Tinyagent Ts banner
alchemiststudiosDOTai alchemiststudiosDOTai

Tinyagent Ts

AI community

Description

TinyAgent brings the core ideas of the original Python library into a lean, zero-dependency TypeScript package. It turns plain functions into LLM-driven tools and lets you chain them together through a simple ReAct-style loop.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

tinyAgent-TS — Modern TypeScript Agent Framework

[![npm version](https://img.shields.io/npm/v/tinyagent-ts.svg)](https://www.npmjs.com/package/tinyagent-ts) [![License: BSL 1.1](https://img.shields.io/badge/License-BSL%201.1-blue.svg)](LICENSE)

**tinyAgent-TS** is a modern TypeScript framework for building AI agents with a clean, modular architecture. It provides a unified agent system with pluggable tools, multiple execution modes, and seamless LLM integration.


Table of Contents

  1. Key Features
  2. Project Structure
  3. Quick Start
  4. Core Concepts
  5. Execution Modes
  6. Tool System
  7. Examples
  8. Python Integration
  9. API Reference
  10. Migration Guide
  11. License

Key Features

  • Unified Agent Architecture: Single configurable Agent class for all use cases
  • Modular Design: Clean separation between models, agents, tools, and execution
  • Multiple Execution Modes: Simple (direct LLM) and ReAct (reasoning + acting)
  • Pluggable Tool System: Easy to add custom tools with Zod schema validation
  • Type-Safe: Full TypeScript support with comprehensive type definitions
  • Default Tools: File operations, web search, Python execution, and more
  • Flexible LLM Support: Works with OpenRouter, OpenAI, Anthropic, and more

Project Structure

The framework follows a clean modular architecture:

tinyagent-ts/
├── src/
│   ├── model/                  # LLM communication layer
│   │   ├── types.ts           # Model interfaces
│   │   ├── model-manager.ts   # Unified LLM communication
│   │   ├── openrouter-provider.ts # OpenRouter implementation
│   │   └── index.ts           # Exports
│   ├── agent/                 # Agent orchestration layer  
│   │   ├── types.ts           # Agent interfaces
│   │   ├── unified-age