[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77VC2XCGTNTH06RAQ02K9GP":3,"skill-same:01M77VC2XCGTNTH06RAQ02K9GP":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M77VC2XCGTNTH06RAQ02K9GP","sota-tracker-claw",null,"Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fsota-tracker-claw\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# SOTA Tracker\n\n**The definitive open-source database of State-of-the-Art AI models.**\n\nAuto-updated daily from [LMArena](https:\u002F\u002Flmarena.ai), [Artificial Analysis](https:\u002F\u002Fartificialanalysis.ai), and [HuggingFace](https:\u002F\u002Fhuggingface.co).\n\n## Why This Exists\n\nAI models are released weekly. Keeping track is impossible. This project:\n\n1. **Curates authoritative data** - LMArena Elo rankings, manual curation for video\u002Fimage\u002Faudio models\n2. **Updates daily** via GitHub Actions\n3. **Exports to JSON\u002FCSV\u002FSQLite** - Use in your own projects\n4. **Provides multiple interfaces** - Static files, REST API, or MCP server\n\n## Quick Start: Use the Data\n\n### Option 1: Download JSON\u002FCSV\n\n```bash\n# Latest data (updated daily)\ncurl -O https:\u002F\u002Fraw.githubusercontent.com\u002Fromancircus\u002Fsota-tracker-mcp\u002Fmain\u002Fdata\u002Fsota_export.json\ncurl -O https:\u002F\u002Fraw.githubusercontent.com\u002Fromancircus\u002Fsota-tracker-mcp\u002Fmain\u002Fdata\u002Fsota_export.csv\n```\n\n### Option 2: Clone and Query Locally\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fromancircus\u002Fsota-tracker-mcp.git\ncd sota-tracker-mcp\n\n# Query with sqlite3\nsqlite3 data\u002Fsota.db \"SELECT name, sota_rank FROM models WHERE category='llm_api' ORDER BY sota_rank LIMIT 10\"\n\n# List forbidden\u002Foutdated models\nsqlite3 data\u002Fsota.db \"SELECT name, reason, replacement FROM forbidden\"\n```\n\n### Option 3: Use with Claude Code (Recommended)\n\nThe recommended approach for Claude Code users is **static file embedding** (lower token cost than MCP):\n\n```bash\n# Set up daily auto-update of CLAUDE.md\ncp scripts\u002Fupdate_sota_claude_md.py ~\u002Fscripts\u002F\n\n# Enable systemd timer (runs at 6 AM daily)\nsystemctl --user enable --now sota-update.timer\n\n# Or run manually\npython ~\u002Fscripts\u002Fupdate_sota_claude_md.py --update\n```\n\nThis embeds a compact SOTA summary directly in your `~\u002F.claude\u002FCLAUDE.md` file.\n\n### Option 4: REST API\n\n```bash\n# Start the API server\nuvicorn rest_api:app --host 0.0.0.0 --port 8000\n\n# Query endpoints\ncurl \"http:\u002F\u002Flocalhost:8000\u002Fapi\u002Fv1\u002Fmodels?category=llm_api\"\ncurl \"http:\u002F\u002Flocalhost:8000\u002Fapi\u002Fv1\u002Fforbidden\"\ncurl \"http:\u002F\u002Flocalhost:8000\u002Fapi\u002Fv1\u002Fmodels\u002FFLUX.1-dev\u002Ffreshness\"\n```\n\n### Option 5: MCP Server (Optional)\n\nMCP support is available but disabled by default (higher token cost). To enable:\n\n```bash\n# Edit .mcp.json to add the server config\ncat > .mcp.json \u003C\u003C 'EOF'\n{\n  \"mcpServers\": {\n    \"sota-tracker\": {\n      \"command\": \"python\",\n      \"args\": [\"server.py\"]\n    }\n  }\n}\nEOF\n```\n\n## Data Sources\n\n| Source | Data | Update Frequency |\n|--------|------|------------------|\n| [LMArena](https:\u002F\u002Flmarena.ai\u002Fleaderboard) | LLM Elo rankings (6M+ human votes) | Daily |\n| [Artificial Analysis](https:\u002F\u002Fartificialanalysis.ai) | LLM