[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-11216":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":16,"starSnapshotCount":16,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},11216,"cc-connect","chenhg5\u002Fcc-connect","chenhg5","Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu\u002FLark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant from anywhere — no public IP required for most platforms.",null,"https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect","Go",12156,1141,28,170,0,111,541,3510,504,116.17,false,"main","2026-06-12 04:00:54","\u003Cp align=\"center\">\n  \u003Cimg src=\".\u002Fdocs\u002Fimages\u002Fbanner.svg\" alt=\"CC-Connect Banner\" width=\"800\"\u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\u002Factions\u002Fworkflows\u002Fci.yml\">\n    \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg\" alt=\"CI Status\"\u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\u002Freleases\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fchenhg5\u002Fcc-connect?include_prereleases\" alt=\"Release\"\u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fcc-connect\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdm\u002Fcc-connect?logo=npm\" alt=\"npm downloads\"\u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\u002Fblob\u002Fmain\u002FLICENSE\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg\" alt=\"License\"\u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgoreportcard.com\u002Freport\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\">\n    \u003Cimg src=\"https:\u002F\u002Fgoreportcard.com\u002Fbadge\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\" alt=\"Go Report Card\"\u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FkHpwgaM4kq\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join-5865F2?logo=discord&logoColor=white\" alt=\"Discord\"\u002F>\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Ft.me\u002F+odGNDhCjbjdmMmZl\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTelegram-Group-26A5E4?logo=telegram&logoColor=white\" alt=\"Telegram\"\u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\".\u002FREADME.md\">English\u003C\u002Fa> | \u003Ca href=\".\u002FREADME.zh-CN.md\">中文\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F23266\" target=\"_blank\">\n    \u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F23266\" alt=\"chenhg5\u002Fcc-connect | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\n## ❤️ Sponsor\n\n> Want to appear here? Contact: chg80333@gmail.com | WeChat: mongorz\n\n\u003Cdetails open>\n\u003Csummary>Sponsors\u003C\u002Fsummary>\n\n[![MiniMax](assets\u002Fbanners\u002Fminimax-en.jpeg)](https:\u002F\u002Fplatform.minimax.io\u002Fsubscribe\u002Ftoken-plan?code=lqYrKBvjke&source=link)\n\nMiniMax-M2.7 is a next-generation large language model designed for autonomous evolution and real-world productivity. Unlike traditional models, M2.7 actively participates in its own improvement through agent teams, dynamic tool use, and reinforcement learning loops. It delivers strong performance in software engineering (56.22% on SWE-Pro, 55.6% on VIBE-Pro, 57.0% on Terminal Bench 2) and excels in complex office workflows, achieving a leading 1495 ELO on GDPval-AA. With high-fidelity editing across Word, Excel, and PowerPoint, and a 97% adherence rate across 40+ complex skills, M2.7 sets a new standard for building AI-native workflows and organizations.\n\n[Click here](https:\u002F\u002Fplatform.minimax.io\u002Fsubscribe\u002Ftoken-plan?code=lqYrKBvjke&source=link) to get an exclusive 12% off the MiniMax Token Plan + voucher for cc-connect users!\n\n---\n\n\u003Ctable>\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Faigocode.com\u002Finvite\u002FCYY3C85C\">\u003Cimg src=\"assets\u002Fsponsors\u002Faigocode.png\" alt=\"AIGoCode\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to AIGoCode for sponsoring this project! AIGoCode is an all-in-one platform that integrates Claude Code, Codex, and the latest Gemini models, providing you with stable, efficient, and highly cost-effective AI coding services. The platform offers flexible subscription plans, zero risk of account suspension, direct access with no VPN required, and lightning-fast responses. AIGoCode has prepared a special benefit for cc-connect users: if you register via \u003Ca href=\"https:\u002F\u002Faigocode.com\u002Finvite\u002FCYY3C85C\">this link\u003C\u002Fa>, you'll receive an extra 10% bonus credit on your first top-up!