Code for Paper "The Geometry of Reasoning: Flowing Logics in Representation Space"

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

Multiplayer at the speed of light

[ICML 24 NGSM workshop] Associative Recurrent Memory Transformer implementation and scripts for training and evaluation

Public repository for Skills

Claude Code superpowers: core skills library

A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you

FreeCAD MCP(Model Context Protocol) server

From babyGPT to diffusion GPT: An annotated implementation of a character-level discrete diffusion model (adapted from Karpathy’s baby GPT).

Diffusion model derived evolutionary algorithm

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

Optimizing inference proxy for LLMs

Neural Networks: Zero to Hero

[ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"

An open-source application for building, observing, and collaborating with teams of AI agents.

Baby Dragon Hatchling (BDH) – Architecture and Code

A JAX-native LLM Post-Training Library

LIMI: Less is More for Agency

Breakthrough Method for Agile Ai Driven Development

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

AgentScope: Agent-Oriented Programming for Building LLM Applications

Autonomous Agents (LLMs) research papers. Updated Daily.

AI MCP Tools for Creating, Storing, and Utilizing Diagrams and Mind-maps with a Permanent Library.

Codes/Notebooks for AI Projects

Official inference framework for 1-bit LLMs

GraphAny: Fully-inductive Node Classification on Arbitrary Graphs

stagewise is the first frontend coding agent for existing production-grade web apps 🪄 -- Lives inside your browser 💻 -- Makes changes in local codebase 🤓 -- Compatible with all kinds of frameworks …

ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.

Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization