開源專案目錄

NirDiamant

Controllable-RAG-Agent

★ 1,625

This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.

chigwell

telegram-mcp

★ 1,625

Telegram MCP server powered by Telethon to let MCP clients read chats, manage groups, and send/modify messages, media, contacts, and settings.

Simpleyyt

ai-manus

★ 1,623

AI Manus是一個通用的AI Agent系統，支援在沙箱環境中運行各種工具和操作。

pixeltable

pixeltable

★ 1,622

The unified multimodal backend for AI data apps. Database, orchestration, and serving in one Python file.

pavlin-policar

openTSNE

★ 1,622

Extensible, parallel implementations of t-SNE

intel

auto-round

★ 1,621

英特爾 AutoRound 是一款用於量化工作流程的模型最佳化工具包，可降低推理成本，同時保持人工智慧部署的準確性。

ammaarreshi

Generals-Mac-iOS-iPad

★ 1,621

Command & Conquer Generals: Zero Hour running natively on macOS, iPhone & iPad — real engine (EA GPL v3 source, via GeneralsX), DXVK/MoltenVK renderer, RTS touch controls. No game assets included.

Tencent

WeMM-Embedding

★ 1,620

WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.

wiredoor

wiredoor

★ 1,620

Self hosted ingress-as-a-service platform that allows you to expose applications and services running in private or local networks to the internet

roryclear

clearcam

★ 1,620

Add object detection, tracking, mobile notifications, and search to any security camera.

vllm-project

guidellm

★ 1,620

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

MayersScott

rkn-block-checker

★ 1,620

Diagnose RKN/TSPU internet blocks layer by layer (DNS, TCP, TLS, HTTP)

csinva

imodels

★ 1,619

此專案圍繞「csinva/imodels」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。

activeloopai

hivemind

★ 1,618

Hivemind turns your traces into reusable skills across agents

ray-r-ren

agent-apprenticeship

★ 1,618

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

MengTo

kage

★ 1,618

An interactive five-chapter night walk through a Kyoto mountain temple, rendered live in Three.js.

Ildaron

Laser_control

★ 1,616

Laser for control mosquito, weed, and pest

Agents365-ai

video-podcast-maker

★ 1,616

Topic → 4K narrated video for coding agents. v5.3.0: local TTS (edge free + azure, no external engine), manifest-based Asset Engine, Remotion composition, cost-gated AI generation, Bilibili/YouTube/Xiaohongshu/Douyin/WeChat Channels

dotnet

infer

★ 1,614

Infer.NET is a framework for running Bayesian inference in graphical models

UbiquitousLearning

mllm

★ 1,613

Fast Multimodal LLM on Mobile Devices