Starred repositories
OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.
Repository for getting started with the OfficeQA Benchmark.
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Hysteria, Tunnel, Mixed, HTTP, Tun, MTProto)
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for p…
Teams-first Multi-agent orchestration for Claude Code
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Agent-native knowledge engine with MCP tools for document indexing, wiki organization, fast retrieval and deep reading across PDF/DOCX/PPTX/Markdown
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 158 ready-to-use skills plus 100+ scientific databases covering biology, chem…
[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
AI agents running research on single-GPU nanochat training automatically
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"
Official Repository of MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
(CVPR 2026) TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better