Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

Python Deep Agent framework built on top of Pydantic-AI, designed to help you quickly build production-grade autonomous AI agents with planning, filesystem operations, subagent delegation, skills, …

Design engineering for Claude Code. Craft, memory, and enforcement for consistent UI.

Differentiable, Hardware Accelerated, Molecular Dynamics

Stanford NLP Python library for Representation Finetuning (ReFT)

Main repository for the Modular Autonomous Discovery for Science (MADSci) Framework

CausalPFN: Amortized Causal Effect Estimation via In-Context Learning

[NeurIPS2025 Spotlight 🔥 ] Official implementation of "UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection"

Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

💫 Toolkit to help you get started with Spec-Driven Development

Low-latency AI engine for mobile devices & wearables

Training Sparse Autoencoders on Language Models

a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

Segment Anything for Microscopy

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

Inference algorithms for models based on Luce's choice axiom

PaCMAP: Large-scale Dimension Reduction Technique Preserving Both Global and Local Structure

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

verl: Volcano Engine Reinforcement Learning for LLMs

[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)

Best practices & guides on how to write distributed pytorch training code

Making large AI models cheaper, faster and more accessible

SGLang is a high-performance serving framework for large language models and multimodal models.

Proteina is a new large-scale flow-based protein backbone generator that utilizes hierarchical fold class labels for conditioning and relies on a tailored scalable transformer architecture.

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).