\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Faihubmix.com\u002F?aff=mGTx\">\u003Cimg src=\"assets\u002Fsponsors\u002Faihubmix.png\" alt=\"AIHubMix\" width=\"120\">\u003C\u002Fa> \u003Cb>AIHubMix\u003C\u002Fb>\u003C\u002Ftd>\n\u003Ctd>Thanks to AIHubMix for sponsoring this project! AIHubMix offers deep integration with 500+ global models including OpenAI, Claude, Gemini, Qwen, DeepSeek, Kimi. Unlimited concurrency, production-grade stability on Google Cloud. One API Key drives all your Agents with native OpenAI\u002FAnthropic\u002FGemini format support — zero code changes. Pay-as-you-go pricing aligned with official providers, plus free models like coding-glm-5.1-free. \u003Ca href=\"https:\u002F\u002Faihubmix.com\u002F?aff=mGTx\">Click here to sign up!\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fnekocode.ai\u002F?aff=CC-CONNECT\">\u003Cimg src=\"assets\u002Fsponsors\u002Fnekocode.jpg\" alt=\"NekoCode\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to NekoCode for sponsoring this project! NekoCode provides reliable, stable, and efficient API relay services for Claude and CodeX with transparent pricing. Exclusive 10% discount for cc-connect users with promo code: CC-CONNECT. High-value, stable AI model access for developers. Register via \u003Ca href=\"https:\u002F\u002Fnekocode.ai\u002F?aff=CC-CONNECT\">this link\u003C\u002Fa>.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fwww.dmxapi.cn\u002Fregister?aff=NDln\">\u003Cimg src=\"assets\u002Fsponsors\u002Fdmx-en.jpg\" alt=\"DMXAPI\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to DMXAPI for sponsoring this project! DMXAPI provides global large model API services to 200+ enterprise users. One API key for all global models. Features include: instant invoicing, unlimited concurrency, starting from $0.15, 24\u002F7 technical support. GPT\u002FClaude\u002FGemini all at 32% off, domestic models 20-50% off, Claude Code exclusive models at 66% off! Register via \u003Ca href=\"https:\u002F\u002Fwww.dmxapi.cn\u002Fregister?aff=NDln\">this link\u003C\u002Fa>.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fwww.shengsuanyun.com\u002F?from=CH_67XCLZGS\">\u003Cimg src=\"assets\u002Fsponsors\u002Fshengsuanyun.svg\" alt=\"Shengsuanyun\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to Shengsuanyun for sponsoring this project! Shengsuanyun is a super factory dedicated to serving AI Native Teams, an industrial-grade AI task parallel execution platform, and a model marketplace that aggregates and supplies computing power from domestic and international LLM and image\u002Fvideo multimedia models such as Claude, Chatgpt, and Gemini. It guarantees no reverse engineering or data manipulation, boasts a 99.7% SLA availability across the entire site, and its \u003Ca href=\"https:\u002F\u002Fwatch.shengsuanyun.com\u002Fstatus\u002Fshengsuanyun\">monitoring interface\u003C\u002Fa> is consistently green. Furthermore, it offers an enterprise-grade customized gateway for refined cost and access control, featuring intelligent routing, security protection, and BYOK enterprise-provided key hosting. The platform is billed on a pay-as-you-go basis and with a tokens plan (coming soon), and invoices are available. New users who register using \u003Ca href=\"https:\u002F\u002Fwww.shengsuanyun.com\u002F?from=CH_67XCLZGS\">this link\u003C\u002Fa> will receive 10 yuan in model power and a 10% bonus on their first deposit.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fwww.aicodemirror.com\u002Fregister?invitecode=KDHMUP\">\u003Cimg src=\"assets\u002Fsponsors\u002Faicodemirror.jpg\" alt=\"AICodeMirror\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to AICodeMirror for sponsoring this project! AICodeMirror provides official high-stability relay services for Claude Code \u002F Codex \u002F Gemini CLI, with enterprise-grade concurrency, fast invoicing, and 24\u002F7 dedicated technical support. Claude Code \u002F Codex \u002F Gemini official channels at 38% \u002F 2% \u002F 9% of original price, with extra discounts on top-ups! AICodeMirror offers special benefits for CC users: register via \u003Ca href=\"https:\u002F\u002Fwww.aicodemirror.com\u002Fregister?invitecode=KDHMUP\">this link\u003C\u002Fa> to enjoy 20% off your first top-up, and enterprise customers can get up to 25% off!