Stars
🔥 Clone and recreate any website as a modern React app in seconds
Qwen Code is a coding agent that lives in the digital world.
We track and analyze the activity and performance of autonomous code agents in the wild
An open-source AI agent that brings the power of Gemini directly into your terminal.
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
Independent technology for modern publishing, memberships, subscriptions and newsletters.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
A comprehensive set of LLM benchmark scores and provider prices. (deprecated, read more in README)
SGLang is a fast serving framework for large language models and vision language models.
A package for statistically rigorous scientific discovery using machine learning. Implements prediction-powered inference.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
[ICML 2025] Official repository for paper "OR-Bench: An Over-Refusal Benchmark for Large Language Models"
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
Arena-Hard-Auto: An automatic LLM benchmark.
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Large Language Model Text Generation Inference