[{"data":1,"prerenderedAt":310},["ShallowReactive",2],{"repo-agentscope-ai-qwenpaw-en":3,"i18n-agentscope-ai-qwenpaw-en":307},{"mirrorPool":4,"detail":13,"relatedProjects":202},[5,9],{"key":6,"label":7,"base":8,"type":6},"github","mirror.github","https:\u002F\u002Fgithub.com\u002F",{"key":10,"label":11,"base":12,"type":10},"auto-proxy","mirror.autoProxy","https:\u002F\u002Fgithub.xxlab.tech\u002F",{"owner":14,"repo":15,"repoId":16,"repoUrl":17,"starCount":18,"language":19,"description":20,"languages":21,"screenshots":29,"homepage":35,"pushedAt":36,"ownerAvatar":37,"ownerName":38,"ownerBio":39,"lastSyncTime":40,"lastReleaseTime":41,"tags":42,"license":59,"category":60,"subgroup":61,"releases":62},"agentscope-ai","QwenPaw",1165324947,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw",37619,"TypeScript","Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.",{"TypeScript":22,"Python":23,"Less":24,"Rust":25,"JavaScript":26,"CSS":26,"HTML":27,"Shell":27,"PowerShell":27,"NSIS":27,"Batchfile":28,"Dockerfile":28,"PLpgSQL":28,"Makefile":28},49,48.2,1.2,0.7,0.2,0.1,0,[30],{"sources":31},[32],{"kind":33,"url":34},"jsdelivr","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fin-face\u002Fgithub_imgs@main\u002Fscreenshots\u002F1165324947\u002F2.webp","http:\u002F\u002Fqwenpaw.agentscope.io\u002F","2026-11-11","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211762292?v=4","AgentScope-AI","","2026-11-11T18:05:34.101886+00:00","2026-11-11T12:41:27Z",[43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58],"agent","agent-harness","agentscope","ai-agent","ai-agents","chatbot","harness-engineering","llm-tools","llms","loop-engineering","mcp","personal-ai-assistant","self-hosted","skills","super-agent","webui","Apache-2.0","ai","AI聊天客户端\u002F助手",[63,82,100,117,134,151,168,185],{"tag":64,"publishAt":41,"semVer":65,"prerelease":68,"assets":69},"v2.3.0",[66,67,28],2,3,false,[70,76],{"fileName":71,"sizeMb":72,"sha256":73,"downloadCount":74,"originUrl":75},"QwenPaw-Tauri-2.3.0-macOS.zip",1216.75,"8ebbbce7ca3a65458471ca99a5513549e1e28e9af81fdd33faf742f33605b1f9",6,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0\u002FQwenPaw-Tauri-2.3.0-macOS.zip",{"fileName":77,"sizeMb":78,"sha256":79,"downloadCount":80,"originUrl":81},"QwenPaw-Tauri-2.3.0-Windows-setup.exe",924.07,"90cda18ed1c93ed3bed04b379d21d229915073d5839b1af94297702f11522c70",68,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0\u002FQwenPaw-Tauri-2.3.0-Windows-setup.exe",{"tag":83,"publishAt":84,"semVer":85,"prerelease":86,"assets":87},"v2.3.0-beta.4","2026-11-10T14:46:45Z",[66,67,28],true,[88,94],{"fileName":89,"sizeMb":90,"sha256":91,"downloadCount":92,"originUrl":93},"QwenPaw-Tauri-2.3.0b4-macOS.zip",1216.66,"06c680107019c3bb3a10239ad82a0032cc03f0f5efc3a978ce9816605e9efb22",10,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0-beta.4\u002FQwenPaw-Tauri-2.3.0b4-macOS.zip",{"fileName":95,"sizeMb":96,"sha256":97,"downloadCount":98,"originUrl":99},"QwenPaw-Tauri-2.3.0b4-Windows-setup.exe",923.98,"cdd6cdf7e39baee96a4694c31ae927afc6311d5c723bf5c5b353d8dfc5c59ec3",88,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0-beta.4\u002FQwenPaw-Tauri-2.3.0b4-Windows-setup.exe",{"tag":101,"publishAt":102,"semVer":103,"prerelease":86,"assets":104},"v2.3.0-beta.3","2026-11-09T11:44:40Z",[66,67,28],[105,111],{"fileName":106,"sizeMb":107,"sha256":108,"downloadCount":109,"originUrl":110},"QwenPaw-Tauri-2.3.0b3-macOS.zip",1205.33,"032dab522e74cedafa5a847d32b60874be2209c3bbe0e2c9eafaab58350b057c",13,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0-beta.3\u002FQwenPaw-Tauri-2.3.0b3-macOS.zip",{"fileName":112,"sizeMb":113,"sha256":114,"downloadCount":115,"originUrl":116},"QwenPaw-Tauri-2.3.0b3-Windows-setup.exe",919.71,"f3383f9eed852760a9370e979774daff1fe8e25a12ca760e8a0a6b210a8e1f42",42,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0-beta.3\u002FQwenPaw-Tauri-2.3.0b3-Windows-setup.exe",{"tag":118,"publishAt":119,"semVer":120,"prerelease":86,"assets":121},"v2.3.0-beta.2","2026-11-02T06:08:12Z",[66,67,28],[122,128],{"fileName":123,"sizeMb":124,"sha256":125,"downloadCount":126,"originUrl":127},"QwenPaw-Tauri-2.3.0