Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
VLX-Seek is an efficient VLM that grounds fine-grained visual targets with high precision in wild environments.
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.
An Open-World Foundation Model for General-Purpose Embodied Intelligence.
Maps and turn-by-turn navigation for Android without Google Play Services: the best of open map data, with Google lookups by choice. Runs on degoogled phones and can avoid Flock cameras
Network stack research tool. TCP tunnel with pluggable transports.
AutoSwarm: Unify Your Agents. Unify Your Context (Codex · Claude Code · DeepSeek Harness · Muse · Grok · WorkBuddy· nanobot · and more)
AI PPT赛道终结者，史上最最最强 PPT Skill！！！ 使用GPT生成豪华的图片格式PPT，然后转换为完全可编辑的PPTX文件。
Fill-in-your-own-data framework for YouTube / short-form video automation: CapCut JSON + ffmpeg tooling + an onboarding questionnaire. Ships with zero private data.