TinyAGI 🦞

Multi-agent, Multi-team, Multi-channel, 24/7 AI assistant

Run multiple teams of AI agents that collaborate with each other simultaneously with isolated workspaces.

<img src="https://img.shields.io/badge/stability-experimental-orange.svg" alt="Experimental" />
<a href="https://opensource.org/licenses/MIT">
  <img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="MIT License" />
</a>
<a href="https://discord.gg/jH6AcEChuD">
  <img src="https://img.shields.io/discord/1353722981163208785?logo=discord&logoColor=white&label=Discord&color=7289DA" alt="Discord" />
</a>
<a href="https://github.com/TinyAGI/tinyagi/releases/latest">
  <img src="https://img.shields.io/github/v/release/TinyAGI/tinyagi?label=Latest&color=green" alt="Latest Release" />
</a>

✨ Features

• ✅ Multi-agent - Run multiple isolated AI agents with specialized roles
• ✅ Multi-team collaboration - Agents hand off work to teammates via chain execution and fan-out
• ✅ Multi-channel - Discord, WhatsApp, and Telegram
• ✅ Web portal (TinyOffice) - Browser-based dashboard for chat, agents, teams, tasks, logs, and settings
• ✅ Team chat rooms - Persistent async chat rooms per team with real-time CLI viewer
• ✅ Multiple AI providers - Anthropic Claude, OpenAI Codex, and custom providers (any OpenAI/Anthropic-compatible endpoint)
• ✅ Auth token management - Store API keys per provider, no separate CLI auth needed
• ✅ Parallel processing - Agents process messages concurrently
• ✅ Live TUI dashboard - Real-time team visualizer and chatroom viewer
• ✅ Persistent sessions - Conversation context maintained across restarts
• ✅ SQLite queue - Atomic transactions, retry logic, dead-letter management
• ✅ Plugin system - Extend TinyAGI with custom plugins for message hooks and event listeners
• ✅ 24/7 operation - Runs as a background process or Docker container

Community

Discord

We are actively looking for contributors. Please reach out.

🚀 Quick Start

Prerequisites

• macOS, Linux and Windows (WSL2)
• Node.js v18+
• Claude Code CLI (for Anthropic provider)
• Codex CLI (for OpenAI provider)

Installation & First Run

curl -fsSL https://raw.githubusercontent.com/TinyAGI/tinyagi/main/scripts/install.sh | bash

This downloads and installs the tinyagi command globally. Then just run:

tinyagi

That's it. TinyAGI auto-creates default settings, starts the daemon, and opens TinyOffice in your browser. No wizard, no configuration needed.

• Default workspace: ~/tinyagi-workspace
• Default agent: tinyagi (Anthropic/Opus)
• Channels: none initially — add later with tinyagi channel setup

Development (run from source repo)

git clone https://github.com/TinyAGI/tinyagi.git
cd tinyagi && npm install && npm run build
npx tinyagi start
npx tinyagi agent list

Other installation methods

From Source:

git clone https://github.com/TinyAGI/tinyagi.git
cd tinyagi && npm install && ./scripts/install.sh

🐳 Docker

docker compose up -d

Set your API key in a .env file or pass it directly:

ANTHROPIC_API_KEY=sk-ant-... docker compose up -d

The API runs on http://localhost:3777. Data is persisted in a tinyagi-data Docker volume.

📱 Channel Setup Guides

Discord Setup

1. Go to Discord Developer Portal
2. Create application → Bot section → Create bot
3. Copy bot token
4. Enable "Message Content Intent"
5. Invite bot using OAuth2 URL Generator

Telegram Setup

1. Open Telegram → Search @BotFather
2. Send /newbot → Follow prompts
3. Copy bot token
4. Start chat with your bot

WhatsApp Setup

After starting TinyAGI, scan the QR code:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
     WhatsApp QR Code
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[QR CODE HERE]

📱 Settings → Linked Devices → Link a Device

---

🌐 TinyOffice Web Portal

TinyAGI includes a web portal for managing your agents, teams, tasks, and chat — all from the browser.

Once you start running TinyAGI locally, you can control it by visiting office.tinyagicompany.com. It connects to your local TinyAGI API at localhost:3777 — no account or sign-up needed.

Alternatively, you can run TinyOffice locally:

tinyagi office  # Builds and starts on http://localhost:3000

TinyOffice Features & Setup

• Dashboard - Real-time queue/system overview and live event feed
• Chat Console - Send messages to default agent, @agent, or @team
• Agents & Teams - Create, edit, and remove agents/teams
• Tasks (Kanban) - Create tasks, drag across stages, assign to agent/team
• Logs & Events - Inspect queue logs and streaming events
• Settings - Edit TinyAGI configuration (settings.json) via UI
• Office View - Visual simulation of agent interactions
• Org Chart - Hierarchical visualization of teams and agents
• Chat Rooms - Slack-style persistent chat rooms per team
• Projects - Project-level task management with filtered kanban boards

Running Locally

Start TinyAGI first (API default: http://localhost:3777), then:

tinyagi office

This auto-detects when dependencies or builds are needed (e.g. after tinyagi update) and starts the production server on http://localhost:3000.