b2-macOS.zip",1195.19,"184a8022963c1e1d08981f4a5d298878f2ab4ab3a36d5f5b07b6a0f1f33c388c",110,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0-beta.2\u002FQwenPaw-Tauri-2.3.0b2-macOS.zip",{"fileName":129,"sizeMb":130,"sha256":131,"downloadCount":132,"originUrl":133},"QwenPaw-Tauri-2.3.0b2-Windows-setup.exe",915.3,"e307ebaab4cfd5043d47eca3d9551cdf148a41474d55ee170118185abfb09f20",361,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0-beta.2\u002FQwenPaw-Tauri-2.3.0b2-Windows-setup.exe",{"tag":135,"publishAt":136,"semVer":137,"prerelease":86,"assets":138},"v2.3.0-beta.1","2026-10-27T12:42:16Z",[66,67,28],[139,145],{"fileName":140,"sizeMb":141,"sha256":142,"downloadCount":143,"originUrl":144},"QwenPaw-Tauri-2.3.0b1-macOS.zip",1018.49,"b8f947e32a25f418e8bdaae52349329f3e8ba7658d172d9db03eadfcda0bfef3",45,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0-beta.1\u002FQwenPaw-Tauri-2.3.0b1-macOS.zip",{"fileName":146,"sizeMb":147,"sha256":148,"downloadCount":149,"originUrl":150},"QwenPaw-Tauri-2.3.0b1-Windows-setup.exe",881.8,"03aaae06b94d88054e033399e880fc7b5284c8116acbe32465d9619068d49ccb",359,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.3.0-beta.1\u002FQwenPaw-Tauri-2.3.0b1-Windows-setup.exe",{"tag":152,"publishAt":153,"semVer":154,"prerelease":68,"assets":155},"v2.2.2.post1","2026-10-22T11:49:43Z",[66,66,66],[156,162],{"fileName":157,"sizeMb":158,"sha256":159,"downloadCount":160,"originUrl":161},"QwenPaw-Tauri-2.2.2.post1-macOS.zip",1007.64,"883601308a98efe6f97f21f55a68f503ca26fb5c17c5afa0467fcfeb5835a1da",391,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.2.2.post1\u002FQwenPaw-Tauri-2.2.2.post1-macOS.zip",{"fileName":163,"sizeMb":164,"sha256":165,"downloadCount":166,"originUrl":167},"QwenPaw-Tauri-2.2.2.post1-Windows-setup.exe",870.69,"a7a50237d0845981054b5e17fccdc9053b2d49e2149442c50ec75bdd66de2de5",2799,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.2.2.post1\u002FQwenPaw-Tauri-2.2.2.post1-Windows-setup.exe",{"tag":169,"publishAt":170,"semVer":171,"prerelease":68,"assets":172},"v2.2.2","2026-10-15T07:10:45Z",[66,66,66],[173,179],{"fileName":174,"sizeMb":175,"sha256":176,"downloadCount":177,"originUrl":178},"QwenPaw-Tauri-2.2.2-macOS.zip",1002.99,"e01fd9fe6a1af22e062d64dc7003db31890cf55d8660932264eabc2cb29b5005",190,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.2.2\u002FQwenPaw-Tauri-2.2.2-macOS.zip",{"fileName":180,"sizeMb":181,"sha256":182,"downloadCount":183,"originUrl":184},"QwenPaw-Tauri-2.2.2-Windows-setup.exe",865.87,"845167880470bc1af60613a05fe9171b906cbd7f7ed6d3bb6f36fe747de13d06",1502,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.2.2\u002FQwenPaw-Tauri-2.2.2-Windows-setup.exe",{"tag":186,"publishAt":187,"semVer":188,"prerelease":86,"assets":189},"v2.2.2-beta.6","2026-10-14T10:50:00Z",[66,66,66],[190,196],{"fileName":191,"sizeMb":192,"sha256":193,"downloadCount":194,"originUrl":195},"QwenPaw-Tauri-2.2.2b6-macOS.zip",1003.14,"85b31faab5b3dadbe5f18685f95c96e3b961eb0c88c70477a12457bb583c237d",23,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.2.2-beta.6\u002FQwenPaw-Tauri-2.2.2b6-macOS.zip",{"fileName":197,"sizeMb":198,"sha256":199,"downloadCount":200,"originUrl":201},"QwenPaw-Tauri-2.2.2b6-Windows-setup.exe",866.05,"f19a6b1e09637c841f8dcff1b06932f5b5395716fccc4d113f731b436f91c536",114,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Freleases\u002Fdownload\u002Fv2.2.2-beta.6\u002FQwenPaw-Tauri-2.2.2b6-Windows-setup.exe",[203,229,244,265,277,293],{"owner":204,"repo":205,"repoId":206,"category":60,"subgroup":61,"language":207,"tags":208,"starCount":221,"ownerUid":222,"latestTag":223,"platforms":224,"lastReleaseTime":226,"downloadCount":227,"description":228},"blader","humanizer",1136666433,"Python",[209,210,211,212,213,214,215,216,217,205,218,219,220],"agent-skills","ai-humanizer","ai-writing","chatgpt","claude","claude-code","codex","cursor","humanize-ai-text","llm","prompt-engineering","writing-tools",53880,1672,"v2.11.1",[225],"other","2026-08-18T00:59:37Z",5054,"A portable Agent Skill that rewrites AI-generated text to sound more natural and human-like using 35 patterns, without changing what it