Stars
A WebSocket-based inter-terminal communication system that creates a local network between multiple Pi coding agent terminals. Enables terminals to discover each other, exchange messages, and orche…
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods
Audio2Face is a real-time audio-to-face animation service that converts streaming audio input into synchronized facial animation data. The system uses advanced machine learning models to extract au…
To bring back voice to those who lost it
AI agents running research on single-GPU nanochat training automatically
real time face swap and one-click video deepfake with only a single image
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
Turing Pi Cluster with Turing RK1s and Jetson Orin Nanos
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. The knowledge is av…
A minimal, secure Python interpreter written in Rust for use by AI
Workload Discovery on AWS is a solution to visualize AWS Cloud workloads. With it you can build, customize, and share architecture diagrams of your workloads based on live data from AWS. The soluti…
Build Real-Time Knowledge Graphs for AI Agents
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
A lightweight, lightning-fast, in-process vector database
MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting
A TTS that fits in your CPU (and pocket)
Open-source runtime for math. Write MATLAB syntax, run on CPU + GPU automatically. Install via CLI, embed via NPM, or try instantly in the browser — no account needed.
A lightweight Kubernetes-compatible container orchestration system written in Rust, implementing the Container Runtime Interface (CRI) with support for single containers, Kubernetes-style pods, and…
Fully automatic censorship removal for language models
Hierarchical Reasoning Model Official Release
Implementation of the Hierarchical Reasoning Model (HRM), applied to a pathfinding task, plus performance study.
Lower-latency OpenMP-style minimalistic scoped thread-pool designed for 'Fork-Join' parallelism in Rust and C++, avoiding memory allocations, mutexes, CAS-primitives, and false-sharing on the hot p…
A light-weight torrent media center at one place.