\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fcc.anyroute.io\u002Fregister?aff=CR455DSQSKEV\">\u003Cimg src=\"assets\u002Fsponsors\u002Fanyrouteio.png\" alt=\"AnyRoute.io\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to AnyRoute.io for sponsoring this project! AnyRoute.io is a reliable, stable, and efficient API relay platform integrating the latest Claude Code and Codex models. Transparent pricing with rates as low as 93% off official prices (just 0.7x), supports invoicing and enterprise-grade high-concurrency usage. Register via \u003Ca href=\"https:\u002F\u002Fcc.anyroute.io\u002Fregister?aff=CR455DSQSKEV\">this link\u003C\u002Fa> to get started.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Faicanapi.com\u002Fregister?aff=rIEy\">\u003Cimg src=\"assets\u002Fsponsors\u002Faican.jpg\" alt=\"aicanapi.com\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to aicanapi.com for sponsoring this project! Aican API provides high-performance, low-latency, high-concurrency API services for enterprises and developers. Claude Code models at up to 84% off, other models at 80% off official price. Doubao Seedance 2 real-person generation service with queue-free access for faster responses. Choose Aican API for simpler, more efficient, and more cost-effective enterprise-grade AI services. Register via \u003Ca href=\"https:\u002F\u002Faicanapi.com\u002Fregister?aff=rIEy\">this link\u003C\u002Fa> to get started.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fpateway.ai\u002F?ch=2qn568&aff=DRA4VUFS\">\u003Cimg src=\"assets\u002Fsponsors\u002Fpatewayai.png\" alt=\"Pateway\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to Pateway for sponsoring this project! PatewayAI is a premium API relay service for serious AI developers, offering 100% official direct access to Claude and Codex models — no reverse engineering, no quality degradation. Transparent billing with token-level verification. Enterprise-grade concurrency, formal contracts and invoicing available. Register via \u003Ca href=\"https:\u002F\u002Fpateway.ai\u002F?ch=2qn568&aff=DRA4VUFS\">this link\u003C\u002Fa> to get $3 free trial credit, up to 40% off on top-ups, and referral rewards up to $150!\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fcy.10dianai.com\u002Fregister?aff=3FQn\">\u003Cimg src=\"assets\u002Fsponsors\u002F10dianai.png\" alt=\"10点AI\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to 10点AI for sponsoring this project! 10dian-AI Enterprise Platform is an AI API gateway for developers and enterprises, aggregating GPT, Claude, Gemini, DeepSeek and more. Optimized for production environments with stable high-concurrency operation, avoiding interface jitter and timeout issues. Affordable pricing, stable uptime, official guarantee. Register via \u003Ca href=\"https:\u002F\u002Fcy.10dianai.com\u002Fregister?aff=3FQn\">this link\u003C\u002Fa> to get ¥5 free credit!\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fcode0.ai\u002Fregister?aff=5cGO\">\u003Cimg src=\"assets\u002Fsponsors\u002Fcode0.svg\" alt=\"Code0\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to Code0 for sponsoring this project! Code0 is an AI model aggregation API relay service for Chinese developers, compatible with OpenAI \u002F Anthropic \u002F Gemini protocols. One key for all mainstream models, stable support for Claude Code, Codex, Gemini CLI, cc-connect and more. Fixed exchange rate: ¥1.5 CNY = $1 USD API credit, transparent pricing, domestic direct connection, ready to use. Register via \u003Ca href=\"https:\u002F\u002Fcode0.ai\u002Fregister?aff=5cGO\">this link\u003C\u002Fa>.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fpassport.compshare.cn\u002Fregister?referral_code=H65IOClRGu5CM7nn5ykfad&ytag=GPU_YY_YX_git_cc-connect\">\u003Cimg src=\"assets\u002Fsponsors\u002Fyouyunzhisuan.png\" alt=\"优云智算\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to 优云智算 for sponsoring this project! 优云智算 (UCloud AI Cloud Platform) provides stable and comprehensive domestic and international model APIs with just one key. Featuring high-value Coding Plan packages (monthly or per-use), plus stable official relay for overseas models. Supports Claude Code, Codex, and API calls. Enterprise features include high concurrency, 7x24 technical support, and self-service invoicing. Register via \u003Ca href=\"https:\u002F\u002Fpassport.compshare.cn\u002Fregister?referral_code=H65IOClRGu5CM7nn5ykfad&ytag=GPU_YY_YX_git_cc-connect\">this link\u003C\u002Fa> to receive ¥5 free platform credit!