Code for the Boxer research paper

Code for the manim-generated scenes used in 3blue1brown videos

Scalable data pre processing and curation toolkit for LLMs

The open source coding agent.

Train the smallest LM you can that fits in 16MB. Best model wins!

Curated list of datasets and tools for post-training.

Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments

InternVL-U is a 4B-parameter unified multimodal model (UMM) that brings multimodal understanding, reasoning, image generation, image editing into a single framework.

OpenClaw-RL: Train any agent simply by talking

Using AI for high quality writing

The agent-native LLM router for OpenClaw. 41+ models, <1ms routing, USDC payments on Base & Solana via x402.

Semi-automated research assistant for academic research and software development. Supports Claude Code, OpenCode, and Codex CLI across ideation, coding, experiments, writing, and publication.

[Remote Sensing 2026] Co-Training Vision Language Models for Remote Sensing Multi-task Learning

Moonshot's most powerful model

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Official repo of "MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents". It can be used to evaluate a GUI agent with a hierarchical manner across multiple platforms, includi…

Config files for my GitHub profile.

[ACL 2026 Main] Official repository for paper: OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents

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.

EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework

爬抖音，爬取别人的美好生活

Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

抖音搜索、抖音Api、抖音直播Api、抖音评论采集、抖音弹幕、抖音采集、抖音爬虫、抖音去水印、抖音下载、抖音解析抖音爬虫源码、抖音去水印源码、抖音解析源码、抖音桌面批量去水印工具源码、抖音快手视频剪辑去重工具源码、直播间送礼、粉丝团

TikTok搜索、TikTokApi、TikTok直播Api、TikTok评论采集、TikTok弹幕、TikTok采集、TikTok爬虫、TikTok去水印 源码

Official Python toolkit for the Qwen3-ASR API. Parallel high‑throughput calls, robust long‑audio transcription, multi‑sample‑rate support.

Official repo for "GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes"

[CVPR 2025] OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?