TopOpenSourceAI
zh

Trending Open Source AI Projects

Ranked by GitHub star change since this site's latest sync — spot what's accelerating.

Last synced:

Rank Project Stars Star Change
1541 AI-Infra-from-Zero-to-Hero

🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSys, etc. 🗃️ Llama3, Mistral, etc. 🧑‍💻 Video Tutorials.

 4.3K +3
1542 ChatGPT-On-CS

AI customer service bot for Pinduoduo, Qianniu, and Douyin Shop: auto-replies, product Q&A, after-sales appeals; unified reception on WeChat, Xiaohongshu, JD, Douyin, Bilibili, Weibo; supports DeepSeek/Qwen and custom knowledge base.

 4.3K +3
1543 zvt

modular quant framework.

 4.3K +3
1544 PyRIT

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

 4.4K +3
1545 neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.

 4.3K +3
1546 bRAG-langchain

Everything you need to know to build your own RAG application

 4.2K +3
1547 ComfyUI-LTXVideo

LTX-Video Support for ComfyUI

 4.1K +3
1548 auto-subs

On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.

 4.1K +3
1549 openagents

OpenAgents - The collaboration OS for AI agents

 4.0K +3
1550 Qwen3-Omni

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

 4.0K +3
1551 gemini-skills

Skills for the Gemini API, SDK and model/agent interactions

 4.0K +3
1552 liteflow

Lightweight rule engine that orchestrates AI agents as components via DSL, supporting hot deployment and multi-language scripting.

 3.8K +3
1553 atmosphere

Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

 3.8K +3
1554 semantic-router

Superfast AI decision making and intelligent processing of multi-modal data.

 3.9K +3
1555 qiushi-skill

Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done.

 3.8K +3
1556 SimpleMem

SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

 3.7K +3
1557 agent-sprite-forge

Agent Skill for generating 2D sprite sheets and map, transparent PNG frames, and animated GIFs from prompts.

 4.0K +3
1558 map-anything

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

 3.7K +3
1559 TurboDiffusion

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

 3.6K +3
1560 SageAttention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

 3.7K +3
< Previous
/ 172
Next >