\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fdragoncode.codes\u002Fregister?ref=23ZELCPX\">\u003Cimg src=\"assets\u002Fsponsors\u002Fdragoncode.png\" alt=\"DragonCode\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to DragonCode for supporting this project. DragonCode has prepared a special benefit for cc-connect users: register via \u003Ca href=\"https:\u002F\u002Fdragoncode.codes\u002Fregister?ref=23ZELCPX\">this link\u003C\u002Fa> to get started.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fcoder.visioncoder.cn\">\u003Cimg src=\"assets\u002Fsponsors\u002Fvisioncoder.png\" alt=\"VisionCoder\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to VisionCoder for supporting this project. \u003Ca href=\"https:\u002F\u002Fcoder.visioncoder.cn\">VisionCoder Developer Platform\u003C\u002Fa> is a reliable and efficient API relay service provider, offering access to mainstream AI models such as Claude Code, Codex, and Gemini. It helps developers and teams integrate AI capabilities more easily and improve productivity. VisionCoder is also offering our users a limited-time \u003Ca href=\"https:\u002F\u002Fcoder.visioncoder.cn\">Token Plan\u003C\u002Fa> promotion: buy 1 month and get 1 month free.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fconsole.claudeapi.com\u002Fregister?aff=GDbA\">\u003Cimg src=\"assets\u002Fsponsors\u002Fclaudeapi.svg\" alt=\"claudeapi.com\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to claudeapi.com for sponsoring this project! claudeapi is a high-quality direct Claude connection service for mid-to-high-end users. It is fully integrated with Anthropic's official first-party Keys and AWS Bedrock official channels — no reverse engineering, no intelligence degradation, no stitching. It fully preserves the official capabilities, long context, and tool-calling performance of Opus \u002F Sonnet \u002F Haiku. Designed specifically for Claude Code power users, Agent developers, and enterprise teams, it focuses on out-of-the-box usability and enterprise-grade stability. Invoicing and team onboarding are supported. Register via \u003Ca href=\"https:\u002F\u002Fconsole.claudeapi.com\u002Fregister?aff=GDbA\">this link\u003C\u002Fa>.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\n\u003Ctr>\n\u003Ctd width=\"150\">\u003Ca href=\"https:\u002F\u002Fddshub.short.gy\u002Fccconnect\">\u003Cimg src=\"assets\u002Fsponsors\u002Fddshub.png\" alt=\"DDS Hub\" width=\"120\">\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd>Thanks to DDS for sponsoring this project! DDS Hub is a reliable and high-performance Claude and CodeX API proxy service. We provides cost-effective domestic Claude direct acceleration services for both individual and enterprise users. We offer stable and low-latency Claude Max number pools, with full support for Claude Haiku, Opus, Sonnet, GPT 5.4 and other flagship models. Invoices are available for recharges of 1000 RMB or more. Enterprise customers can also enjoy customized grouping and dedicated technical support services. Exclusive benefit for CC connect users: Register via \u003Ca href=\"https:\u002F\u002Fddshub.short.gy\u002Fccconnect\">this link\u003C\u002Fa> and enjoy an extra 10% credit on your first recharge (please contact the group admin to claim after recharging)!\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003C\u002Fdetails>\n\n---\n\n\u003Cbr>\n\n\u003Cp align=\"center\">\n  \u003Cb>Control your local AI agents from any chat app. Anywhere, anytime.\u003C\u002Fb>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  cc-connect bridges AI agents running on your machine to the messaging platforms you already use.\u003Cbr\u002F>\n  Code review, research, automation, data analysis — anything an AI agent can do,\u003Cbr\u002F>\n  now accessible from your phone, tablet, or any device with a chat app.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fimages\u002Fconnector.png\" alt=\"CC-Connect Architecture\" width=\"90%\"\u002F>\n\u003C\u002Fp>\n\n\n## 🆕 What’s New in v1.3.0\n\n- **🌐 Web Admin UI (Recommended)** — Full management dashboard embedded in the binary — **no extra dependencies**. Create and edit projects, manage providers, monitor sessions, edit cron jobs, and **chat with your agent directly from the browser**. Supports 5 languages (en\u002Fzh\u002Fzh-TW\u002Fja\u002Fes). We recommend managing cc-connect through the web UI instead of editing `config.toml` by hand. Run `cc-connect web` to configure and open the dashboard, then run `cc-connect` to start the service.