Cc Connect Ai Bridge

作者 reason-machines2384a003145a無授權條款83 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫3 個月前更新

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu, Telegram, Slack, Discord, DingTalk, WeChat Work, LINE) without a public IP.

僅含說明DevOps & CloudAI & Agents
AI 產生的概覽

將本機 AI 程式開發代理橋接到 Telegram、Slack、飛書等訊息平台，讓你遠端與其對話。

功能
此技能說明如何安裝、設定與執行 cc-connect，這是一套把本機執行的 AI 程式開發代理（Claude Code、Codex、Cursor、Gemini CLI 等）連接到 Telegram、飛書、Slack、Discord、釘釘、企業微信、LINE、QQ 等訊息平台的工具。內容涵蓋設定檔範例、平台與代理類型對照表、聊天指令、排程工作、語音與多模態設定，以及疑難排解指引。產出為設定與使用說明，而非程式碼或指令碼。
適用情境
當你想透過訊息應用程式控制或與本機 AI 程式開發代理對話、建立團隊共用機器人，或在聊天中安排週期性代理工作時使用。為特定平台設定 cc-connect，或排查機器人沒有回應的問題時也適用。
執行需求
需要 cc-connect 工具（可透過 npm、預先編譯的執行檔安裝，或以 Go 1.22+ 從原始碼建置）、本機已安裝支援的 AI 程式開發代理，以及機器人權杖或應用程式 ID 與密鑰等平台憑證。部分平台與語音功能還需要額外的 API 金鑰和網路存取。此技能本身不含指令碼，僅為說明文件。

CC-Connect AI Bridge

Skill by ara.so — Daily 2026 Skills collection.

CC-Connect bridges locally running AI coding agents (Claude Code, Codex, Cursor Agent, Gemini CLI, Qoder CLI, OpenCode, iFlow CLI) to messaging platforms you already use. You can chat with your local agent from Telegram, Feishu, Slack, Discord, DingTalk, WeChat Work, LINE, or QQ — no public IP required for most platforms.

Installation

Via npm (recommended)

bash
# Stablenpm install -g cc-connect
# Beta (includes personal WeChat / Weixin ilink and other beta features)npm install -g cc-connect@beta

Via binary

bash
# Linux amd64curl -L -o cc-connect https://github.com/chenhg5/cc-connect/releases/latest/download/cc-connect-linux-amd64chmod +x cc-connectsudo mv cc-connect /usr/local/bin/
# macOS arm64curl -L -o cc-connect https://github.com/chenhg5/cc-connect/releases/latest/download/cc-connect-darwin-arm64chmod +x cc-connectsudo mv cc-connect /usr/local/bin/

Build from source (Go 1.22+)

bash
git clone https://github.com/chenhg5/cc-connect.gitcd cc-connectmake build# binary appears at ./bin/cc-connect

Self-update

bash
cc-connect update          # stablecc-connect update --pre    # beta / pre-release

Quick AI-assisted Setup

Send this prompt to Claude Code or any AI coding agent — it will install and configure cc-connect automatically:

Follow https://raw.githubusercontent.com/chenhg5/cc-connect/refs/heads/main/INSTALL.md to install and configure cc-connect.

Configuration

bash
mkdir -p ~/.cc-connectcp config.example.toml ~/.cc-connect/config.toml

Minimal config.toml — Claude Code + Telegram

toml
[project.my-project]name        = "my-project"work_dir    = "/home/user/myproject"data_dir    = "/home/user/.cc-connect/data"admin_from  = "123456789"          # Your Telegram user ID
[project.my-project.agent]type = "claude-code"               # claude-code | codex | cursor | gemini | qoder | opencode | iflow
[project.my-project.platform]type  = "telegram"token = "$TELEGRAM_BOT_TOKEN"      # set via env or paste value

