LiteReality-Agent

We propose LeapTalk, a novel framework that achieves stable and real-time talking-head generation with a single forward step, scaling to arbitrarily long videos.

Locate a nearby Bluetooth device by signal strength, from the macOS command line — for when Find My isn't available

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Evolution API is an open-source WhatsApp integration API

augmented reality anatomy educational explorer

computer vision and sports

Fast and accurate AI powered file content types detection

A feed-forward 3D foundation model for reconstructing scenes from streaming data

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

A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven f…

Desktop app to generate 3D models from images using local AI — runs entirely on your GPU

The only downloader you need. 下载器的集大成者.

autonomous red teaming platform; multi-agent offensive-security meta-harness

👾 A sleek, zero-setup torrent finder and downloader that lives right in your terminal.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

KaliGPT: an Agentic AI (built with Gemini, ChatGPT, Ollama, OpenRouter Models) fine tuned for ethical hackers & students in offensive security making workflows smarter, faster, and more accessible.

First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come …

ComfyUI wrapper for LiTo: single-image to 3D Gaussian Splat generation (Apple Research, ICLR 2026)

KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM

Real-world benchmarks of llama.cpp RPC across Apple Silicon (Metal) + NVIDIA Blackwell (CUDA) over 10GbE

Real-world benchmarks of llama.cpp RPC across Apple Silicon (Metal) + NVIDIA Blackwell (CUDA) over 10GbE

An image-to-world skillset for Claude.

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, a…

Simple, privacy-respecting local NVR — fast setup, flexible recording, no cloud required

[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

🤖 A minimal and customizable Docker image running the Android emulator as a service.

LLM inference in C/C++

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.