Lists (1)
Stars
MCP server for controlling Adobe Premiere Pro via CEP/ExtendScript — 269 tools for AI-driven video editing
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Navigate any Python codebase via knowledge graph + resumable LangGraph agents, powered by SurrealDB
HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods
PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models
A native Mac workspace for Hermes: real SSH, real terminal, real session data.
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.
The easiest way to turn SVGs into interactive React 3D components
eplicates and extends Anthropic's April 2026 paper ["Emotion Concepts and their Function in a Large Language Model"](https://transformer-circuits.pub/2026/emotions/index.html) on open-weight models…
The bedrock layer for AI coding agents. One governance.md. Any project. Never stale. Universal skills + cross-agent compilation (Claude, Cursor, Codex, Gemini, Aider).
The best-benchmarked open-source AI memory system. And it's free.
Reverse engineer any repo into it's original prompt
On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.
Native and Compact Structured Latents for 3D Generation
Isolate vocals, drums, bass, and other instrumental stems from any song
A Claude skill for developing WebGPU applications with Three.js
Native macOS GUI companion for the Hermes AI agent — dashboard, session browser, activity feed, embedded terminal chat, memory editor, and more
Inspired by the need for freedom in app monetization. Thanks to the open-source community for their invaluable contributions to software freedom.
A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.
TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.