\n- **Lifecycle Event Hooks** — New `[[hooks]]` config triggers shell commands or HTTP webhooks on message, session, cron, permission, and error events. Async by default, fail-open.\n- **Skill Management** — New `\u002Fskills` page with local skill browser and recommended presets.\n- **Global Provider Management** — Add\u002Fedit\u002Fdelete providers in the web UI; import from cc-switch config.\n- **Personal WeChat** — Chat with your local agent from **Weixin (personal)** via ilink long-polling; QR `weixin setup`, CDN media, no public IP. *[Setup → `docs\u002Fweixin.md`](docs\u002Fweixin.md)*\n- **Weibo DM** — Chat with your agent via **Weibo private messages** over WebSocket; no public IP needed, text streaming supported.\n- **Feishu Enhancements** — Auto-resolve `@name` mentions, multi-level reply chain recognition, done-emoji reactions.\n- **New Agents** — Kimi CLI and Pi agent support added.\n\n\n## 🧩 Platform feature snapshot\n\nHigh-level view of what each **built-in platform** can do in cc-connect.\n\n**Legend**\n\n| Symbol | Meaning |\n|--------|---------|\n| ✅ | Works in **stable** cc-connect with typical configuration |\n| ⚠️ | Partial, needs extra config (e.g. speech \u002F ASR), or limited by the vendor app or API |\n| ❌ | Not supported or not applicable in practice |\n\n† **QQ (NapCat \u002F OneBot)** — unofficial self-hosted bridge; behaviour depends on your NapCat \u002F network setup.\n\n| Capability | Feishu | DingTalk | Telegram | Slack | Discord | LINE | WeCom | Weibo | **Weixin**\u003Cbr>*(personal)* | QQ† | QQ Bot |\n|------------|:------:|:--------:|:--------:|:-----:|:-------:|:----:|:-----:|:-----:|:-------------------------:|:---:|:------:|\n| Text & slash commands | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |\n| Markdown \u002F cards | ✅ | ✅ | ✅ | ✅ | ✅ | ⚠️ | ⚠️ | ❌ | ✅ | ✅ | ✅ |\n| Streaming \u002F chunked replies | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |\n| Images & files | ✅ | ✅ | ✅ | ✅ | ✅ | ⚠️ | ✅ | ❌ | ✅ | ✅ | ✅ |\n| Voice \u002F STT \u002F TTS | ⚠️ | ⚠️ | ✅ | ⚠️ | ⚠️ | ❌ | ⚠️ | ❌ | ✅ | ⚠️ | ⚠️ |\n| Private (DM) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |\n| Group \u002F channel | ✅ | ✅ | ✅ | ✅ | ✅ | ⚠️ | ✅ | ❌ | ✅ | ✅ | ✅ |\n\n> **WeCom:** Webhook mode needs a **public URL**; long-connection \u002F WS style setups often do not.  \n> **Voice row:** many platforms need `[speech]` \u002F TTS providers enabled in `config.toml`; values are a best-effort summary.  \n> Per-platform setup: [Platform setup guides](#-platform-setup-guides) below.\n\n\n## ✨ Why cc-connect?\n\n### 🤖 Universal Agent Support\n**10+ AI Agents** — Claude Code, Codex, Cursor Agent, Kimi CLI, Qoder CLI, Gemini CLI, OpenCode, iFlow CLI, Pi, Devin — plus any agent that supports the [Agent Client Protocol (ACP)](https:\u002F\u002Fagentclientprotocol.com\u002Fget-started\u002Fagents). Use whichever fits your workflow, or all of them at once.\n\n### 📱 Platform Flexibility\n**11 Chat Platforms** — Feishu, DingTalk, Slack, Telegram, Discord, WeChat Work, Weibo, LINE, QQ, QQ Bot (Official), plus **Weixin (personal ilink)** for **personal WeChat**. Most platforms need **zero public IP**.\n\n### 🔄 Multi-Agent Orchestration\n**Multi-Bot Relay** — Bind multiple bots in a group chat and let them communicate with each other. Ask Claude, get insights from Gemini — all in one conversation.\n\n### 🎮 Complete Chat Control\n**Full Control from Chat** — Switch models (`\u002Fmodel`), tune reasoning (`\u002Freasoning`), change permission modes (`\u002Fmode`), manage sessions, all via slash commands.\n\n**Directory Switching in Chat** — Change where the next session starts with `\u002Fdir \u003Cpath>` (and `\u002Fcd \u003Cpath>` as a compatibility alias), plus quick history jump via `\u002Fdir \u003Cnumber>` \u002F `\u002Fdir -`.\n\n### 🧠 Persistent Memory\n**Agent Memory** — Read and write agent instruction files (`\u002Fmemory`) without touching the terminal.\n\n### ⏰ Intelligent Scheduling\n**Scheduled Tasks** — Set up cron jobs in natural language. *\"Every day at 6am, summarize GitHub trending\"* just works.\n\n### 🎤 Multimodal Support\n**Voice & Images** — Send voice messages or screenshots; cc-connect handles STT\u002FTTS and multimodal forwarding.\n\n### 📦 Multi-Project Architecture\n**Multi-Project** — One process, multiple projects, each with its own agent + platform combo.\n\n### 🌍 Multilingual Interface\n**5 Languages** — Native support for English, Chinese (Simplified & Traditional), Japanese, and Spanish. Built-in i18n ensures everyone feels at home.\n\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fimages\u002Fscreenshot\u002Fcc-connect-lark.JPG\" alt=\"飞书\" width=\"32%\" \u002F>\n  \u003Cimg src=\"docs\u002Fimages\u002Fscreenshot\u002Fcc-connect-telegram.JPG\" alt=\"Telegram\" width=\"32%\" \u002F>\n  \u003Cimg src=\"docs\u002Fimages\u002Fscreenshot\u002Fcc-connect-wechat.JPG\" alt=\"微信\" width=\"32%\" \u002F>\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Cem>Left：Lark  |  Telegram  |  Right：Wechat\u003C\u002Fem>\n\u003C\u002Fp>\n\n\n## 🚀 Quick Start\n\n### 🤖 Install & Configure via AI Agent (Recommended)\n\n> **The easiest way** — Send this to Claude Code or any AI coding agent, and it will handle the entire installation and configuration for you:\n\n```bash\nFollow https:\u002F\u002Fraw.githubusercontent.com\u002Fchenhg5\u002Fcc-connect\u002Frefs\u002Fheads\u002Fmain\u002FINSTALL.md to install and configure cc-connect.\n```\n\n\n### 📦 Manual Install\n\n**Via npm:**\n\n```bash\nnpm install -g cc-connect\n```\n\n**Via Homebrew (macOS \u002F Linux):**\n\n```bash\nbrew install cc-connect\n```\n\n**Download binary from [GitHub Releases](https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\u002Freleases):**\n\n```bash\n# Linux amd64 - Stable\ncurl -L -o cc-connect https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\u002Freleases\u002Flatest\u002Fdownload\u002Fcc-connect-linux-amd64\nchmod +x cc-connect\nsudo mv cc-connect \u002Fusr\u002Flocal\u002Fbin\u002F\n\n```\n\n**Build from source (requires Go 1.22+):**\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect.git\ncd cc-connect\nmake build\n```\n\n\n### ⚙️ Configure\n\n> **💡 Tip: Use the Web UI to configure** — After installing, run `cc-connect web` to configure the web admin and open the dashboard in your browser. You can visually create projects, add platforms, manage providers, and chat with your agent — no need to manually edit TOML files. **Note:** `cc-connect web` only configures and opens the browser — you still need to run `cc-connect` separately to start the service.\n\nIf you prefer manual configuration:\n\n```bash\nmkdir -p ~\u002F.cc-connect\ncp config.example.toml ~\u002F.cc-connect\u002Fconfig.toml\nvim ~\u002F.cc-connect\u002Fconfig.toml\n```\n\nSet `admin_from = \"alice,bob\"` in a project to allow those user IDs to run privileged commands such as `\u002Fdir` and `\u002Fshell`.\nWhen a user runs `\u002Fdir reset`, cc-connect restores the configured `work_dir` and clears the persisted override stored under `data_dir\u002Fprojects\u002F\u003Cproject>.state.json`.\n\n\n### ▶️ Run\n\n```bash\n.\u002Fcc-connect\n```\n\n\n### 🔄 Upgrade\n\n```bash\n# npm\nnpm install -g cc-connect\n\n# Homebrew\nbrew upgrade cc-connect\n\n# Binary self-update\ncc-connect update           # Stable\ncc-connect update --pre     # Include pre-releases\n```\n\n\n## 📊 Support Matrix\n\n| Component | Type | Status |\n|-----------|------|--------|\n| Agent | Claude Code | ✅ Supported |\n| Agent | Codex (OpenAI) | ✅ Supported |\n| Agent | Cursor Agent | ✅ Supported |\n| Agent | Gemini CLI (Google) | ✅ Supported |\n| Agent | Qoder CLI | ✅ Supported |\n| Agent | OpenCode (Crush) | ✅ Supported |\n| Agent | iFlow CLI | ✅ Supported |\n| Agent | Kimi CLI (Moonshot) | ✅ Supported |\n| Agent | Pi (Cursor Background Agent) | ✅ Supported |\n| Agent | ACP (Agent Client Protocol) | ✅ Any [ACP-compatible agent](https:\u002F\u002Fagentclientprotocol.com\u002Fget-started\u002Fagents) |\n| Agent | Devin (Cognition) | ✅ Supported (via ACP) |\n| Agent | Goose (Block) | 🔜 Planned |\n| Agent | Aider | 🔜 Planned |\n| Platform | Feishu (Lark) | ✅ WebSocket — no public IP needed |\n| Platform | DingTalk | ✅ Stream — no public IP needed |\n| Platform | Telegram | ✅ Long Polling — no public IP needed |\n| Platform | Slack | ✅ Socket Mode — no public IP needed |\n| Platform | Discord | ✅ Gateway — no public IP needed |\n| Platform | Weibo | ✅ WebSocket — no public IP needed |\n| Platform | LINE | ✅ Webhook — public URL required |\n| Platform | WeChat Work | ✅ WebSocket \u002F Webhook |\n| Platform | Weixin (personal, ilink) | ✅— HTTP long polling — no public IP needed |\n| Platform | QQ (NapCat\u002FOneBot) | ✅ WebSocket |\n| Platform | QQ Bot (Official) | ✅ WebSocket — no public IP needed |\n\n\n## 📖 Platform