Cc Connect Ai Bridge
Chat with a locally running Claude Code, Cursor, Codex, or Gemini CLI session from Telegram, Slack, Feishu, or similar without exposing a public IP.
Overview
CC-Connect AI Bridge is an agent skill most often used in Build (also Operate) that connects local AI coding agents to messaging platforms so you can drive sessions from chat without a public IP.
Install
npx skills add https://github.com/aradotso/trending-skills --skill cc-connect-ai-bridgeWhat is this skill?
- Bridges Claude Code, Codex, Cursor Agent, Gemini CLI, Qoder, OpenCode, and iFlow CLI to chat apps
- Supports Feishu, Telegram, Slack, Discord, DingTalk, WeChat Work, LINE, and QQ
- Documents npm global install and Linux/macOS binary release paths including beta WeChat features
- Enables phone-side control and scheduled agent tasks from messaging threads
- Designed so most platforms work without requiring your own public IP
- Documents stable and @beta npm install paths
- Lists 8+ messaging platforms and 7+ supported local agent CLIs
Adoption & trust: 807 installs on skills.sh; 31 GitHub stars; 0/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your coding agent only lives in a local terminal, so you cannot steer or monitor runs from your phone or team chat when you step away.
Who is it for?
Indie devs who already run Claude Code or similar locally and want Telegram/Slack as a remote control plane.
Skip if: Builders who need a hosted multi-tenant SaaS chat product with no local agent footprint.
When should I use this skill?
User wants to connect Claude Code to Telegram, bridge an AI agent to Feishu/Slack/Discord, chat with Claude from phone, configure cc-connect, or schedule agent tasks from chat.
What do I get? / Deliverables
You get a documented cc-connect install and platform wiring path so messages on Telegram, Slack, Feishu, or peers reach your local agent session.
- Installed cc-connect CLI
- Platform-specific bridge configuration outline
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Wiring agents to external messaging is core integration work done while you assemble your agent toolchain. Integrations subphase is where third-party channels attach to local coding agents as control and notification surfaces.
Where it fits
Wire Claude Code to Slack so cofounder questions hit your local session during build week.
Restart or nudge a long Codex job from Telegram while away from your desk.
Get launch-checklist agent output piped into a team Feishu channel without deploying a cloud relay.
How it compares
Local-agent-to-chat bridge skill, not an MCP server catalog entry for a single API.
Common Questions / FAQ
Who is cc-connect-ai-bridge for?
Solo builders and small teams running local AI coding CLIs who want Feishu, Telegram, Slack, Discord, or regional chat apps as the UI.
When should I use cc-connect-ai-bridge?
In Build integrations when connecting agents to messaging; in Operate iterate when you need on-call style agent control from phone chat or scheduled tasks from a channel.
Is cc-connect-ai-bridge safe to install?
Following the skill installs third-party cc-connect binaries or npm packages with network access—review the Security Audits panel on this Prism page and audit github.com/chenhg5/cc-connect before production use.
SKILL.md
READMESKILL.md - Cc Connect Ai Bridge
# CC-Connect AI Bridge > Skill by [ara.so](https://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 # Stable npm install -g cc-connect # Beta (includes personal WeChat / Weixin ilink and other beta features) npm install -g cc-connect@beta ``` ### Via binary ```bash # 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+) ```bash git clone https://github.com/chenhg5/cc-connect.git cd cc-connect make build # binary appears at ./bin/cc-connect ``` ### Self-update ```bash 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 ```bash mkdir -p ~/.cc-connect cp 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` 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 (Ant