Multi-project config

toml
# Project 1: Claude on Telegram[project.dev]name     = "dev"work_dir = "/home/user/project-a"data_dir = "/home/user/.cc-connect/data/dev"
[project.dev.agent]type = "claude-code"
[project.dev.platform]type  = "telegram"token = "$TELEGRAM_BOT_TOKEN"
# Project 2: Gemini on Feishu[project.research]name     = "research"work_dir = "/home/user/project-b"data_dir = "/home/user/.cc-connect/data/research"
[project.research.agent]type = "gemini"
[project.research.platform]type           = "feishu"app_id         = "$FEISHU_APP_ID"app_secret     = "$FEISHU_APP_SECRET"verification_token = "$FEISHU_VERIFICATION_TOKEN"

All supported platform types

type valuePlatformPublic IP needed?
telegramTelegramNo (long polling)
feishuFeishu / LarkNo (WebSocket)
dingtalkDingTalkNo (Stream)
slackSlackNo (Socket Mode)
discordDiscordNo (Gateway)
wecomWeChat WorkNo (WS) / Yes (Webhook)
lineLINEYes (Webhook)
qqQQ via NapCat/OneBotNo
qqbotQQ Bot OfficialNo
weixinPersonal WeChat (beta)No (ilink long polling)

All supported agent types

type valueAgent
claude-codeClaude Code (Anthropic)
codexCodex (OpenAI)
cursorCursor Agent
geminiGemini CLI (Google)
qoderQoder CLI
opencodeOpenCode / Crush
iflowiFlow CLI

Platform-specific configuration

Telegram

toml
[project.mybot.platform]type  = "telegram"token = "$TELEGRAM_BOT_TOKEN"# Get token from @BotFather on Telegram# No public IP required — uses long polling

Feishu / Lark

toml
[project.mybot.platform]type               = "feishu"app_id             = "$FEISHU_APP_ID"app_secret         = "$FEISHU_APP_SECRET"verification_token = "$FEISHU_VERIFICATION_TOKEN"# Uses WebSocket — no public IP needed# Set up at https://open.feishu.cn/

Slack

toml
[project.mybot.platform]type              = "slack"bot_token         = "$SLACK_BOT_TOKEN"app_token         = "$SLACK_APP_TOKEN"# app_token must start with xapp- (Socket Mode)# Enable Socket Mode in your Slack app settings

Discord

toml
[project.mybot.platform]type  = "discord"token = "$DISCORD_BOT_TOKEN"# Uses Discord Gateway — no public IP needed

DingTalk

toml
[project.mybot.platform]type       = "dingtalk"client_id  = "$DINGTALK_CLIENT_ID"client_secret = "$DINGTALK_CLIENT_SECRET"# Uses DingTalk Stream — no public IP needed

WeChat Work (WeCom)

toml
[project.mybot.platform]type           = "wecom"corp_id        = "$WECOM_CORP_ID"agent_id       = "$WECOM_AGENT_ID"secret         = "$WECOM_SECRET"connection_type = "websocket"   # websocket (no public IP) or webhook

Personal WeChat (beta only)

bash
# Install beta build firstnpm install -g cc-connect@beta
# Scan QR code to log incc-connect weixin setup
toml
[project.mybot.platform]type = "weixin"# Auth state is stored after QR scan — no public IP needed

Running cc-connect

bash
# Default config location: ~/.cc-connect/config.tomlcc-connect
# Custom config pathcc-connect --config /path/to/config.toml
# Run specific project onlycc-connect --project my-project

Chat Commands (sent in the messaging platform)

CommandDescription
/helpShow all available commands
/model <name>Switch AI model (e.g. /model claude-opus-4-5)
/mode <mode>Change permission mode (e.g. /mode auto)
/reasoning <level>Tune reasoning intensity
/dir <path>Switch working directory for next session
/dir <number>Jump to a directory from history
/dir -Toggle to previous directory
/dir resetRestore configured work_dir
/cd <path>Alias for /dir
/memoryRead or write the agent's memory/instruction file
/shell <cmd>Run a shell command (admin only)
/sessionManage sessions (list, continue, new)
/continueContinue from last session (forks to avoid inheriting broken state)
/cron <spec> <task>Schedule a recurring task
/stopStop the currently running agent

Slash command examples (in chat)

# Ask the agent to review a PRReview the changes in branch feature/auth and summarize the risks.
# Switch to a different model/model gemini-2.0-flash
# Change working directory/dir /home/user/other-project
# Schedule a daily summary/cron 0 6 * * * Summarize GitHub trending Go repos and post here
# Read agent memory/memory
# Update agent memory/memory Always prefer table-driven tests in Go. Use context.Context for cancellation.

