Animation engine for explanatory math videos

A library of agent skills for CAD, CAE and CAM

Comp AI CRM is an open source, CRM designed for AI agents. Agentic-first CRM.

Removes 20+ patterns of AI slop from any piece of writing.

Think with AI beyond the chat box. A shared canvas for handwriting, equations, diagrams, and spatial reasoning.

AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 152 shot recipe cards, 209 motion previews, a production-ready template

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

Clone a voice from a few minutes of audio and generate speech locally — Qwen3-TTS fine-tuning pipeline with CLI and web UI

Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a separate vision model through tools: look, OCR, scan, crop, com…

Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Document viewer and in-place editor plugin for Directory Opus. Markdown with Reading, Live and Source split preview, Mermaid diagrams, LaTeX/AsciiMath maths, syntax-highlighted code, an editable CS…

Finally, a way to let ChatGPT touch your WordPress site that doesn't involve handing over your API key, your admin password, or your dignity.

Infinite Worlds with Versatile Interactions

Community plugin to control Blender 3D with any LLM of your choice

Agent-neutral LLM advisor skill for TrustedRouter model choice, cost, speed, privacy, MCP, SDKs, and AI IQ context.

Codex skill for complete paper-cut collage ad production, local IndexTTS-2 voice cloning, animation, audio and MP4 QC

Three.js medieval settlement sandbox: procedural hills, forest, and rivers. Curved dirt roads with PBR wear blending, wooden bridges, and junctions. Place mills, quarries, reforesters, and burgage …

Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.

Skills to help agents understand videos

Scripts for agents, shared between my repositories.

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

A TTS that fits in your CPU (and pocket)

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.

A tiny Rust gateway for running coding agents across model providers safely.

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

[ECCV 2026] WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion

Setup wizard for Hermes Gateway Desktop

Reusable skills, scripts, and production workflows for agent-led video creation with HyperFrames, FFmpeg, captions, audio sync, and render QA. Community project from real HyperFrames video work; no…

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.