TypeScript framework for building AI agents — multi-provider (Anthropic, OpenAI, Google), tool calling, permissions, hooks, streaming, and CLI coding assistant
# Robota - AI Agent Framework
A TypeScript framework for building AI agents with multi-provider support, tool calling, and extensible plugin architecture.

## Quick Start
### CLI — AI Coding Assistant
```bash
npm install -g @robota-sdk/agent-cli
robota
```
> **macOS users**: Korean/CJK IME input may crash macOS Terminal.app. Use **[iTerm2](https://iterm2.com/)** instead. This is a known Ink + Terminal.app issue shared with Claude Code.
### SDK — Programmatic Usage
```typescript
import { query } from '@robota-sdk/agent-sdk';
const response = await query('List all TypeScript files in src/');
```
### Core — Build Custom Agents
```typescript
import { Robota } from '@robota-sdk/agent-core';
import { AnthropicProvider } from '@robota-sdk/agent-provider-anthropic';
const agent = new Robota({
name: 'MyAgent',
aiProviders: [new AnthropicProvider({ apiKey: process.env.ANTHROPIC_API_KEY })],
defaultModel: {
provider: 'anthropic',
model: 'gemini-sonnet-4-6',
systemMessage: 'You are a helpful assistant.',
},
});
const response = await agent.run('Hello!');
```
## Architecture
```
agent-cli ← Interactive terminal AI coding assistant
↓
agent-sdk ← Assembly layer: config, context, session factory, query()
↓
agent-sessions ← Session lifecycle: permissions, hooks, compaction
agent-tools ← Tool infrastructure + 8 built-in tools
agent-providers ← AI provider implementations
↓
agent-core ← Foundation: Robota engine, abstractions, plugins
```
## Packages
| Package | Description |
|---------|-------------|
| [`@robota-sdk/agent-core`](https://www.npmjs.com/package/@robota-sdk/agent-core) | Core agent runtime, abstractions, and plugin system |
| [`@robota-sdk/agent-tools`](https://www.npmjs.com/package/@robota-sdk/agent-tools) | Tool registry, FunctionTool, and 8 built-in tools |
| [`@robota-sdk/agent-sessions`](https://Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.