benchmarks, pricing, speed | Daily |\n| [HuggingFace](https:\u002F\u002Fhuggingface.co) | Model downloads, trending | Daily |\n| Manual curation | Video, Image, Audio, Video2Audio models | As needed |\n\n## Categories\n\n| Category | Description | Top Models (Feb 2026) |\n|----------|-------------|----------------------|\n| `llm_api` | Cloud LLM APIs | Gemini 3 Pro, Grok 4.1, Claude Opus 4.5 |\n| `llm_local` | Local LLMs (GGUF) | Qwen3, Llama 3.3, DeepSeek-V3 |\n| `llm_coding` | Code-focused LLMs | Qwen3-Coder, DeepSeek-V3 |\n| `image_gen` | Image generation | Z-Image-Turbo, FLUX.2-dev, Qwen-Image |\n| `video` | Video generation | LTX-2, Wan 2.2, HunyuanVideo 1.5 |\n| `video2audio` | Video-to-audio (foley) | MMAudio V2 Large |\n| `tts` | Text-to-speech | ChatterboxTTS, F5-TTS |\n| `stt` | Speech-to-text | Whisper Large v3 |\n| `embeddings` | Vector embeddings | BGE-M3 |\n\n## REST API Endpoints\n\n| Endpoint | Description |\n|----------|-------------|\n| `GET \u002Fapi\u002Fv1\u002Fmodels?category=X` | Get SOTA for a category |\n| `GET \u002Fapi\u002Fv1\u002Fmodels\u002F:name\u002Ffreshness` | Check if model is current or outdated |\n| `GET \u002Fapi\u002Fv1\u002Fforbidden` | List outdated models to avoid |\n| `GET \u002Fapi\u002Fv1\u002Fcompare?model_a=X&model_b=Y` | Compare two models |\n| `GET \u002Fapi\u002Fv1\u002Frecent?days=30` | Models released in past N days |\n| `GET \u002Fapi\u002Fv1\u002Frecommend?task=chat` | Get recommendation for a task |\n| `GET \u002Fhealth` | Health check |\n\n## Run Your Own Scraper\n\n```bash\n# Install dependencies\npip install -r requirements.txt\npip install playwright\nplaywright install chromium\n\n# Run all scrapers\npython scrapers\u002Frun_all.py --export\n\n# Output:\n# data\u002Fsota_export.json\n# data\u002Fsota_export.csv\n# data\u002Flmarena_latest.json\n```\n\n## GitHub Actions (Auto-Update)\n\nThis repo uses GitHub Actions to:\n- **Daily**: Scrape all sources, update database, commit changes\n- **Weekly**: Create a tagged release with JSON\u002FCSV exports\n\nTo enable on your fork:\n1. Fork this repo\n2. Go to Settings → Actions → Enable workflows\n3. Data will auto-update daily at 6 AM UTC\n\n## File Structure\n\n```\nsota-tracker-mcp\u002F\n├── server.py                    # MCP server (optional)\n├── rest_api.py                  # REST API server\n├── init_db.py                   # Database initialization + seeding\n├── requirements.txt             # Dependencies\n├── data\u002F\n│   ├── sota.db                  # SQLite database\n│   ├── sota_export.json         # Full JSON export\n│   ├── sota_export.csv          # CSV export\n│   └── forbidden.json           # Outdated models list\n├── scrapers\u002F\n│   ├── lmarena.py               # LMArena scraper (Playwright)\n│   ├── artificial_analysis.py   # AA scraper (Playwright)\n│   └── run_all.py               # Unified runner\n├── fetchers\u002F\n│   ├── huggingface.py           # HuggingFace API\n│   └── cache_manager.py         # Smart caching\n└── .github\u002Fworkflows\u002F\n    └── daily-scrape.yml         # GitHub Actions workflow\n```\n\n## Contributing\n\nFound a model that's missing or incorrectly ranked?\n\n1. **For manual additions**: Edit `init_db.py` and submit a PR\n2. **For scraper improvements**: Edit files in `scrapers\u002F`\n3. **For new data sources**: Add a new scraper and update `run_all.py`\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for full developer setup and PR process.