says.",{"owner":230,"repo":231,"repoId":232,"category":60,"subgroup":61,"language":207,"tags":233,"starCount":234,"ownerUid":235,"latestTag":236,"platforms":237,"lastReleaseTime":241,"downloadCount":242,"description":243},"oobabooga","textgen",580642043,[],47722,112222186,"v4.9",[238,239,240],"windows","mac","linux","2026-05-20T19:02:34Z",76997,"An open-source desktop app for running large language models locally, supporting text chat, vision, tool-calling, and API services, 100% offline with no telemetry.",{"owner":245,"repo":246,"repoId":247,"category":60,"subgroup":61,"language":19,"tags":248,"starCount":257,"ownerUid":258,"latestTag":259,"platforms":260,"lastReleaseTime":262,"downloadCount":263,"description":264},"chatboxai","chatbox",610260322,[249,48,212,213,214,250,251,252,253,254,255,256],"assistant","copilot","deepseek","gemini","gpt","gpt-5","ollama","openai",42323,199570308,"v1.20.3",[238,239,240,261],"android","2026-05-31T10:35:37Z",11836,"A desktop AI client supporting ChatGPT, Claude, and other LLMs, available for Windows, Mac, and Linux.",{"owner":266,"repo":267,"repoId":268,"category":60,"subgroup":61,"language":19,"tags":269,"starCount":270,"ownerUid":271,"latestTag":272,"platforms":273,"lastReleaseTime":274,"downloadCount":275,"description":276},"a-ghorbani","pocketpal-ai",847231566,[],9170,11278140,"v1.23.0",[261],"2026-11-10T11:46:02Z",1285,"PocketPal AI is an open-source AI assistant app that runs entirely on your phone, supporting offline chat with GGUF language models (Gemma, Qwen, Phi, Llama, etc.), on-device neural TTS, personalized Pals, tool calling, and Hugging Face model downloads. All conversations stay on-device with no account, no cloud, and no internet required.",{"owner":278,"repo":278,"repoId":279,"category":60,"subgroup":61,"language":280,"tags":281,"starCount":286,"ownerUid":287,"latestTag":288,"platforms":289,"lastReleaseTime":290,"downloadCount":291,"description":292},"rikkahub",946702247,"Kotlin",[43,261,282,212,251,252,283,284,53,285],"app","jetpack-compose","llm-ui","openrouter",8757,211976783,"3.2.0",[261],"2026-11-10T15:26:37Z",223,"A native Android LLM chat client that supports switching between multiple AI providers, featuring Material You design, multimodal input, MCP support, and agent customization.",{"owner":294,"repo":294,"repoId":295,"category":60,"subgroup":61,"language":296,"tags":297,"starCount":300,"ownerUid":301,"latestTag":302,"platforms":303,"lastReleaseTime":304,"downloadCount":305,"description":306},"nullclaw",1159542259,"Zig",[60,249,298,299],"personal","zig",8101,262007611,"v2026.5.29",[238,239,240,225],"2026-05-29T13:41:10Z",3413,"A fully autonomous AI assistant infrastructure written in Zig — 678KB static binary, ~1MB RAM, \u003C2ms startup, runs on ARM, x86, and RISC-V, with 50+ providers, 19 channels, and 35+ tools.",{"description":308,"readmeHtml":309},"QwenPaw is a personal AI assistant that deploys locally or in the cloud with one click, featuring a three-layer memory system (live working context, full verbatim history, and a self-evolving personal knowledge base), compatibility with local models and 14+ cloud providers, support for DingTalk, Lark, WeChat, Discord, Telegram, and other chat channels, and extensibility through Skills and plugins.","\u003Ch2 id=\"project-overview\">Project Overview\u003C\u002Fh2>\u003Cp>QwenPaw is your personal AI assistant — deploy locally or in the cloud, extend with Skills & Plugins, connect across every channel. It never forgets: a three-layer memory system includes live working context, full verbatim history, and a self-evolving personal knowledge base powered by ReMe. Conversations and resources continuously become readable, editable, searchable, and linked Markdown memory.