English  |  中文文档  |  Full Reference

TaroCub

Run Codex, Claude Code, and Antigravity locally. Control them from Telegram and Feishu/Lark.
TaroCub runs real CLI agents on your own machine, then gives them durable chat surfaces, files, sessions, tasks, cron, audit logs, and multi-agent workflows.
Resume local sessions anytime from your phone, whether you are at your desk, commuting, or walking the dog.

Quick Start  |   Surfaces  |   Core Highlights  |   Lark Setup  |   Commands  |   Docs

What This Is

TaroCub is a local bridge, not a hosted agent product. It runs the real Codex, Claude Code, and Antigravity CLIs on your own computer, then gives them a durable messaging control surface across Telegram and Feishu/Lark.

This project was formerly named cc-telegram-bridge; the old repository URL, state directories, and cctb shorthand remain useful for compatibility while the public name moves to TaroCub.

It is built for people who already use CLI agents heavily and want:

• phone-first operation through Telegram;
• Feishu/Lark-native operation with cards, Docs comments, Sheets, and group workflows;
• durable state for sessions, cron jobs, file delivery, usage, timelines, audit logs, and multi-agent routing.

The intended setup flow is agent-assisted: clone the repo, open it in Codex, Claude Code, or Antigravity, and ask the agent to configure the bridge for you. The CLI exists so your local agent can do the boring setup work instead of making you hand-edit every file.

The old long README is preserved as Full Reference. This landing page is intentionally short.

Quick Start

Recommended: ask your local agent to configure it

Open this repository in Codex, Claude Code, or Antigravity and say:

Read the README and configure TaroCub for me.
Use this Telegram bot token: <paste token>
Enable YOLO mode for my personal bot instance.

For Lark, say:

Read the README and configure the Feishu/Lark bot for me.
Run the Lark wizard, check permissions, install/bind lark-cli, and tell me what I need to scan or approve.

That is the preferred path. Manual commands are still below for operators who want to see each step.

Telegram

Create a Telegram bot with @BotFather, then run:

git clone https://github.com/cloveric/tarocub.git
cd tarocub
npm install
npm run build

npm run dev -- telegram configure <telegram-bot-token>
npm run dev -- telegram yolo on
npm run dev -- telegram service start

telegram yolo on is the recommended default for a personal, trusted bot instance. It lets Codex, Claude Code, and Antigravity keep moving without asking for approval on every turn. Use telegram yolo unsafe only for fully trusted local workspaces, and use telegram yolo off when you explicitly want approval prompts.

Send any message to the bot. It will reply with a pairing code:

npm run dev -- telegram access pair <pairing-code>

You can now talk to your local CLI agent from Telegram.

Feishu / Lark

For the full Lark-native setup, let the aggregate setup command install/bind lark-cli >= 1.0.41, run the QR wizard, provision permissions, and check the app:

npm install
npm run build

node dist/src/index.js lark setup --install-cli --identity bot-only
node dist/src/index.js lark service start

If lark doctor reports missing app scopes, copy the JSON it prints into the Feishu/Lark app permission page, publish the app version, then run:

node dist/src/index.js lark provision
node dist/src/index.js lark doctor

Surfaces

Core Highlights

Feature Map

Lark Setup

Lark has two levels:

Recommended production flow:

node dist/src/index.js lark setup --install-cli --identity bot-only
node dist/src/index.js lark auth start --recommend --domain docs,drive --scope "sheets:spreadsheet:create sheets:spreadsheet:write_only sheets:spreadsheet:read sheets:spreadsheet.meta:read"
node dist/src/index.js lark auth finish <device-code>
node dist/src/index.js lark service restart

lark setup wraps the QR wizard, lark-cli preflight/bind, app provisioning, OAuth status check, and lark doctor. If you already created the app and only want to re-check the local side, use node dist/src/index.js lark setup --skip-wizard --install-cli --identity bot-only.

Useful Lark commands:

node dist/src/index.js lark setup --install-cli
node dist/src/index.js lark status
node dist/src/index.js lark permissions --missing
node dist/src/index.js lark access pair <code>
node dist/src/index.js lark send --chat oc_xxx --message "hello"
node dist/src/index.js lark timeline 20
node dist/src/index.js lark dashboard

Inside Lark, the bot supports the same core slash surface as Telegram: /status, /usage, /engine, /model, /effort, /fast, /yolo, /goal, /resume, /detach, /stop, /reset, /cron, /board, /mini, /fan, /chain, /verify, /group, /newgroup, /newtopic, and /continue.

Operator Commands

Telegram

telegram service start --instance work
telegram service restart --all
telegram service status --all
telegram engine codex --instance work
telegram yolo on --instance work
telegram usage --instance work
telegram timeline --instance work
telegram dashboard --instance work
telegram backup --instance work --out ./work.cctb.gz

Lark

lark service start
lark service restart
lark doctor
lark access status
lark cli identity status
lark auth status --verify
lark send --chat oc_xxx --message "hello"

In-chat slash commands

# basics
/help
/status
/usage
/btw can you sanity-check this without changing the session?

# engine and safety
/engine codex
/model gpt-5.5
/effort xhigh
/fast off
/yolo on
/config

# goals and sessions
/goal ship this with tests
/goal status
/resume
/resume thread thread_abc123
/resume conversation fdfc8ab1-7936-4599-98b0-d8ba2593c250
/detach
/reset
/stop
/continue

# scheduled and durable work
/cron list
/cron add 0 9 * * 1 weekly summary
/board add write launch plan
/board list

# multi-agent workflows
/mini here planner
/mini ask planner break this into tickets
/fan compare these approaches
/chain improve this answer step by step
/verify implement and review this

# groups and Lark-native project spaces
/group status
/group all
/newgroup Project Room
/newtopic Research Thread

# approvals when cards are unavailable
/approve
/deny

Current Release

• v0.1.0 — resets the public product to TaroCub, renames the GitHub/package surface, adds the product thesis to the banner, and keeps cctb plus old state paths as compatibility surfaces.
• v4.6.70 — transitional release that introduced the TaroCub family name before the full product reset.
• v4.6.69 — makes Lark setup more self-healing: when user OAuth is missing, setup now prints the recommended Docs/Drive/Sheets auth command, and the docs clarify that user-default no longer force-rebinds existing lark-cli sessions.
• v4.6.68 — deepens Lark-native reliability: safe running reactions, native @name resolution, card-to-text fallback, one-shot lark setup, clearer permission repair, and safer lark-cli binding that will not wipe user OAuth.
• v4.6.67 — closes a Lark runtime secret-boundary gap: runtime lark-cli child processes now get LARK_CHANNEL=1 without inheriting LARK_APP_SECRET.

See GitHub Releases for the full changelog.

Safety Model

The bridge is powerful because it controls local CLIs. Treat it like local automation, not a sandboxed SaaS bot.

• Run it only on machines and workspaces you trust.
• Use access pairing/allowlists before exposing private or group chats.
• Use YOLO/full-auto only for trusted instances.
• Keep app secrets in bridge state, not prompts, argv, or child-process env.
• Use doctor, timeline, audit, and dashboard before guessing at failures.

More detail: Security Boundaries, State Model, and Full Reference.

Docs

Development

npm install
npm run build
npm test -- --run

The project is TypeScript, Node.js >= 20, and Vitest. It stores runtime state under ~/.cctb/<instance> for Telegram instances and ~/.cctb/lark for the default Lark state dir.

License

MIT