開源專案目錄

ArcadeData

arcadedb

★ 1,159

專案速覽：ArcadeDB 多模型資料庫，一個支援 SQL、Cypher、Gremlin、HTTP/JSON、MongoDB 和 Redis 的 DBMS。 ArcadeDB 是 OrientDB（第一個多模型 DBMS）的概念分支。 ArcadeDB 支援向量嵌入。

tikv

pd

★ 1,158

TiKV 的放置驅動程式。具有預設連接埠的單節點 您可以直接在本機電腦上執行 pd-server。

janvarev

Irene-Voice-Assistant

★ 1,158

Ирина - русский голосовой ассистент для работы оффлайн. Поддерживает скиллы через плагины.

extropic-ai

thrml

★ 1,157

Thermodynamic Hypergraphical Model Library in JAX

scalameta

scalameta

★ 1,156

用於讀取、分析、轉換和產生 Scala 程式的函式庫。教學 如果您想了解如何使用 scalameta，請參閱本教學。

OpenHands

software-agent-sdk

★ 1,155

A clean, modular SDK for building AI agents with OpenHands V1.

easystats

performance

★ 1,155

:muscle: Models' quality and performance metrics (R2, ICC, LOO, AIC, BF, ...)

nico-martin

gemma4-browser-extension

★ 1,155

On-device AI agent Chrome extension powered by Transformers.js and Gemma 4

exoframejs

exoframe

★ 1,155

Exoframe is a self-hosted tool that allows simple one-command deployments using Docker

vm0-ai

vm0

★ 1,154

Zero, your trustworthy AI teammate for real work.

AI-QL

tuui

★ 1,153

A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.

yuezhiai

jonex

★ 1,153

All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine

lhotse-speech

lhotse

★ 1,152

Tools for handling multimodal data in machine learning projects.

ObservedObserver

streamlit-shadcn-ui

★ 1,151

此專案圍繞「ObservedObserver/streamlit-shadcn-ui」建置，面向真實業務場景，提供可重複使用、可持續維運的開源實作。

geektutu

interview-questions

★ 1,151

机器学习/深度学习/Python/Go语言面试题笔试题(Machine learning Deep Learning Python and Golang Interview Questions)

facebookresearch

fairseq2

★ 1,151

FAIR Sequence Modeling Toolkit 2

open-gigaai

giga-world-1

★ 1,151

A Roadmap to Build World Models for Robot Policy Evaluation

NVIDIA-Merlin

NVTabular

★ 1,151

NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

fcakyon

claude-codex-settings

★ 1,150

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

puemos

craftplan

★ 1,150

Self-hosted software for managing artisanal D2C micro-businesses