For development with hot-reload:

cd tinyoffice
npm install
npm run dev

If TinyAGI API is on a different host/port, set:

cd tinyoffice
echo 'NEXT_PUBLIC_API_URL=http://localhost:3777' > .env.local

📋 Commands

Commands work with the tinyagi CLI.

Core Commands

Command	Description	Example
(no command)	Install, configure defaults, start, and open TinyOffice	tinyagi
start	Start TinyAGI daemon	tinyagi start
stop	Stop all processes	tinyagi stop
restart	Restart TinyAGI	tinyagi restart
status	Show current status and activity	tinyagi status
channel setup	Configure channels interactively	tinyagi channel setup
logs [type]	View logs (discord/telegram/whatsapp/queue/heartbeat/all)	tinyagi logs queue

Agent Commands

Command	Description	Example
agent list	List all configured agents	tinyagi agent list
agent add	Add new agent (interactive)	tinyagi agent add
agent show <id>	Show agent configuration	tinyagi agent show coder
agent remove <id>	Remove an agent	tinyagi agent remove coder
agent reset <id>	Reset agent conversation	tinyagi agent reset coder
agent provider <id> [provider]	Show or set agent's AI provider	tinyagi agent provider coder anthropic
`agent provider

--model | Set agent's provider and model |tinyagi agent provider coder openai --model gpt-5.3-codex` |

Team Commands

Command	Description	Example
team list	List all configured teams	tinyagi team list
team add	Add new team (interactive)	tinyagi team add
team show <id>	Show team configuration	tinyagi team show dev
team remove <id>	Remove a team	tinyagi team remove dev
team add-agent <t> <a>	Add an existing agent to a team	tinyagi team add-agent dev reviewer
team remove-agent <t> <a>	Remove an agent from a team	tinyagi team remove-agent dev reviewer
team visualize [id]	Live TUI dashboard for team chains	tinyagi team visualize dev

Chatroom Commands

Command	Description	Example
chatroom <team>	Real-time TUI viewer with type-to-send	tinyagi chatroom dev
office	Start TinyOffice web portal on port 3000	tinyagi office

Every team has a persistent chat room. Agents post to it using [#team_id: message] tags, and messages are broadcast to all teammates. The chatroom viewer polls for new messages in real time — type a message and press Enter to post, or press q/Esc to quit.

API endpoints:

GET  /api/chatroom/:teamId          # Get messages (?limit=100&since=0)
POST /api/chatroom/:teamId          # Post a message (body: { "message": "..." })

Provider & Custom Provider Commands

Command	Description	Example
provider [name]	Show or switch global AI provider	tinyagi provider anthropic
provider <name> --model <model>	Switch provider and model; propagates to matching agents	tinyagi provider openai --model gpt-5.3-codex
provider <name> --oauth-token <token>	Store OAuth token for a built-in provider	tinyagi provider anthropic --oauth-token sk-ant-oat01-...
provider list	List all custom providers	tinyagi provider list
provider add	Add a new custom provider (interactive)	tinyagi provider add
provider remove <id>	Remove a custom provider	tinyagi provider remove proxy
model [name]	Show or switch AI model	tinyagi model opus

Custom provider details

Custom providers let you use any OpenAI or Anthropic-compatible API endpoint (e.g., OpenRouter, proxy servers, self-hosted models).

Define a custom provider in settings.json:

{
  "custom_providers": {
    "my-proxy": {
      "name": "My Proxy",
      "harness": "claude",
      "base_url": "https://proxy.example.com/v1",
      "api_key": "sk-...",
      "model": "claude-sonnet-4-6"
    }
  }
}

Field	Required	Description
name	Yes	Human-readable display name
harness	Yes	CLI to use: claude or codex
base_url	Yes	API endpoint URL
api_key	Yes	API key for authentication
model	No	Default model name for CLI

Assign a custom provider to an agent:

tinyagi agent provider coder custom:my-proxy
tinyagi agent provider coder custom:my-proxy --model gpt-4o

Auth token storage — store credentials for built-in providers so you don't need separate CLI auth:

tinyagi provider anthropic --oauth-token sk-ant-oat01-...
tinyagi provider anthropic --api-key sk-ant-...
tinyagi provider openai --api-key sk-...

Anthropic supports both oauth_token (exported as CLAUDE_CODE_OAUTH_TOKEN) and api_key (exported as ANTHROPIC_API_KEY). OAuth takes priority if both are set. OpenAI keys are saved as models.openai.api_key and exported as OPENAI_API_KEY. If nothing is configured, the process inherits environment variables directly.

API endpoints:

GET    /api/custom-providers              # List custom providers
PUT    /api/custom-providers/:id          # Create or update
DELETE /api/custom-providers/:id          # Delete

See [docs/AGENTS.md](docs/AGENT