\u003C\u002Fp>\n\u003Ch2 id=\"key-features\">Key Features\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>Never forgets\u003C\u002Fstrong>: Three-layer memory (live working context, full verbatim history, self-evolving personal knowledge base)\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Local or cloud, runs free\u003C\u002Fstrong>: Built-in QwenPaw-Flash models (2B \u002F 4B \u002F 9B) trained for agent tasks, no API key needed; also works with Ollama, LM Studio, or 14+ cloud providers\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Security built in\u003C\u002Fstrong>: Kernel-level Sandbox, Tool Guard, File Guard, Skill Scanner, and Access Policy. Dangerous commands are blocked before they run\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Multi-agent & parallel\u003C\u002Fstrong>: Spawn independent agents with their own memory and skills. Sub-agents at runtime. Agent Communication Protocol (ACP) for cross-system orchestration\u003C\u002Fli>\n\u003Cli>\u003Cstrong>File workspace\u003C\u002Fstrong>: Unified file navigation, preview, editing, diffs, upload, and download across project and Agent files\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Extensible\u003C\u002Fstrong>: Skills for scheduling, documents, browser, news, and more. Plugin architecture with a marketplace. MCP integration for external tools\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Reachable anywhere\u003C\u002Fstrong>: DingTalk, Lark, WeChat, Discord, Telegram, iMessage, QQ — one instance, all channels\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Yours, not ours\u003C\u002Fstrong>: Deploy locally — data stays on your machine. No third-party hosting, no data upload\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"target-audience\">Target Audience\u003C\u002Fh2>\u003Cul>\n\u003Cli>Users who want a personal AI assistant with full data control\u003C\u002Fli>\n\u003Cli>Users who need unified AI capabilities across multiple chat channels\u003C\u002Fli>\n\u003Cli>Users who want to automate daily tasks (news digests, report generation, multi-channel broadcasting)\u003C\u002Fli>\n\u003Cli>Developers and users who need code review and document processing\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"quick-start\">Quick Start\u003C\u002Fh2>\u003Col>\n\u003Cli>Visit the official documentation at qwenpaw.agentscope.io for installation options\u003C\u002Fli>\n\u003Cli>Choose local or cloud deployment\u003C\u002Fli>\n\u003Cli>Configure a model Provider (use built-in QwenPaw-Flash or connect Ollama \u002F LM Studio \u002F cloud API)\u003C\u002Fli>\n\u003Cli>Connect chat channels (DingTalk, Lark, WeChat, Discord, Telegram, etc.)\u003C\u002Fli>\n\u003Cli>Install Skills and plugins as needed to build custom workflows\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Ch2 id=\"core-advantages\">Core Advantages\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>Data sovereignty\u003C\u002Fstrong>: With local deployment, data stays entirely on your machine with no third-party hosting\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Three-layer memory\u003C\u002Fstrong>: Conversations and resources continuously become a searchable, linked Markdown knowledge base\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Unified multi-channel\u003C\u002Fstrong>: One instance connects to all mainstream chat platforms\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Multi-agent architecture\u003C\u002Fstrong>: Supports spawning independent agents, runtime sub-agents, and cross-system orchestration\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Security built in\u003C\u002Fstrong>: Dangerous commands are intercepted by kernel-level Sandbox and multiple guards before execution\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"system-requirements\">System Requirements\u003C\u002Fh2>\u003Cul>\n\u003Cli>OS: Windows, macOS, Linux\u003C\u002Fli>\n\u003Cli>Additional dependencies: Ollama \u002F LM Studio required for local running, or use the built-in QwenPaw Local runtime; cloud deployment requires the corresponding platform runtime\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"notes\">Notes\u003C\u002Fh2>\u003Cul>\n\u003Cli>QwenPaw-Flash models (2B \u002F 4B \u002F 9B) are trained for agent tasks and suit daily assistant scenarios; for complex reasoning tasks, connecting a larger model is recommended\u003C\u002Fli>\n\u003Cli>For multi-user scenarios, refer to the self-hosted QwenPaw Hub solution\u003C\u002Fli>\n\u003C\u002Ful>\n",1794623933938]