\n\n## OpenCode \u002F Agents.md Integration\n\nThe repo now supports updating `agents.md` files for OpenCode agents:\n\n```bash\n# Update your agents.md with latest SOTA data\npython update_agents_md.py\n\n# Minimal version (top 1 model per category, lightweight)\npython update_agents_md.py --minimal\n\n# Custom categories and limit\npython update_agents_md.py --categories llm_local image_gen --limit 3\n\n# Force refresh from sources first\npython update_agents_md.py --refresh\n```\n\n### Automation\n\nAdd to your cron or systemd timer for daily updates:\n\n```cron\n# ~: crontab -e\n@daily python ~\u002FApps\u002Fsota-tracker-mcp\u002Fupdate_agents_md.py\n```\n\nOr systemd:\n\n```bash\n# ~\u002F.config\u002Fsystemd\u002Fuser\u002Fsota-update.service\n[Unit]\nDescription=Update SOTA models for agents\nAfter=network.target\n\n[Service]\nExecStart=%h\u002FApps\u002Fsota-tracker-mcp\u002Fupdate_agents_md.py\n\n[Install]\nWantedBy=default.target\n\n# ~\u002F.config\u002Fsystemd\u002Fuser\u002Fsota-update.timer\n[Unit]\nDescription=Daily SOTA data update\nOnCalendar=daily\nAccuracySec=1h\n\n[Install]\nWantedBy=timers.target\n\n# Enable\nsystemctl --user enable --now sota-update.timer\n```\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for full setup guide\n\n## Data Attribution & Legal\n\nThis project aggregates **publicly available benchmark data** from third-party sources. We do not claim ownership of rankings, Elo scores, or benchmark results.\n\n### Data Sources (Used With Permission)\n\n| Source | Data | Permission |\n|--------|------|------------|\n| [LMArena](https:\u002F\u002Flmarena.ai) | Chatbot Arena Elo rankings | `robots.txt: Allow: \u002F` |\n| [Artificial Analysis](https:\u002F\u002Fartificialanalysis.ai) | LLM quality benchmarks | `robots.txt: Allow: \u002F` (explicitly allows AI crawlers) |\n| [HuggingFace](https:\u002F\u002Fhuggingface.co) | Model metadata, downloads | Public API |\n| [Open LLM Leaderboard](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fopen-llm-leaderboard\u002Fopen_llm_leaderboard) | Open-source LLM benchmarks | CC-BY license |\n\n### Disclaimer\n\n- All benchmark scores and rankings are the intellectual work of their respective sources\n- This project provides aggregation and tooling, not original benchmark data\n- Data is scraped once daily to minimize server load\n- If you are a data source and wish to be excluded, please open an issue\n\n### Fair Use\n\nThis project:\n- Aggregates factual data (not copyrightable)\n- Adds value through tooling (API server, unified format, forbidden list)\n- Attributes all sources with links\n- Does not compete commercially with sources\n- Respects robots.txt permissions\n\n## License\n\nMIT - See [LICENSE](LICENSE) for details.\n\nThe **code** in this repository is MIT licensed. The **data** belongs to its respective sources (see attribution above).\n",{},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fs\u002Fsota-tracker-claw",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill sota-tracker-claw",{"tool":37,"command":38},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill sota-tracker-claw",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill sota-tracker-claw","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fsota-tracker-claw\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]