A Tree Search Library with Flexible API for LLM Inference-Time Scaling

Official repo for Learning to Reason for Long-Form Story Generation

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

MCP generator for OpenAPIs 🫳🎤💥

A monorepo template for building webapps - perfect for LLMs

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Exploring Applications of GRPO

Scira (Formerly MiniPerplx) is a minimalistic AI-powered search engine that helps you find information on the internet and cites it too. Powered by Vercel AI SDK!

🔧 Compare how Agent systems perform on several benchmarks. 📊🚀

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

An autonomous agent that conducts deep research on any data using any LLM providers

This is the template I use to start new full-stack projects.

Automatic evals for LLMs

Fully open data curation for reasoning models

Fully open reproduction of DeepSeek-R1

LLM101n: Let's build a Storyteller

Using Azure Machine Learning

A python parametric CAD scripting framework based on OCCT

AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Official inference repo for FLUX.1 models

Foundational Models for State-of-the-Art Speech and Text Translation

Explore how you can use Amazon Bedrock with Python in a dynamic environment! It includes a FastAPI app and a Next.js frontend, perfect for learning and experimentation with generative AI on AWS.

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

AI chat for any model.

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.