Secure open source cloud runtime for AI apps & AI agents

Awesome Reasoning LLM Tutorial/Survey/Guide

A collection of MCP (Model Context Protocol) tools and examples for wandb and weave

Verdict is a library for scaling judge-time compute.

A framework for manifesting AI agents with a complete lack of conventional limitations

A chat interface for talking to Tyler, but you already knew that.

Medical o1, Towards medical complex reasoning with LLMs

The official Python library for the OpenAI API

NextBench is a collection of wide variety of benchmarks for accessing the performance of LLMs and VLMs and more.

Model Context Protocol Servers

Prompt design using JSX.

AdalFlow: The library to build & auto-optimize LLM applications.

Fully open reproduction of DeepSeek-R1

An extremely fast Python package and project manager, written in Rust.

A course on aligning smol models.

Customizable, AI-driven virtual assistant designed to streamline customer service operations, handle common inquiries, and improve overall user satisfaction through automated and contextually aware…

🤗 smolagents: a barebones library for agents that think in python code.

🙌 OpenHands: Code Less, Make More

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"

Agent driven automation starting with the web. Try it: https://www.emergence.ai/web-automation-api

Robust recipes to align language models with human and AI preferences

A Lightweight Recommendation System

Simple, unified interface to multiple Generative AI providers

Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Automatically evaluate your LLMs in Google Colab

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.