Translated[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. An open-source multimodal dialogue model with performance close to GPT-4o
- image-classification
- image-text-retrieval
- llm
- semantic-segmentation
Repository Index
65,764 visible repositories in the index
217–240 of 887 · Most stars
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖
the LLM vulnerability scanner
- ai
- llm-evaluation
- llm-security
- security-scanners
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
- decision-model
- jev
- qwen3
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
TranslatedAzur Lane bot (CN/EN/JP/TW) Azur Lane script | Seamless commissions and research, fully automatic Operation Siren (open world)
- azurlane
- azur-lane
- bot
- alas
TranslatedIntelligent Xianyu (Goofish) customer service bot system: an AI-based attendance solution built specifically for the Xianyu platform, providing 24/7 automated attendance on Xianyu, with support for multi-expert collaborative decision-making, intelligent price negotiation, and context-aware conversation.
Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract structured data with LLMs via Pydantic AI, or control the browser in natural language with Stagehand. Works with BeautifulSoup, Parsel, Playwright, and raw HTTP. Download HTML, PDF, images, and other files. Proxy rotation included.
- apify
- automation
- beautifulsoup
- crawler
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.
- age-of-empires
- claude-code
- claude-code-plugin
- fal
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
- academia
- arxiv
- brave
- deep-research
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!
- outlier-detection
- anomaly-detection
- outlier
- outlier-ensembles
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
Mobile-Agent: The Powerful GUI Agent Family
- agent
- mllm
- mobile-agents
- multimodal
Private AI agents for highly regulated teams, and for anyone who wants AI on their own computer. Open-source Python agent framework that runs fully offline.
Curated prompts, frameworks and papers for LLMs and agents, with an engineering bias. Prompt engineering, context engineering, agent harnesses, red teaming.
- awesome
- awesome-list
- chatgpt
- prompt
A unified ecosystem and workspace for large-scale federated learning of Large Models & LLMS. Store compute as Wifi
- compute-orchestration
- distributed-systems
- edge-computing
- edge-intelligence
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
- knowledge-graph
- large-language-model
- logical-reasoning
- multi-hop-question-answering
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
- model-serving
- mlops
- llmops
- generative-ai
👀 Train a 65M-parameter VLM from scratch in just 2h!
- artificial-intelligence
- chatgpt
- vision-language-model