# Lighter

> A lightweight TypeScript AI agent framework. Currently in alpha.

Start with the quickstart, then explore the guides and API reference.

- [Lighter](/docs/): Lighter is a lightweight TypeScript framework for building AI agents. It handles the loop between model calls and tool execution so you can build an agent with just a few lines of code.
- [Quickstart](/docs/getting-started/quickstart/): Connect to a model and get your first reply with a minimal example. This guide uses OpenAI and requires Node.js 22+ and a TypeScript project configured for ESM.
- [Core concepts](/docs/getting-started/concepts/): Six components cover the main ideas in Lighter: Provider, Model, Agent, Message, Tool, and Hook.
- [Configure an agent](/docs/guides/configuration/): Only model is required when creating an Agent. Add tools, a system prompt, and lifecycle hooks as needed.
- [Add tools](/docs/guides/tools/): Tools let the model call functions you define. You describe the tool and implement its logic; Agent validates arguments, runs the function, and returns the result to the model.
- [Manage messages and conversation history](/docs/guides/conversations/): Lighter does not automatically save conversations. Pass existing history into each run, then append the new messages from its result to continue the conversation.
- [Stream responses](/docs/guides/streaming/): Use stream() instead of run() to receive text as the model generates it. Both methods execute the same tool loop.
- [Use lifecycle hooks](/docs/guides/hooks/): Hooks let you read or modify requests and results at specific points. Use them for logging, input preprocessing, and response checks.
- [Handle errors](/docs/guides/errors/): Agent uses status to indicate whether a run completed. When a model or hook fails, check the result before reading error.
- [Choose and configure a provider](/docs/providers/): Providers connect to model services. After switching providers, you still use the same message and tool interfaces through Model and Agent.
- [Custom providers](/docs/providers/custom/): Implement the Provider interface and pass it to new Model(provider) to connect another model service. Agent does not need to know the service's specific API.
- [Use Model directly](/docs/advanced/model/): Use Model directly when you need a single model call or want to control tool execution yourself.
- [Runtime limits and application responsibilities](/docs/advanced/limits/): Lighter handles the core loop between the model and tools. Your application adds storage, execution limits, permissions, and monitoring as needed.
- [Agent API](/docs/reference/agent/): This page covers Lighter 0.1.0. For usage, see configure an agent and streaming.
- [Model and Provider API](/docs/reference/model-and-providers/): For usage, see use Model directly, built-in providers, and custom providers.
- [Messages API](/docs/reference/messages/): Messages use role to identify their purpose. For usage, see conversation history.
- [Tool API](/docs/reference/tools/): Tool wraps parameter validation, function execution, and tool results. For usage, see add tools.
- [Hooks API](/docs/reference/hooks/): All four hook classes share the same construction pattern. For a working example, see lifecycle hooks.
- [Errors API](/docs/reference/errors/): For usage, see error handling. Built-in providers use ModelError for recognized model-call errors.

[Full documentation](/llms-full.txt)