002Fraw.githubusercontent.com\u002Fskyworkai\u002Fskyclaw\u002Fmain\u002Fassets\u002Fbenchmark_style_chart_1600.png)\n\n## Showcase\n\nThe release page features locally rendered screenshots and short videos, showcasing real generated demos across UI applications and interactive games.\n\n### Static Previews\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>Flight & Travel\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Instagram-style\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Xiaohongshu-style\u003C\u002Fb>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fskyworkai\u002Fskyclaw\u002Fmain\u002Fassets\u002Fflight_travel_preview_crop.png\" width=\"260\"\u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fskyworkai\u002Fskyclaw\u002Fmain\u002Fassets\u002Finstagram_preview_crop.png\" width=\"260\"\u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fskyworkai\u002Fskyclaw\u002Fmain\u002Fassets\u002Fxiaohongshu_preview_crop.png\" width=\"260\"\u002F>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n### Interactive Demos\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>Bouncing Balls\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Fbouncing_balls.english.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Bingo Match\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Fbingo.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>2048 Puzzle\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002F2048\u002Findex.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>Tetris\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Ftetris\u002Findex.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Super Mario\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Fmario_game.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Airplane Battle\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Fairplane_battle\u002Findex.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>Chess\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Fchess.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Texas Hold'em\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Ftexas_holdem\u002Findex.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Financial Terminal\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Ffinancial_terminal_cn\u002Findex.html\">Open\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>Tank Roguelike\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002Ftank-roguelike.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Slay the Spire (杀戮尖塔)\u003C\u002Fb>\u003Cbr>\u003Ca href=\"https:\u002F\u002Fpicture-search.tiangong.cn\u002Fskyclaw-demos\u002F%E6%9D%80%E6%88%AE%E5%B0%96%E5%A1%94.html\">Play\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n## Citation\n\nIf you reference SkyClaw-v1.0 in your work, please use the following citation:\n\n```bibtex\n@misc{skyclaw2026,\n  title={SkyClaw-v1.0: A Million-Context Agent Model at Ultra-Low Cost},\n  author={Peiyu Wang and Min Zou and Liang Zeng and Weishen and Peng Cheng and Haoran Zhang and Yu Cheng and Yang Liu},\n  year={2026},\n  month={May},\n  howpublished={\\url{https:\u002F\u002Fskyworkai.github.io\u002Fskyclaw\u002F}},\n  url={https:\u002F\u002Fskyworkai.github.io\u002Fskyclaw\u002F},\n}\n```\n\n*Corresponding authors: Yu Cheng, Yang Liu*\n","SkyClaw-v1.0 是一个高性能的代理模型，专为复杂的工具使用、多轮次代理工作流和成本敏感的生产任务而设计。其核心功能包括支持高达百万个上下文令牌的处理能力，并且在输入成本上具有显著优势（最低每百万令牌0.3元人民币）。该模型分为标准版和精简版两个版本，分别适用于追求最强代理性能和对速度及成本有更高要求的应用场景。技术特点方面，SkyClaw-v1.0 在多个主要代理基准测试中表现出色，甚至接近更大规模的专有模型。此外，它还提供了与OpenAI兼容的API接口，便于集成到现有系统中。此项目非常适合需要高效处理大量数据同时控制成本的企业或个人开发者采用。","2026-06-11 04:09:29","CREATED_QUERY"]