Call any LLM API with cost tracking, guardrails, logging and load balancing. 1.8k+ models, 80+ providers, 50+ endpoints (unified + native format). Available as a Python SDK or Proxy Server (AI Gateway).

A model-driven approach to building AI agents in just a few lines of code.

The most accurate document search and store for building AI apps

Evaluate your LLM's response with Prometheus and GPT4 💯

A set of tools that gives agents powerful capabilities.

Claude Code settings, commands and agents for vibe coding

Agent samples built using the Strands Agents SDK.

A website where you can compare every AI Model ✨

Lightweight LLM Interaction Framework

multi1: create o1-like reasoning chains with multiple AI providers (and locally). Supports LiteLLM as backend too for 100+ providers at once.

An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder can help you to build your own agents and tools.

This python program allows you to use Claude Code with Google's Gemini models.

Co-create PowerPoint slide decks with AI

A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.

This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite AI coding assistant to vibe-code Strands Agents.

Run Anthropic's Claude Code CLI using OpenAl's GPT-5 as the model backend (OR, if you need, use this repo as a LiteLLM Server boilerplate for creating your own AI assistants with LibreChat as the UI)

VividNode: Multi-purpose Text & Image Generation Desktop Chatbot (supporting various models including GPT).

To simplify and streamline LLM operations, empowering developers and organizations to harness the full potential of large language models with ease.

A Python Package to Access World-Class Generative Models

Documentation for the Strands Agents SDK. A model-driven approach to building AI agents in just a few lines of code.