Yutao

valuecell. ValueCell is a community-driven, multi-agent platform for financial applications.

kimi-cli. Kimi Code CLI is your next CLI agent.

nautilus_trader. Production-grade Rust-native trading engine with deterministic event-driven architecture

agents-for-openbb. Custom agents for OpenBB Workspace

OpenBB. Open Data Platform for analysts, quants and AI agents.

ccxt. A unified trading API with more than 100 crypto exchanges and prediction markets in JavaScript / TypeScript / Python / C# / PHP / Go / Java

Biomni. Biomni: a general-purpose biomedical AI agent

hummingbot. Open source software that helps you create and deploy high-frequency crypto trading bots

thetagang. ThetaGang is an IBKR bot for collecting money

ibkr-ai-agent. Interactive Brokers MCP-based AI Agent

ibkr_agent. Python

ibkr-mcp-server. MCP Server for IBKR Client

a-list-of-claude-code-agents. A list of Claude Code Sub-Agents submitted by the community.

Kimi-K2. Kimi K2 is the large language model series developed by Moonshot AI team

Feishu-MCP. Feishu / Lark 飞书文档与任务管理工具，支持 MCP 服务器和 CLI + Skill 两种使用方式，可无缝集成 Cursor、Claude Code、Cline 等 AI 编码工具

opcode. A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

BrowserOS. 🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.

quantstats. Portfolio analytics for quants, written in Python

superagent. Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

moonpalace. MoonPalace（月宫）是由 Moonshot AI 月之暗面提供的 API 调试工具。

stagehand. The SDK For Browser Agents

TradingAgents. TradingAgents: Multi-Agents LLM Financial Trading Framework

quantitative_analysis. 量化分析

mcp-yahoo-finance. A Model Context Protocol (MCP) server for Yahoo Finance.

autogen. A programming framework for agentic AI

xhs-mcp-server. 小红书MCP服务器 | 秒级工具调用执行，笔记用户搜索、通知消息监控等；打造2026最简单、最快速、最精准、最好用的小红书MCPServer！

deepwiki-open. Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

deer-flow. An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

FramePack. Lets make video diffusion practical!

ai-hedge-fund. An AI Hedge Fund Team

OpenHands. 🙌 OpenHands: AI-Driven Development

RD-Agent. Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

qlib. Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

KunQuant. A compiler, optimizer and executor for financial expressions and factors

CHRONOS. Repo for NAACL 2025 Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"

MoBA. MoBA: Mixture of Block Attention for Long-Context LLMs

FunClip. FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.

ai2srt. 利用 GeminiAI 一键为长视频创建解说短视频，并支持音视频转录字幕

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

octogen. Octogen is an Open-Source Code Interpreter Agent Framework

electron-browser-shell. A minimal, tabbed web browser with support for Chrome extensions—built on Electron.

music. a music player forked from YesPlayMusic。高颜值的第三方网易云播放器，支持 Windows / macOS / Linux :electron/Docker:

CogVLM. a state-of-the-art-level open visual language model | 多模态预训练模型

bark-voice-cloning-HuBERT-quantizer. The code for the bark-voicecloning model. Training and inference.

fastsdcpu. Fast stable diffusion on CPU and AI PC

worktool. 一款安全稳定的Android无障碍服务工具，支持控制企微/微信来运行的无人值守群管理企业微信机器人

openinterpreter. A coding agent for open models like Kimi K3

Grounding_LLMs_with_online_RL. We perform functional grounding of LLMs' knowledge in BabyAI-Text

FastGPT. FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

ToolBench. [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

SuperAGI. <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

codeinterpreter-api. 👾 Open source implementation of the ChatGPT Code Interpreter

gpt-code-ui. An open source implementation of OpenAI's ChatGPT Code interpreter

DB-GPT. open-source agentic AI data assistant for the next generation of AI + Data products.

so-vits-svc. SoftVC VITS Singing Voice Conversion

bark. 🔊 Text-Prompted Generative Audio Model

docprompting. Data and code for "DocPrompting: Generating Code by Retrieving the Docs" @ICLR 2023

JARVIS. JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

gerev. 🧠 AI-powered enterprise search engine 🔎

fastertransformer_backend. Python

plantuml. Generate diagrams from textual description

apitable. 🚀🎉📚 APITable, an API-oriented low-code platform for building collaborative apps and better than all other Airtable open-source alternatives.

chat-gpt-ppt. Use ChatGPT (or other backends) to generate PPT automatically, all in one single file.

