{"success":true,"count":19,"updatedAt":"2026-07-26T20:00:04.771Z","data":{"deepseek":{"name":"DeepSeek","full_name":null,"stargazers_count":0,"forks_count":0,"watchers_count":null,"open_issues_count":null,"updated_at":null,"pushed_at":null,"html_url":null,"description":"DeepSeek-V3 is a 671B MoE model (37B active) that matches top proprietary models at drastically lower training cost. DeepSeek-R1 achieves reasoning on par with OpenAI o1 via pure RL without supervised fine-tuning.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"qwen":{"name":"Qwen","full_name":"QwenLM/Qwen","stargazers_count":21480,"forks_count":1861,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:19:16Z","pushed_at":"2026-03-05T13:55:17Z","html_url":"https://github.com/QwenLM/Qwen","description":"Qwen spans 100+ open-weight models from 0.6B to 32B, plus MoE and multimodal variants. Includes Qwen-Agent framework with function calling, MCP, and code interpreter, plus a terminal coding agent.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"chatglm":{"name":"ChatGLM","full_name":"zai-org/ChatGLM3","stargazers_count":13669,"forks_count":1585,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T11:31:56Z","pushed_at":"2025-01-13T06:55:26Z","html_url":"https://github.com/zai-org/ChatGLM3","description":"ChatGLM is a family of bilingual Chinese/English LLMs from Tsinghua University spinoff Zhipu AI. GLM-4.5 is a 355B MoE model with multimodal variants including CogVLM and CogVideoX.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"kimi":{"name":"Kimi","full_name":"MoonshotAI/Kimi-K2","stargazers_count":11037,"forks_count":888,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T18:51:14Z","pushed_at":"2026-01-21T05:33:12Z","html_url":"https://github.com/MoonshotAI/Kimi-K2","description":"Kimi K2 is a 1T-parameter MoE model (32B active) with SOTA performance among non-thinking models. K2.5 adds native vision via MoonViT, enabling agentic tasks like replicating website user journeys from video.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"ernie":{"name":"ERNIE Bot","full_name":"PaddlePaddle/ERNIE","stargazers_count":7725,"forks_count":1442,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T15:01:00Z","pushed_at":"2026-07-24T21:37:38Z","html_url":"https://github.com/PaddlePaddle/ERNIE","description":"ERNIE 4.5 is a native multimodal model processing text, images, and video. Baidu open-sourced 10 models in the series under Apache 2.0, including a 47B MoE model with only 3B active parameters.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"doubao":{"name":"Doubao","full_name":null,"stargazers_count":0,"forks_count":0,"watchers_count":null,"open_issues_count":null,"updated_at":null,"pushed_at":null,"html_url":null,"description":"Doubao 2.0 is ByteDance's agent-era AI that decomposes complex objectives into executable sub-tasks using advanced reasoning chains. Doubao-Seed-Code achieved SOTA on SWE-Bench-Verified.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"minimax":{"name":"MiniMax","full_name":null,"stargazers_count":0,"forks_count":0,"watchers_count":null,"open_issues_count":null,"updated_at":null,"pushed_at":null,"html_url":null,"description":"MiniMax develops multimodal AI with a novel Lightning Attention mechanism. M2.5 achieves SOTA in coding, tool use, and agentic workflows. Served 236M+ users across 200+ countries via Talkie and Hailuo AI.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"yi":{"name":"Yi","full_name":"01-ai/Yi","stargazers_count":7825,"forks_count":492,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T15:00:49Z","pushed_at":"2024-11-27T09:25:57Z","html_url":"https://github.com/01-ai/Yi","description":"Yi series from Kai-Fu Lee's 01.AI includes models that outperformed LLaMA2-70B at a fraction of the size. Yi-34B is fully bilingual English/Chinese with commercially permissive licensing.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"spark":{"name":"Spark","full_name":null,"stargazers_count":0,"forks_count":0,"watchers_count":null,"open_issues_count":null,"updated_at":null,"pushed_at":null,"html_url":null,"description":"Spark X1.5 is a 293B MoE model (30B active) with 130+ language support. Built on iFlytek's decades of speech AI expertise with leading voice cloning and mathematical reasoning capabilities.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"nanoclaw":{"name":"NanoClaw","full_name":"qwibitai/nanoclaw","stargazers_count":30375,"forks_count":12876,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:36:31Z","pushed_at":"2026-07-26T15:23:04Z","html_url":"https://github.com/qwibitai/nanoclaw","description":"Runs each Skill in OS-level sandboxes (Apple Sandbox or Docker), directly addressing OpenClaw RCE risks. Best personal alternative for users prioritizing security.