Starred repositories
Scalable toolkit for efficient model reinforcement
Amazon Nova Act is a research preview of a new AI model for developers to build agents that take actions in web browsers
Python bindings to the Tree-sitter parsing library
Official Repository of Absolute Zero Reasoner
A repo lists papers related to LLM based agent
SYSTEM PROMPT TRANSPARENCY FOR ALL - CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, WINDSURF, DEVIN, REPLIT, AND MORE!
A lightweight framework for building LLM-based agents
Sim Studio is an open-source AI agent workflow builder. Sim Studio's interface is a lightweight, intuitive way to quickly build and deploy LLMs that connect with your favorite tools.
Code for the paper "AutoPresent: Designing Structured Visuals From Scratch" (CVPR 2025)
Source code for the collaborative reasoner research project at Meta FAIR.
Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
An implementation of the CSM(Conversation Speech Model) for Apple Silicon using MLX.
List of curated use cases built using Sesame's CSM 1B
A Datacenter Scale Distributed Inference Serving Framework
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
A Conversational Speech Generation Model
Audiobook Creator is an open-source tool that converts books (EPUB, PDF, TXT) into fully voiced audiobooks with intelligent character voice attribution. It uses NLP, LLMs, and Kokoro TTS to generat…
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
FlashMLA: Efficient MLA decoding kernels
DeepEP: an efficient expert-parallel communication library
My learning notes/codes for ML SYS.
Scalable toolkit for efficient model alignment
A very simple GRPO implement for reproducing r1-like LLM thinking.