Multi-Agent Relay (group chat orchestration)

Bind multiple bots in one group chat so they communicate with each other:

toml
# Bot 1: Claude[project.claude-bot]name     = "claude-bot"work_dir = "/home/user/project"data_dir = "/home/user/.cc-connect/data/claude"
[project.claude-bot.agent]type = "claude-code"
[project.claude-bot.platform]type  = "telegram"token = "$TELEGRAM_CLAUDE_BOT_TOKEN"
# Bot 2: Gemini (same group)[project.gemini-bot]name     = "gemini-bot"work_dir = "/home/user/project"data_dir = "/home/user/.cc-connect/data/gemini"
[project.gemini-bot.agent]type = "gemini"
[project.gemini-bot.platform]type  = "telegram"token = "$TELEGRAM_GEMINI_BOT_TOKEN"

Add both bots to the same Telegram group. Mention them by name and they will pick up and respond to each other's output.

Voice and Multimodal

For platforms that support voice (Telegram, Feishu, DingTalk), enable speech in config:

toml
[speech]provider = "openai"           # openai | azure | googleapi_key  = "$OPENAI_API_KEY"
[speech.stt]model = "whisper-1"
[speech.tts]model = "tts-1"voice = "alloy"

Send a voice message in Telegram → cc-connect transcribes it → forwards text to the agent → optionally speaks the response back.

For images/screenshots: just attach the image in chat. cc-connect forwards it to multimodal-capable agents.

Cron Scheduling

toml
# In config.toml, per-project cron settings[project.mybot.cron]timeout = "30m"          # max runtime per jobfresh_session = true     # start a new session for each run

From chat:

# Every weekday at 9am, run a standup summary/cron 0 9 * * 1-5 Summarize open PRs and blockers in this repo
# Every hour, check for new issues labeled "urgent"/cron 0 * * * * Check for new GitHub issues labeled urgent and notify me

Admin configuration

toml
[project.mybot]admin_from = "alice,123456789"   # comma-separated usernames or IDs

Admins can use /shell, /dir, and other privileged commands. Non-admins cannot.

Directory structure

~/.cc-connect/├── config.toml                          # main config└── data/    └── projects/        └── my-project.state.json        # persisted dir override, session state

Common patterns

Pattern 1: Mobile-first AI development

Install cc-connect on your dev machine, connect it to Telegram. From your phone:

  1. Send a task description as a message
  2. Agent runs on your machine
  3. Streamed response appears in chat
  4. Reply to continue the conversation

Pattern 2: Team shared AI bot (Slack/Feishu)

One cc-connect instance per project, shared in a team channel. Team members can ask questions, trigger code reviews, or run analyses — all without terminal access.

Pattern 3: Scheduled reports

/cron 0 8 * * 1 Generate a weekly summary of commits and open issues, format as markdown

Pattern 4: Multi-project routing

Run multiple projects in one cc-connect process, each bot handles a different repo or concern.

Troubleshooting

Bot not responding

  1. Check that cc-connect is running: ps aux | grep cc-connect
  2. Verify the platform token/credentials in config
  3. For Telegram: ensure the bot token is valid (/start in BotFather chat)
  4. For Feishu: check WebSocket connection in Feishu Open Platform console

Agent not found

bash
# Verify agent is installed and in PATHwhich claude     # for claude-codewhich gemini     # for geminiwhich codex      # for codex

Set explicit path in config if needed:

toml
[project.mybot.agent]type = "claude-code"bin  = "/usr/local/bin/claude"

Session inherits broken state

Use /continue which forks the session, or start fresh:

/session new

Personal WeChat not available

You need the beta build:

bash
npm install -g cc-connect@betacc-connect weixin setup   # scan QR in terminal

Context too long / auto-compress

Enable in config:

toml
[project.mybot.agent]auto_compress        = truecompress_threshold   = 80000   # tokens before compression kicks in

