Introduction
A modern, modular, and type-safe framework for building AI agents using typescript
What is Agenite?
Agenite is a powerful TypeScript framework designed for building sophisticated AI agents. It provides a modular, type-safe, and flexible architecture that makes it easy to create, compose, and control AI agents with advanced capabilities.
The name Agenite (pronounced as Agen-ite) comes from combining “Agent” with the suffix “-ite”, representing a framework that crystallizes best practices for building AI agents.
Key features
Type safety and developer experience
Type safety and developer experience
- Built from the ground up with TypeScript
- Robust type checking for tools and agent configurations
- Excellent IDE support and autocompletion
Tool integration
Tool integration
- First-class support for function calling
- Built-in JSON Schema validation
- Structured error handling
- Easy API integration
Provider agnostic
Provider agnostic
- Support for AWS Bedrock and Ollama
- Consistent interface across providers
- Easy extension for new providers
Advanced architecture
Advanced architecture
- Bidirectional flow using JavaScript generators
- Step-based execution model
- Built-in state management with reducers
- Flexible middleware system
Model context protocol (MCP)
Model context protocol (MCP)
- Standardized protocol for connecting LLMs to data sources
- Client implementation for interacting with MCP servers
- Access to web content, filesystem, databases, and more
- Similar to how USB-C provides universal hardware connections
Core concepts
Agents
Agents are the central building blocks in Agenite. An agent:
- Orchestrates interactions between LLMs and tools
- Manages conversation state and context
- Handles tool execution and results
- Supports nested execution for complex workflows
- Provides streaming capabilities for real-time interactions
Tools
Tools extend agent capabilities by providing specific functionalities:
- Strong type safety with TypeScript
- JSON Schema validation for inputs
- Flexible error handling
- Easy API integration
Providers
Currently supported LLM providers:
- AWS Bedrock with Claude models
- Local models via Ollama
- Consistent interface for easy provider switching
- Built-in streaming support
Available packages
Agenite is organized into several modules that you can install based on your needs:
Core packages
These are the essential packages for building agents with Agenite.
@agenite/agent
Core agent library for orchestrating LLMs and tools
@agenite/tool
Tool interface for extending agent capabilities
@agenite/llm
LLM abstraction layer and utilities
Provider packages
Choose one or more provider packages based on the LLMs you want to use.
@agenite/openai
OpenAI API provider (GPT models)
@agenite/anthropic
Anthropic API provider (Claude models)
@agenite/bedrock
AWS Bedrock provider (Claude, Titan models)
@agenite/ollama
Ollama provider for local models
MCP package
Integration with the Model Context Protocol (MCP) for standardized data access.
@agenite/mcp
Client implementation for interacting with MCP servers to access external data sources
Middleware packages
Optional packages for enhancing agent functionality.
Typical installation
For a basic setup with OpenAI:
For AWS Bedrock with optional pretty logging:
Next steps
Install Agenite
Start by installing the core packages and your preferred provider:
Learn the basics
Follow our Quick start guide to create your first agent
Explore examples
Check out our Examples to see Agenite in action
Build something amazing
Use our API reference to build your own AI agents