
cc-connect-ai-bridge
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.
- Installs
- 936
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/trending-skills --skill cc-connect-ai-bridge- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads cc-connect-ai-bridge automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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)
# Stable
npm install -g cc-connect
# Beta (includes personal WeChat / Weixin ilink and other beta features)
npm install -g cc-connect@beta
Via binary
# Linux amd64
curl -L -o cc-connect https://github.com/chenhg5/cc-connect/releases/latest/download/cc-connect-linux-amd64
chmod +x cc-connect
sudo mv cc-connect /usr/local/bin/
# macOS arm64
curl -L -o cc-connect https://github.com/chenhg5/cc-connect/releases/latest/download/cc-connect-darwin-arm64
chmod +x cc-connect
sudo mv cc-connect /usr/local/bin/
Build from source (Go 1.22+)
git clone https://github.com/chenhg5/cc-connect.git
cd cc-connect
make build
# binary appears at ./bin/cc-connect
Self-update
cc-connect update # stable
cc-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
mkdir -p ~/.cc-connect
cp config.example.toml ~/.cc-connect/config.toml
Minimal config.toml — Claude Code + Telegram
[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 = "$TELEGRAM_BOT_TOKEN" # set via env or paste value
Multi-project config
# Project 1: Claude on Telegram
[project.dev]
name = "dev"
work_dir = "/home/user/project-a"
data_dir = "/home/user/.cc-connect/data/dev"
[project.dev.agent]
type = "claude-code"
[project.dev.platform]
type = "telegram"
token = "$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 = "$FEISHU_VERIFICATION_TOKEN"
All supported platform types
type value | Platform | Public IP needed? |
|---|---|---|
telegram | Telegram | No (long polling) |
feishu | Feishu / Lark | No (WebSocket) |
dingtalk | DingTalk | No (Stream) |
slack | Slack | No (Socket Mode) |
discord | Discord | No (Gateway) |
wecom | WeChat Work | No (WS) / Yes (Webhook) |
line | LINE | Yes (Webhook) |
qq | QQ via NapCat/OneBot | No |
qqbot | QQ Bot Official | No |
weixin | Personal WeChat (beta) | No (ilink long polling) |
All supported agent types
type value | Agent |
|---|---|
claude-code | Claude Code (Anthropic) |
codex | Codex (OpenAI) |
cursor | Cursor Agent |
gemini | Gemini CLI (Google) |
qoder | Qoder CLI |
opencode | OpenCode / Crush |
iflow | iFlow CLI |
Platform-specific configuration
Telegram
[project.mybot.platform]
type = "telegram"
token = "$TELEGRAM_BOT_TOKEN"
# Get token from @BotFather on Telegram
# No public IP required — uses long polling
Feishu / Lark
[project.mybot.platform]
type = "feishu"
app_id = "$FEISHU_APP_ID"
app_secret = "$FEISHU_APP_SECRET"
verification_token = "$FEISHU_VERIFICATION_TOKEN"
# Uses WebSocket — no public IP needed
# Set up at https://open.feishu.cn/
Slack
[project.mybot.platform]
type = "slack"
bot_token = "$SLACK_BOT_TOKEN"
app_token = "$SLACK_APP_TOKEN"
# app_token must start with xapp- (Socket Mode)
# Enable Socket Mode in your Slack app settings
Discord
[project.mybot.platform]
type = "discord"
token = "$DISCORD_BOT_TOKEN"
# Uses Discord Gateway — no public IP needed
DingTalk
[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)
[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)
# Install beta build first
npm install -g cc-connect@beta
# Scan QR code to log in
cc-connect weixin setup
[project.mybot.platform]
type = "weixin"
# Auth state is stored after QR scan — no public IP needed
Running cc-connect
# Default config location: ~/.cc-connect/config.toml
cc-connect
# Custom config path
cc-connect --config /path/to/config.toml
# Run specific project only
cc-connect --project my-project
Chat Commands (sent in the messaging platform)
| Command | Description |
|---|---|
/help | Show 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 reset | Restore configured work_dir |
/cd <path> | Alias for /dir |
/memory | Read or write the agent's memory/instruction file |
/shell <cmd> | Run a shell command (admin only) |
/session | Manage sessions (list, continue, new) |
/continue | Continue from last session (forks to avoid inheriting broken state) |
/cron <spec> <task> | Schedule a recurring task |
/stop | Stop the currently running agent |
Slash command examples (in chat)
# Ask the agent to review a PR
Review 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:
# 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 = "$TELEGRAM_GEMINI_BOT_TOKEN"
Add both bots to the same Telegram group. Mention them by name and they will pick up and respond to each other's output.