Setup Guides\n\n| Platform | Guide | Connection | Public IP? |\n|----------|-------|------------|------------|\n| Feishu (Lark) | [docs\u002Ffeishu.md](docs\u002Ffeishu.md) | WebSocket | No |\n| DingTalk | [docs\u002Fdingtalk.md](docs\u002Fdingtalk.md) | Stream | No |\n| Telegram | [docs\u002Ftelegram.md](docs\u002Ftelegram.md) | Long Polling | No |\n| Slack | [docs\u002Fslack.md](docs\u002Fslack.md) | Socket Mode | No |\n| Discord | [docs\u002Fdiscord.md](docs\u002Fdiscord.md) | Gateway | No |\n| Weibo | [docs\u002Fweibo.md](docs\u002Fweibo.md) | WebSocket | No |\n| WeChat Work | [docs\u002Fwecom.md](docs\u002Fwecom.md) | WebSocket \u002F Webhook | No (WS) \u002F Yes (Webhook) |\n| Weixin (personal) | [docs\u002Fweixin.md](docs\u002Fweixin.md) | HTTP long polling (ilink) | No |\n| QQ \u002F QQ Bot | [docs\u002Fqq.md](docs\u002Fqq.md) | WebSocket | No |\n\n\n## 🎯 Key Features\n\n### 💬 Session Management\n\n```\n\u002Fnew [name]       Start a new session\n\u002Flist             List all sessions\n\u002Fswitch \u003Cid>      Switch session\n\u002Fcurrent          Show current session\n\u002Fdir [path|reset] Show, switch, or reset work directory\n```\n\nProject configs rotate to a fresh session automatically after long inactivity. This prevents \"context drift\" where stale chat history (failed commands, debugging noise) is repeatedly re-ingested via `--continue` and starts to dominate the model's attention. The previous session is preserved and remains accessible via `\u002Flist` and `\u002Fswitch`.\n\n```toml\n[[projects]]\nreset_on_idle_mins = 30   # default when unset; set to 0 to disable\n```\n\nThe default is **30 minutes** when unset. Set `reset_on_idle_mins = 0` to opt out and always continue the previous session.\n\n### 🛡️ OS-User Isolation (`run_as_user`)\n\nOn Linux\u002FmacOS, a project can spawn its agent under a different Unix\nuser for OS-level file-system isolation from the supervisor user that\nruns cc-connect. Currently supported by Claude Code.\n\n```toml\n[[projects]]\nname = \"claude-sandboxed\"\nrun_as_user = \"partseeker-coder\"\nrun_as_env = [\"PGSSLROOTCERT\"]\n```\n\nThe target user needs passwordless sudo from the supervisor, no sudo\nof its own, read+write on `work_dir`, and its own `~\u002F.claude\u002Fsettings.json`\nwith whatever credentials the agent uses. If you authenticate via\n`claude.ai` OAuth, symlink the target user's `~\u002F.claude\u002F.credentials.json`\nto the supervisor's copy so token refresh stays in sync — see the\n[environment propagation checklist](.\u002Fdocs\u002Fusage.md#environment-propagation-what-moves-into-the-target-users-home)\nfor details. See\n[`docs\u002Fusage.md`](.\u002Fdocs\u002Fusage.md#running-agents-as-a-different-unix-user-run_as_user)\nfor the full setup.\n\nBefore starting cc-connect, audit the setup with:\n\n```bash\ncc-connect doctor user-isolation\n```\n\nThis runs three go\u002Fno-go preflight gates and an isolation probe that\nreports what the target user can and cannot read. cc-connect refuses to\nstart if any gate fails or if the probe detects a cross-user leak.\n\n---\n\n### 🔐 Permission Modes\n\n```\n\u002Fmode             Show available modes\n\u002Fmode yolo        # Auto-approve all tools\n\u002Fmode default     # Ask for each tool\n```\n\n\n### 🔄 Provider Management\n\n```\n\u002Fprovider list              List providers\n\u002Fprovider switch \u003Cname>     Switch API provider at runtime\n```\n\n\n### 🤖 Model Selection\n\n```\n\u002Fmodel                      List available models (format: alias - model)\n\u002Fmodel switch \u003Calias>       Switch to model by alias\n```\n\n\n### 📂 Work Directory\n\n```\n\u002Fdir                         Show current work directory and history\n\u002Fdir \u003Cpath>                  Switch to a path (relative or absolute)\n\u002Fdir \u003Cnumber>                Switch from history\n\u002Fdir -                       Switch to previous directory\n\u002Fcd \u003Cpath>                   Compatibility alias for \u002Fdir \u003Cpath>\n```\n\n\n### ⏰ Scheduled Tasks\n\n```bash\n\u002Fcron add 0 6 * * * Summarize GitHub trending\n```\n\n### 📎 Agent Attachment Send-Back\n\nWhen an agent generates a local screenshot, chart, PDF, bundle, or other file, it can send that attachment back to the current chat.