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"picoclaw":{"name":"PicoClaw","full_name":"sipeed/picoclaw","stargazers_count":29729,"forks_count":4345,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T16:48:30Z","pushed_at":"2026-07-23T18:29:33Z","html_url":"https://github.com/sipeed/picoclaw","description":"Optimized for RISC-V and ARM embedded boards, capable of 24/7 operation on $10 devices. Features Whisper voice integration, making it ideal for physical AI assistants and IoT deployments.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"zeroclaw":{"name":"ZeroClaw","full_name":"zeroclaw-labs/zeroclaw","stargazers_count":32399,"forks_count":4843,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T18:51:01Z","pushed_at":"2026-07-26T18:50:53Z","html_url":"https://github.com/zeroclaw-labs/zeroclaw","description":"Ultra-fast, ultra-light Claw variant written in Rust. Sub-10ms startup time and minimal footprint make it ideal for scripting, automation, and edge computing.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"nullclaw":{"name":"NullClaw","full_name":"nullclaw/nullclaw","stargazers_count":7884,"forks_count":927,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:41:47Z","pushed_at":"2026-07-19T04:20:06Z","html_url":"https://github.com/nullclaw/nullclaw","description":"The absolute minimum. No dependencies, sub-1MB binary — ideal for the most resource-constrained environments.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"ironclaw":{"name":"IronClaw","full_name":"nearai/ironclaw","stargazers_count":12561,"forks_count":1488,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T15:07:11Z","pushed_at":"2026-07-26T18:57:41Z","html_url":"https://github.com/nearai/ironclaw","description":"Built for stability and long-term continuous operation in industrial environments. C++ core ensures predictable performance over extended uptime.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"nanobot":{"name":"nanobot","full_name":"HKUDS/nanobot","stargazers_count":46266,"forks_count":8192,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:40:00Z","pushed_at":"2026-07-26T19:07:41Z","html_url":"https://github.com/HKUDS/nanobot","description":"Delivers core agent functionality with 99% fewer lines of code than OpenClaw.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"agent-zero":{"name":"Agent Zero","full_name":"agent0ai/agent-zero","stargazers_count":18542,"forks_count":3689,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T14:08:42Z","pushed_at":"2026-07-25T22:58:43Z","html_url":"https://github.com/agent0ai/agent-zero","description":"Multi-agent collaboration platform with Docker container isolation. Features hierarchical agent swarms, web UI, and comprehensive tool support. Best for teams needing collaborative AI agents with security isolation.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"hermes-agent":{"name":"Hermes Agent","full_name":"NousResearch/hermes-agent","stargazers_count":220862,"forks_count":42104,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:56:24Z","pushed_at":"2026-07-26T19:58:15Z","html_url":"https://github.com/NousResearch/hermes-agent","description":"Self-improving AI agent with automatic skill creation from experience. Features 40+ built-in tools, 6 deployment backends (local, Docker, SSH, Modal, Daytona, Singularity), 5+ messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal, Email, CLI), works with 200+ models via OpenRouter. Server-first design with sandboxed execution and container hardening. Gets smarter over time by auto-creating skills from experience.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"nemoclaw":{"name":"NemoClaw","full_name":"NVIDIA/NemoClaw","stargazers_count":21942,"forks_count":2978,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:55:56Z","pushed_at":"2026-07-26T19:52:44Z","html_url":"https://github.com/NVIDIA/NemoClaw","description":"NVIDIA NemoClaw is an open source stack that adds privacy and security controls to OpenClaw. Uses NVIDIA OpenShell to enforce policy-based guardrails, routes inference through Nemotron models, and supports sandboxed deployments via Docker. The most significant fork release after OpenClaw itself.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},"openclaw":{"name":"OpenClaw","full_name":"openclaw/openclaw","stargazers_count":384222,"forks_count":80721,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:52:43Z","pushed_at":"2026-07-26T19:44:39Z","html_url":"https://github.com/openclaw/openclaw","description":"The original and most widely deployed Claw AI agent. Features the richest ecosystem with 5,000+ official and community skills, covering everything from everyday tasks to automated code review.