A skill to stop your coding agent from burying the answer. ADHD-friendly output.

Offline, privacy-first grammar checker. Fast, open-source, Rust-powered

🚀 A curated list of awesome AI-powered news aggregation, RSS management, and content automation tools

Write HTML. Render video. Built for agents.

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Claude Code skill/plugin: immersive scroll-scrubbed 'fly through the world' landing pages generated with Higgsfield (Emons-style diorama flights, seamless connectors, portable scrub engine).

FOSS 2D animation tool for turning static illustrations into mesh-deformable characters

AI-powered Claude skill for Spine 2D skeletal animation — auto-rig, animate, and preview characters

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

AI-powered 3D suite built on Blender, with an integrated agent, moodboard, generation tools and layer-based painting

Caffeine for modern macOS

The public version of the Marching Squares Terrain plugin for godot.

Performance comparison of Javascript rendering/game engines: Three.js, Pixi.js, Phaser, Babylon.js, Two.js, Hilo, melonJS, Kaboom, Kaplay, Kontra, Excalibur, Litecanvas, LittleJS, Canvas API and DOM.

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

Lore is a next-generation, open source version control system

The open-source AI voice studio. Clone, dictate, create.

[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

SkinTokens: A Learned Compact Representation for Unified Autoregressive Rigging

A Warcraft III world editor.

Godot-MCP — Model Context Protocol (MCP) integration for the Godot Engine. AI tools for the Godot Editor in C#, with cloud connection to ai-game.dev. Apache-2.0.

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

Lightweight (7MB) Terminal-first AI-native dev workspace

super expressive prompting model based on ltx2.3

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

The agent that grows with you

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

Dead-simple Bun CLI that runs Codex and Claude Code in a loop.