Config not found

Default path is ~/.cc-connect/config.toml. Pass explicitly:

bash
cc-connect --config /custom/path/config.toml

Check version

bash
cc-connect --version

Environment variables reference

VariableUsed for
TELEGRAM_BOT_TOKENTelegram bot token
FEISHU_APP_IDFeishu app ID
FEISHU_APP_SECRETFeishu app secret
FEISHU_VERIFICATION_TOKENFeishu verification token
SLACK_BOT_TOKENSlack bot OAuth token (xoxb-...)
SLACK_APP_TOKENSlack app-level token (xapp-...)
DISCORD_BOT_TOKENDiscord bot token
DINGTALK_CLIENT_IDDingTalk app client ID
DINGTALK_CLIENT_SECRETDingTalk app client secret
WECOM_CORP_IDWeChat Work corp ID
WECOM_AGENT_IDWeChat Work agent ID
WECOM_SECRETWeChat Work app secret
OPENAI_API_KEYOpenAI API key (for Codex agent or STT/TTS)

Values in config.toml can reference env vars using $VAR_NAME syntax.

Platform setup guides

  • Feishu/Lark: docs/feishu.md
  • DingTalk: docs/dingtalk.md
  • Telegram: docs/telegram.md
  • Slack: docs/slack.md
  • Discord: docs/discord.md
  • WeChat Work: docs/wecom.md
  • Personal WeChat (beta): docs/weixin.md
  • QQ / QQ Bot: docs/qq.md

來源與署名

來源：reason-machines/trending-skills位於skills/cc-connect-ai-bridge提交2384a00

授權條款： 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架

更多來自 reason-machines/trending-skills 的技能

Yourvpndead Vpn Detection

reason-machines

介紹一款 Android 應用程式，用來偵測 VPN 用戶端並探測本機 SOCKS5 與 Clash API 連接埠是否外洩。

Security833 個月前更新

X Mentor Skill Nuwa

reason-machines

提供 X（Twitter）內容策略指引：推文與長推撰寫、鉤子評論、成長策略與帳號診斷。

Marketing & Sales833 個月前更新

Wildworld Dataset

reason-machines

介紹 WildWorld 動作條件 ARPG 世界建模資料集，並提供預期的載入、篩選與基準評測程式碼。

Data & Analytics833 個月前更新

Understand Anything Knowledge Graph

reason-machines

為程式碼庫建立可互動的知識圖譜，並支援視覺化探索、搜尋與提問。

Software Development833 個月前更新

Webphysics Avbd Engine

reason-machines

指導將實驗性 WebGPU AVBD 剛體與軟體物理引擎整合到瀏覽器專案中。

Software Development833 個月前更新

Ui Ux Pro Max Skill

reason-machines

依產品描述產生 UI/UX 設計系統，包含頁面結構、風格、配色、字體搭配與檢查清單。

Design & Creative833 個月前更新

更多DevOps & Cloud技能

Playwright Devops

microsoft

精選

Playwright 的 DevOps 工作流程：分析 main 分支最新提交的 GitHub Actions 失敗並下載失敗作業日誌。

包含腳本
DevOps & Cloud97K今天更新

M5 Onboard

anthropics

精選

透過 USB 偵測 M5Stack ESP32 開發板，燒錄 UIFlow 2.0 韌體並安裝 MicroPython 應用程式套件。

DevOps & Cloud37K今天更新

Yeet

openai

精選

使用 GitHub CLI 一次完成暫存、提交、推送並建立或更新 GitHub 拉取請求。

DevOps & Cloud27K4 週前更新

Runbook

anthropics

精選

為重複性任務建立或更新逐步操作手冊，包含疑難排解、回復與升級流程。

DevOps & Cloud27K今天更新

Incident Response

anthropics

精選

引導事故回應流程：嚴重程度分級、狀態更新、緩解追蹤，以及無責事後檢討。

DevOps & Cloud27K今天更新

Deploy Checklist

anthropics

精選

產生部署前就緒檢查清單，涵蓋部署前、部署、部署後與回復觸發條件。

DevOps & Cloud27K今天更新