Stars
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients
Python tool for converting files and office documents to Markdown.
ymichael / open-codex
Forked from openai/codexLightweight coding agent that runs in your terminal
Lightweight coding agent that runs in your terminal
https://transformer-circuits.pub/2025/attribution-graphs/methods.html
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
DeepEP: an efficient expert-parallel communication library
FlashMLA: Efficient MLA decoding kernels
Fully open reproduction of DeepSeek-R1
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Turn any glasses into AI-powered smart glasses
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
Supercharge Your LLM Application Evaluations 🚀
A quick guide (especially) for trending instruction finetuning datasets
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
A generative speech model for daily dialogue.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
An extremely fast Python package and project manager, written in Rust.
Community managed domain list. Generate geosite.dat for V2Ray.
Speech To Speech: an effort for an open-sourced and modular GPT4-o
AI 助手全套开源解决方案，自带运营管理后台，开箱即用。集成了 ChatGPT, Azure, ChatGLM,讯飞星火，文心一言等多个平台的大语言模型。支持 MJ AI 绘画，Stable Diffusion AI 绘画，微博热搜等插件工具。采用 Go + Vue3 + element-plus 实现。
Label Studio is a multi-type data labeling and annotation tool with standardized output format
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Quickly and accurately render even the largest data.