Voice and Multimodal
For platforms that support voice (Telegram, Feishu, DingTalk), enable speech in config:
[speech]
provider = "openai" # openai | azure | google
api_key = "$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
# In config.toml, per-project cron settings
[project.mybot.cron]
timeout = "30m" # max runtime per job
fresh_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
[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:
- Send a task description as a message
- Agent runs on your machine
- Streamed response appears in chat
- 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
- Check that
cc-connectis running:ps aux | grep cc-connect - Verify the platform token/credentials in config
- For Telegram: ensure the bot token is valid (
/startin BotFather chat) - For Feishu: check WebSocket connection in Feishu Open Platform console
Agent not found
# Verify agent is installed and in PATH
which claude # for claude-code
which gemini # for gemini
which codex # for codex
Set explicit path in config if needed:
[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:
npm install -g cc-connect@beta
cc-connect weixin setup # scan QR in terminal
Context too long / auto-compress
Enable in config:
[project.mybot.agent]
auto_compress = true
compress_threshold = 80000 # tokens before compression kicks in
Config not found
Default path is ~/.cc-connect/config.toml. Pass explicitly:
cc-connect --config /custom/path/config.toml
Check version
cc-connect --version
Environment variables reference
| Variable | Used for |
|---|---|
TELEGRAM_BOT_TOKEN | Telegram bot token |
FEISHU_APP_ID | Feishu app ID |
FEISHU_APP_SECRET | Feishu app secret |
FEISHU_VERIFICATION_TOKEN | Feishu verification token |
SLACK_BOT_TOKEN | Slack bot OAuth token (xoxb-...) |
SLACK_APP_TOKEN | Slack app-level token (xapp-...) |
DISCORD_BOT_TOKEN | Discord bot token |
DINGTALK_CLIENT_ID | DingTalk app client ID |
DINGTALK_CLIENT_SECRET | DingTalk app client secret |
WECOM_CORP_ID | WeChat Work corp ID |
WECOM_AGENT_ID | WeChat Work agent ID |
WECOM_SECRET | WeChat Work app secret |
OPENAI_API_KEY | OpenAI 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
FAQ
What does the cc-connect-ai-bridge skill do?
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.
How do I install cc-connect-ai-bridge?
Run npx skills add https://github.com/reason-machines/trending-skills --skill cc-connect-ai-bridge in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/cc-connect-ai-bridge/ (personal) or .claude/skills/cc-connect-ai-bridge/ (project).
Which AI agents can use cc-connect-ai-bridge?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is cc-connect-ai-bridge safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains cc-connect-ai-bridge?
It is published by reason-machines in reason-machines/trending-skills. It has 936 recorded installs.
More from reason-machines/trending-skills
openclaw-control-center
reason-machines/trending-skills
Local-first, security-first control center for OpenClaw agents — visibility dashboard with readonly defaults, token attribution, collaboration tracing, and safe write operations.
inkos-multi-agent-novel-writing
reason-machines/trending-skills
Multi-agent CLI system for autonomous novel writing, auditing, and revision with human review gates
claude-hud-statusline
reason-machines/trending-skills
A Claude Code plugin that displays a real-time HUD showing context usage, active tools, running agents, and todo progress in your terminal statusline.
understand-anything-knowledge-graph
reason-machines/trending-skills
Turn any codebase into an interactive knowledge graph using Claude Code skills — explore, search, and ask questions about any project visually.
agency-agents-ai-specialists
reason-machines/trending-skills
A collection of specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, and other AI coding tools — covering engineering, design, marketing, sales, and more.
agent-browser-automation
reason-machines/trending-skills
Headless browser automation CLI for AI agents using native Rust binary with Chrome DevTools Protocol
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。