47,133 repositories indexed
1–24 of 181 · Most stars
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.
The repository host gives no description.
Infrastructure for continually self‑improving agents
PRINTFILM: AI short-video marketing and AI short-drama creation platform
TranslatedFlyingMouse Format (飞鼠格式) - a free file format conversion tool for Windows (works offline, with FFmpeg/LibreOffice/Poppler/Tesseract built in). Converts between image/document/spreadsheet/PPT/PDF/audio-video/WPS formats + OCR + batch conversion; audio supports only common formats. Author: 牢蜂 (LaoFeng, "jailed bee") | For personal free use only; commercial sale, resale, and re-skinning are prohibited
TranslatedA knowledge graph for mathematics (primary school to high school), English (grade 3 to high school), and junior high school physics: 1,644 knowledge points, 2,403 prerequisite edges, and 6,723 questions, aligned with the curriculum standards, with an adaptive prerequisite diagnostic.
TranslatedChinese version of the AI pose reference gallery · 1439 sets / 2878 images / fully localized into Chinese · zero-dependency static gallery
A studio for image and video generation — one prompt bar, each model’s own settings, and every finished run in one gallery.
The open source AI video agent: turns any coding agent into a video agent, with an editor to change anything it makes.
TranslatedQwen-Image 2.1 NSFW/pose image generation skill: author-level prompt recipes + NSFW LoRA + 136-pose VNCCS mannequin control; works with Claude Code / Codex / Cursor / OpenClaw
Turn any script into viral, multi-style animated stickman videos for Faceless YouTube Channels. Automate visuals, voiceover, captions & SFX. 100% Free & Open-Source.
Translated词光 (Ciguang, "word light") · Word Atlas — Illustrated IELTS vocabulary with 7,298 words, UK/US audio and FSRS review. Open-source app + CC BY 4.0 dataset.
Motion films that never cut to the next slide: every beat grows out of the one before, one continuous camera, continuity measured by an oracle. Product launch films and feature demos, made with a coding agent.
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
Specialised AI models for logo design — a brand-analysis model turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces real lockups and clear-space rules. Early access open.
TranslatedNon-autoregressive System 1 decision engine, designed for structured, typed decision-making scenarios. DeepOpen Multilingual, non-autoregressive System 1 decision engine.
The repository host gives no description.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
Multi-segment MiniMax H3 Director for official ComfyUI MiniMax-H3
Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
The animation engine for agents: blazingly fast math and 3D videos with Manim's Python API, on a Rust GPU core.