Laya model playing Flappy Bird on a CPU using OpenVINO INT8 inference

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.

Local typed decisions, contrastive data curation, and model evaluation.

A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.

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 re…

Turn any open model into a classifier/jev endpoint

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Fastest and cheapest web agent

LLM inference in C/C++

Simulate the C. Elegans worm brain in your browser and interact with the worm as it moves around

Supplemental data for Berg et al. (2025)

A curated list of fruit fly connectome projects: MaleCNS, FlyWire, brain simulations, embodied models, games, and research tools.

best way to save what you love

px0 is the IDE for humans and AI, optimized for quick, fast code reviews. It turns your browser into a zero-latency console with native Git and GitHub integrations, instant search across massive co…

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…

WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder…

Pioneering Automated GUI Interaction with Native Agents

Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, CPU only, lossless, on stock llama.cpp

Password protect a static HTML page, decrypted in-browser in JS with no dependency. No server logic needed.

Model Zoo For OpenCV DNN and Benchmarks.

YuNet Face Detection on DepthAI

[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) …

GLM-5: From Vibe Coding to Agentic Engineering

Write HTML. Render video. Built for agents.

A ComfyUI-style visual node editor for OpenCV image processing with sharable workflows

Rembg is a tool to remove images background

Qwen3.8-27B at 64K on one RTX 3060 12GB: D-CFR llama.cpp research patch and benchmarks