\n\nFirst release supports:\n- Feishu\n- Telegram\n\nIf your agent does not natively inject the system prompt, run this once in chat after upgrading:\n\n```text\n\u002Fbind setup\n```\n\nor:\n\n```text\n\u002Fcron setup\n```\n\nThis refreshes the cc-connect instructions in the project memory file so the agent knows how to send attachments back.\n\nYou can control this feature globally in `config.toml`:\n\n```toml\nattachment_send = \"on\"  # default: \"on\"; set to \"off\" to block image\u002Ffile send-back\n```\n\nThis switch is independent from the agent's `\u002Fmode`. It only controls `cc-connect send --image\u002F--file`.\n\nExamples:\n\n```bash\ncc-connect send --image \u002Fabsolute\u002Fpath\u002Fto\u002Fchart.png\ncc-connect send --file \u002Fabsolute\u002Fpath\u002Fto\u002Freport.pdf\ncc-connect send --file \u002Fabsolute\u002Fpath\u002Fto\u002Freport.pdf --image \u002Fabsolute\u002Fpath\u002Fto\u002Fchart.png\n```\n\nNotes:\n- Absolute paths are the safest option.\n- `--image` and `--file` can both be repeated.\n- `attachment_send = \"off\"` disables only attachment send-back; ordinary text replies still work.\n- This command is for generated attachments, not ordinary text replies.\n\n📖 **Full documentation:** [docs\u002Fusage.md](docs\u002Fusage.md)\n\n\n## 📚 Documentation\n\n- [Usage Guide](docs\u002Fusage.md) — Complete feature documentation\n- [INSTALL.md](INSTALL.md) — AI-agent-friendly installation guide\n- [config.example.toml](config.example.toml) — Configuration template\n- [CONTRIBUTING.md](CONTRIBUTING.md) — How to report issues and contribute pull requests\n\n\n## 👥 Community\n\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FkHpwgaM4kq)\n- [Telegram](https:\u002F\u002Ft.me\u002F+odGNDhCjbjdmMmZl)\n\n\n## ☕ Support the Project\n\nIf cc-connect has been helpful to you, consider buying us a coffee! Your support helps us:\n\n- 🛠️ Maintain and improve the project\n- 📚 Write better documentation and tutorials\n- 🐛 Fix bugs and add new features faster\n- ☕ Keep the developers caffeinated\n\n### How to Donate\n\n**Buy Me a Coffee**: [https:\u002F\u002Fbuymeacoffee.com\u002Fcg33](https:\u002F\u002Fbuymeacoffee.com\u002Fcg33)\n\n**WeChat Pay \u002F Alipay**:\n\n| WeChat Pay | Alipay |\n|:----------:|:------:|\n| \u003Cimg src=\"docs\u002Fimages\u002Fwechatpay.jpg\" alt=\"WeChat Pay\" width=\"150\"> | \u003Cimg src=\"docs\u002Fimages\u002Falipay.jpg\" alt=\"Alipay\" width=\"150\"> |\n\n### Thank You, Donors! 🎉\n\nWe're grateful to everyone who has supported this project. Leave your GitHub username in the donation message if you'd like to be recognized here!\n\n\u003C!-- Donors will be listed below -->\n| Avatar | GitHub Username | Date |\n|--------|-----------------|------|\n| \u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1762560?v=4\" width=\"40\" height=\"40\" style=\"border-radius: 50%;\"> | [@thx0701](https:\u002F\u002Fgithub.com\u002Fthx0701) | 2026-04-29 |\n\n\n## 🤝 Commercial Cooperation\n\nWe accept the following commercial collaborations:\n\n- **Enterprise Customization**: Custom deployment for internal AI tooling (Feishu, DingTalk, WeChat Work, Slack, etc.)\n- **Technical Consulting**: AI agent integration and architecture design\n- **Outsourcing Projects**: AI-related system development\n\n**Contact**: **Email**: chg80333@gmail.com | **WeChat**: mongorz | [Telegram](https:\u002F\u002Ft.me\u002F+odGNDhCjbjdmMmZl) | [Discord](https:\u002F\u002Fdiscord.gg\u002FkHpwgaM4kq)\n\n\n## 🙏 Contributors\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fchenhg5\u002Fcc-connect\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=chenhg5\u002Fcc-connect&v=20250313\" \u002F>\n\u003C\u002Fa>\n\n\n## ⭐ Star History\n\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F#chenhg5\u002Fcc-connect&Date\">\n \u003Cpicture>\n   \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=chenhg5\u002Fcc-connect&type=Date&theme=dark\" \u002F>\n   \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=chenhg5\u002Fcc-connect&type=Date\" \u002F>\n   \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=chenhg5\u002Fcc-connect&type=Date\" \u002F>\n \u003C\u002Fpicture>\n\u003C\u002Fa>\n\n\n## 📄 License\n\nMIT License\n\n\n\u003Cp align=\"center\">\n  \u003Csub>Built with ❤️ by the cc-connect community\u003C\u002Fsub>\n\u003C\u002Fp>\n","cc-connect 是一个将本地AI编码助手（如Claude Code、Cursor、Gemini CLI、Codex）与多种消息平台（飞书\u002F蓝信、钉钉、Slack、Telegram、Discord、LINE、企业微信）连接起来的桥梁，让用户无需公网IP即可在任何地方通过聊天方式与AI开发助手交互。该项目使用Go语言编写，支持多平台部署和集成，具有良好的可扩展性和稳定性。适用于需要频繁进行代码编写、调试或学习的开发者，特别是在远程工作或团队协作场景下，能够显著提高工作效率和沟通便捷性。",2,"2026-06-11 03:31:24","trending"]