Stars
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.
Opinionated skills for AI coding agents to create stunning diagrams and visualizations directly in Markdown. These skills extend agent capabilities across diagram generation, data visualization, an…
A Git-compatible VCS that is both simple and powerful
Open implementation of Attention Residuals (Kimi Team, arXiv:2603.15031)
"If you have a big enough dictionary, just about everything is a word." ― Dave Barry
Latent Collaboration in Multi-Agent Systems
MoBA: Mixture of Block Attention for Long-Context LLMs
This repository contains the official implementation of the paper **"Improving Rationality in the Reasoning Process of Language Models through Self-playing Game."**
Free, simple, fast interactive diagrams for any GitHub repository
A high-throughput and memory-efficient inference and serving engine for LLMs
Voice-to-text app for macOS to transcribe what you say to text almost instantly
Real-time monitoring for Claude Code agents through simple hook event tracking.
Beads - A memory upgrade for your coding agent
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Give your agents the power of the Hugging Face ecosystem
Edit Banana: A framework for converting statistical formats into editable.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
Official Project Page for Deep Delta Learning (https://huggingface.co/papers/2601.00417)
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
open-source agentic AI data assistant for the next generation of AI + Data products.