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"}},"repositories":[{"name":"DeepSeek","full_name":null,"stargazers_count":0,"forks_count":0,"watchers_count":null,"open_issues_count":null,"updated_at":null,"pushed_at":null,"html_url":null,"description":"DeepSeek-V3 is a 671B MoE model (37B active) that matches top proprietary models at drastically lower training cost. DeepSeek-R1 achieves reasoning on par with OpenAI o1 via pure RL without supervised fine-tuning.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"Qwen","full_name":"QwenLM/Qwen","stargazers_count":21480,"forks_count":1861,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:19:16Z","pushed_at":"2026-03-05T13:55:17Z","html_url":"https://github.com/QwenLM/Qwen","description":"Qwen spans 100+ open-weight models from 0.6B to 32B, plus MoE and multimodal variants. Includes Qwen-Agent framework with function calling, MCP, and code interpreter, plus a terminal coding agent.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"ChatGLM","full_name":"zai-org/ChatGLM3","stargazers_count":13669,"forks_count":1585,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T11:31:56Z","pushed_at":"2025-01-13T06:55:26Z","html_url":"https://github.com/zai-org/ChatGLM3","description":"ChatGLM is a family of bilingual Chinese/English LLMs from Tsinghua University spinoff Zhipu AI. GLM-4.5 is a 355B MoE model with multimodal variants including CogVLM and CogVideoX.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"Kimi","full_name":"MoonshotAI/Kimi-K2","stargazers_count":11037,"forks_count":888,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T18:51:14Z","pushed_at":"2026-01-21T05:33:12Z","html_url":"https://github.com/MoonshotAI/Kimi-K2","description":"Kimi K2 is a 1T-parameter MoE model (32B active) with SOTA performance among non-thinking models. K2.5 adds native vision via MoonViT, enabling agentic tasks like replicating website user journeys from video.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"ERNIE Bot","full_name":"PaddlePaddle/ERNIE","stargazers_count":7725,"forks_count":1442,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T15:01:00Z","pushed_at":"2026-07-24T21:37:38Z","html_url":"https://github.com/PaddlePaddle/ERNIE","description":"ERNIE 4.5 is a native multimodal model processing text, images, and video. Baidu open-sourced 10 models in the series under Apache 2.0, including a 47B MoE model with only 3B active parameters.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"Doubao","full_name":null,"stargazers_count":0,"forks_count":0,"watchers_count":null,"open_issues_count":null,"updated_at":null,"pushed_at":null,"html_url":null,"description":"Doubao 2.0 is ByteDance's agent-era AI that decomposes complex objectives into executable sub-tasks using advanced reasoning chains. Doubao-Seed-Code achieved SOTA on SWE-Bench-Verified.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"MiniMax","full_name":null,"stargazers_count":0,"forks_count":0,"watchers_count":null,"open_issues_count":null,"updated_at":null,"pushed_at":null,"html_url":null,"description":"MiniMax develops multimodal AI with a novel Lightning Attention mechanism. M2.5 achieves SOTA in coding, tool use, and agentic workflows. Served 236M+ users across 200+ countries via Talkie and Hailuo AI.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"Yi","full_name":"01-ai/Yi","stargazers_count":7825,"forks_count":492,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T15:00:49Z","pushed_at":"2024-11-27T09:25:57Z","html_url":"https://github.com/01-ai/Yi","description":"Yi series from Kai-Fu Lee's 01.AI includes models that outperformed LLaMA2-70B at a fraction of the size. Yi-34B is fully bilingual English/Chinese with commercially permissive licensing.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"Spark","full_name":null,"stargazers_count":0,"forks_count":0,"watchers_count":null,"open_issues_count":null,"updated_at":null,"pushed_at":null,"html_url":null,"description":"Spark X1.5 is a 293B MoE model (30B active) with 130+ language support. Built on iFlytek's decades of speech AI expertise with leading voice cloning and mathematical reasoning capabilities.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"NanoClaw","full_name":"qwibitai/nanoclaw","stargazers_count":30375,"forks_count":12876,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:36:31Z","pushed_at":"2026-07-26T15:23:04Z","html_url":"https://github.com/qwibitai/nanoclaw","description":"Runs each Skill in OS-level sandboxes (Apple Sandbox or Docker), directly addressing OpenClaw RCE risks. Best personal alternative for users prioritizing security.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"PicoClaw","full_name":"sipeed/picoclaw","stargazers_count":29729,"forks_count":4345,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T16:48:30Z","pushed_at":"2026-07-23T18:29:33Z","html_url":"https://github.com/sipeed/picoclaw","description":"Optimized for RISC-V and ARM embedded boards, capable of 24/7 operation on $10 devices. Features Whisper voice integration, making it ideal for physical AI assistants and IoT deployments.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"ZeroClaw","full_name":"zeroclaw-labs/zeroclaw","stargazers_count":32399,"forks_count":4843,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T18:51:01Z","pushed_at":"2026-07-26T18:50:53Z","html_url":"https://github.com/zeroclaw-labs/zeroclaw","description":"Ultra-fast, ultra-light Claw variant written in Rust. Sub-10ms startup time and minimal footprint make it ideal for scripting, automation, and edge computing.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"NullClaw","full_name":"nullclaw/nullclaw","stargazers_count":7884,"forks_count":927,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:41:47Z","pushed_at":"2026-07-19T04:20:06Z","html_url":"https://github.com/nullclaw/nullclaw","description":"The absolute minimum. No dependencies, sub-1MB binary — ideal for the most resource-constrained environments.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"IronClaw","full_name":"nearai/ironclaw","stargazers_count":12561,"forks_count":1488,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T15:07:11Z","pushed_at":"2026-07-26T18:57:41Z","html_url":"https://github.com/nearai/ironclaw","description":"Built for stability and long-term continuous operation in industrial environments. C++ core ensures predictable performance over extended uptime.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"nanobot","full_name":"HKUDS/nanobot","stargazers_count":46266,"forks_count":8192,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:40:00Z","pushed_at":"2026-07-26T19:07:41Z","html_url":"https://github.com/HKUDS/nanobot","description":"Delivers core agent functionality with 99% fewer lines of code than OpenClaw.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"Agent Zero","full_name":"agent0ai/agent-zero","stargazers_count":18542,"forks_count":3689,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T14:08:42Z","pushed_at":"2026-07-25T22:58:43Z","html_url":"https://github.com/agent0ai/agent-zero","description":"Multi-agent collaboration platform with Docker container isolation. Features hierarchical agent swarms, web UI, and comprehensive tool support. Best for teams needing collaborative AI agents with security isolation.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"Hermes Agent","full_name":"NousResearch/hermes-agent","stargazers_count":220862,"forks_count":42104,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:56:24Z","pushed_at":"2026-07-26T19:58:15Z","html_url":"https://github.com/NousResearch/hermes-agent","description":"Self-improving AI agent with automatic skill creation from experience. Features 40+ built-in tools, 6 deployment backends (local, Docker, SSH, Modal, Daytona, Singularity), 5+ messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal, Email, CLI), works with 200+ models via OpenRouter. Server-first design with sandboxed execution and container hardening. Gets smarter over time by auto-creating skills from experience.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"NemoClaw","full_name":"NVIDIA/NemoClaw","stargazers_count":21942,"forks_count":2978,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:55:56Z","pushed_at":"2026-07-26T19:52:44Z","html_url":"https://github.com/NVIDIA/NemoClaw","description":"NVIDIA NemoClaw is an open source stack that adds privacy and security controls to OpenClaw. Uses NVIDIA OpenShell to enforce policy-based guardrails, routes inference through Nemotron models, and supports sandboxed deployments via Docker. The most significant fork release after OpenClaw itself.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"},{"name":"OpenClaw","full_name":"openclaw/openclaw","stargazers_count":384222,"forks_count":80721,"watchers_count":null,"open_issues_count":null,"updated_at":"2026-07-26T19:52:43Z","pushed_at":"2026-07-26T19:44:39Z","html_url":"https://github.com/openclaw/openclaw","description":"The original and most widely deployed Claw AI agent. Features the richest ecosystem with 5,000+ official and community skills, covering everything from everyday tasks to automated code review.","latest_release":null,"recent_commits":null,"_source":"database+disk-cache"}]}