Co-Speech-Motion-Generation. Freeform Body Motion Generation from Speech

ml-neuman. Official repository of NeuMan: Neural Human Radiance Field from a Single Video (ECCV 2022)

RPA. Ui.Vision Open-Source RPA Software with Computer Vision, OCR, Anthropic Computer Use/LLM. Selenium IDE import/export.

lowdefy. Build apps that AI can generate, humans can review, and teams can maintain. Config that works between code and natural language.

VideoPose3D. Efficient 3D human pose estimation in video using 2D keypoint trajectories

PaddleBoBo. 基于飞桨开发的虚拟主播

docusaurus. Easy to maintain open source documentation websites.

vuepress-theme-antdocs. 🔥🎨 An Ant Design style theme for VuePress. (QQ Group: 867711329) [NOTE: The AntDocs-next is WIP.]

FastDeploy. High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

fastDeploy. Deploy DL/ ML inference pipelines with minimal extra code.

aframe. :a: Web framework for building virtual reality experiences.

NVFlare. NVIDIA Federated Learning Application Runtime Environment

mellotron. Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

nnsvs. Neural network-based singing voice synthesis library for research

TikTok-Compilation-Video-Generator. A system of bots that collects clips automatically via custom made filters, lets you easily browse these clips, and puts them together into a compilation video ready to be uploaded straight to any social media platform. Full VPS support is provided, along with an accounts system so multiple users can use the bot at once. This bot is split up into three separate programs. The server. The client. The video generator. These programs perform different functions that when combined creates a very powerful system for auto generating compilation videos.

screenity. The free and privacy-friendly screen recorder with no limits 🎥

DiffSinger. DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

WGANSing. Multi-voice singing voice synthesis

deckdeckgo. The web open source editor for presentations

moving-letters. Text animated with anime.js

taichi. Productive, portable, and performant GPU programming in Python.

luci. LuCI - OpenWrt Configuration Interface

online_speaker_change_detector. Online streaming speaker change detection model in Pytorch

n8n. Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

talking-head-anime-demo. Demo for the "Talking Head Anime from a Single Image."

LipSync. LipSync for Unity3D 根据语音生成口型动画 支持fmod

talking-head-anime-2-demo. Demo programs for the Talking Head Anime from a Single Image 2: More Expressive project.

Wav2Lip. This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

openpose. OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

OpenVtuber. 虚拟爱抖露(アイドル)共享计划, 是基于单目RGB摄像头的人眼与人脸特征点检测算法, 在实时3D面部捕捉以及模型驱动领域的应用.

vignette. The open source VTuber software. ❤

VTuber_Unity. Use Unity 3D character and Python deep learning algorithms to stream as a VTuber!

OpenVTuberProject. Open Vtuber project containing all sub projects

EEND_PyTorch. A PyTorch implementation of End-to-End Neural Diarization

cyclone. Powerful workflow engine and end-to-end pipeline solutions implemented with native Kubernetes resources. https://cyclone.dev

ormb. Docker for Your ML/DL Models Based on OCI Artifacts

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

uhubctl. uhubctl - USB hub per-port power control

AutoHotkey. AutoHotkey - macro-creation and automation-oriented scripting utility for Windows.

pywinauto. Windows GUI Automation with Python (based on text properties)

find3-cli-scanner. The command-line scanner that supports Bluetooth and WiFi

indoor-location. balabala

find3. High-precision indoor positioning framework, version 3.

IndoorPos. 这是一个采用蓝牙4.0--iBeacon技术的室内定位服务端程序。

docker-wxwork. DoWork is a Dockerized WeChat Work (盒装企业微信) PC Windows Client for Linux

docker-wechat. DoChat is a Dockerized WeChat (盒装微信) PC Windows Client for Linux

Python-UIAutomation-for-Windows. 🐍Python 3 wrapper of Microsoft UIAutomation. Support UIAutomation for MFC, WindowsForm, WPF, Modern UI(Metro UI), Qt, IE, Firefox, Chrome ...

TagUI. Free RPA tool by AI Singapore

speexdsp. Speex audio processing library - THIS IS A MIRROR, DEVELOPMENT HAPPENS AT https://gitlab.xiph.org/xiph/speexdsp

ec. Echo Canceller, part of Voice Engine project

EarTrumpet. EarTrumpet - Volume Control for Windows

BackgroundMusic. Background Music, a macOS audio utility: automatically pause your music, set individual apps' volumes and record system audio.

go-webrtcvad. cgo interface to WebRTC Voice Activity Dectection

gotapestry. Go on Tapestry

ice. 🚀 ice.js: The Progressive App Framework Based On React（基于 React 的渐进式应用框架）

rpi-audio-receiver. Raspberry Pi Audio Receiver with Bluetooth A2DP, AirPlay 2, and Spotify Connect

LibreASR. :speech_balloon: An On-Premises, Streaming Speech Recognition System

CPWechatXposed. 使用Xposed Hook微信等APP

bluez-alsa. Bluetooth Audio ALSA Backend

pybluez. Bluetooth Python extension module

BluetoothGattMitm. Revealing unknown GATT/BLE protocol by mediation in communication between device and client

Bluetooth_LE_MITM. Man-in-the-Middle Relay program between a Bluetooth Low-Energy (BTLE) Peripheral and Central

phasen. A unofficial Pytorch implementation of Microsoft's PHASEN

webcamoid. Webcamoid is a full featured and multiplatform camera suite.

voice-engine. building blocks to create voice interface applications

odas. ODAS: Open embeddeD Audition System

electron-transparency-demo. Demo for transparent windows with click-through in Electron

SpeechSplit. Unsupervised Speech Decomposition Via Triple Information Bottleneck

Realtime-audio2audio-alignment. temp_files

QASystemOnMedicalKG. A tutorial and implement of disease centered Medical knowledge graph and qa system based on it。知识图谱构建，自动问答，基于kg的自动问答。以疾病为中心的一定规模医药领域知识图谱，并以该知识图谱完成自动问答与分析服务。

VGGVox. VGGVox models for Speaker Identification and Verification trained on the VoxCeleb (1 & 2) datasets

WebRTCVAD_Wrapper. A simple Python wrapper to simplify working with WebRTC VAD and its rougher analogue based on RMS and ZCR (useful for processing audio recordings before using them with neural networks).

openrpa. Free Open Source Enterprise Grade RPA

TNN. TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.

zoomChatBot. A chatbot for zoom, in python.

Zoogle. Zoom Google Assistant Bot

MediaStreamRecorder. Cross browser audio/video/screen recording. It supports Chrome, Firefox, Opera and Microsoft Edge. It even works on Android browsers. It follows latest MediaRecorder API standards and provides similar APIs.

Guyu. Chinese GPT2: pre-training and fine-tuning framework for text generation

SongNet. Code for ACL 2020 paper "Rigid Formats Controlled Text Generation"：https://www.aclweb.org/anthology/2020.acl-main.68/

Resemblyzer. A python package to analyze and compare voices with deep learning

openvino. OpenVINO™ is an open source toolkit for optimizing and deploying AI inference

wechat.hook.sdk. 商用版微信开发SDK，非微信ipad/mac/android协议，已封装好全部API接口，可实现微信99%功能； 可开发微信群控、云控、微信机器人、个人号SCRM客服系统等， 微信二次开发SDK，微信个人号开发API接口协议。（提供源代码）

DALI. A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

cheetah. On-device streaming speech-to-text engine powered by deep learning

CnC_Remastered_Collection. Command & Conquer: Remastered Collection

CTC_pytorch. CTC end -to-end ASR for timit and 863 corpus.

espresso. Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

StreamingTransformer. Python

Tacotron-2. DeepMind's Tacotron-2 Tensorflow implementation

deep-voice-conversion. Deep neural networks for voice conversion (voice style transfer) in Tensorflow

asteroid. The PyTorch-based audio source separation toolkit for researchers

rnnt-speech-recognition. End-to-end speech recognition using RNN Transducers in Tensorflow 2.0

photo2cartoon. 人像卡通化探索项目 (photo-to-cartoon translation project)

espnet. End-to-End Speech Processing Toolkit

prefix-beam-search. Code for prefix beam search tutorial by @labodk

aeneas. aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

lip-reading-deeplearning. :unlock: Lip Reading - Cross Audio-Visual Recognition using 3D Architectures

open_stt_e2e. PyTorch end-to-end speech recognition

python-wechaty. Python Wechaty is a Conversational RPA SDK for Chatbot Makers written in Python

warp-rnnt. CUDA-Warp RNN-Transducer

warp-transducer. A fast parallel implementation of RNN Transducer.

server. The Triton Inference Server provides an optimized cloud and edge inferencing solution.

label-studio. Label Studio is a multi-type data labeling and annotation tool with standardized output format

rasa-webchat. A feature-rich chat widget for Rasa and Botfront

MegEngine. MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

nemo_examples. Python

dl_inference. 通用深度学习推理工具，可在生产环境中快速上线由TensorFlow、PyTorch、Caffe框架训练出的深度学习模型。

RE-VERB. speaker diarization system using an LSTM

TensorRT. PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

ffsubsync. Automagically synchronize subtitles with video.

vadnet. Real-time Voice Activity Detection in Noisy Eniviroments using Deep Neural Networks

WechatEnhancement. 仅供学习交流，禁止用于其他用途，请及时删除，禁止任何公司或个人发布与传播，不接受任何捐赠

jittor. Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

PyTorch_ONNX_TensorRT. A tutorial about how to build a TensorRT Engine from a PyTorch Model with the help of ONNX

Speech. A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

DSAlign. DeepSpeech based forced alignment tool

DSAlign. DeepSpeech based forced alignment tool

gorgonia. Gorgonia is a library that helps facilitate machine learning in Go.

deepspeech2-online-decoder. Online (real-time) decoder to be used with DeepSpeech2 model

Speech-Transformer. A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.

audiomentations. A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

wukong-robot. 🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目，支持ChatGPT多轮对话能力，还可能是首个支持脑机交互的开源智能音箱项目。

_rasa_chatbot. A Chinese task oriented chatbot in IVR(Interactive Voice Response) domain, implement by rasa. This is a demo with toy dataset, more data should be added for performance.

CTCWordBeamSearch. Connectionist Temporal Classification (CTC) decoder with dictionary and language model.

CTCDecoder. Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

mtl-text-recognition. multi-task learning for text recognition with joint CTC-attention

ASRFrame. An Automatic Speech Recognition Frame ，一个中文语音识别的完整框架， 提供了多个模型

mypy. Optional static typing for Python

code-server. VS Code in the browser

ev3play. 买了个lego ev3玩

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

deep-dregs. A streaming Speech to Text server using DeepSpeech

Gather-Deployment. Gathers Python deployment, infrastructure and practices.

service-streamer. Boosting your Web Services of Deep Learning Applications.

argo-workflows. Workflow Engine for Kubernetes

spleeter. Deezer source separation library including pretrained models.

pie. 百度云流式语音识别客户端 SDK