Lists (3)
Sort Name ascending (A-Z)
Starred repositories
Traust security auditing harness, skills, and commands
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
OpenShell is the safe, private runtime for autonomous AI agents.
Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0
This Magisk module adds the required firmware for external wireless adapters to be used with NetHunter.
Docker configuration for running VLLM on dual DGX Sparks
AI-based automatic backporting and feature porting for codebases and LLM inference engines
Hardware testing for the software world. Real or virtual, local or remote, human, automated or agentic.
A command line tool and library for transferring data with URL syntax, supporting DICT, FILE, FTP, FTPS, GOPHER, GOPHERS, HTTP, HTTPS, IMAP, IMAPS, LDAP, LDAPS, MQTT, MQTTS, POP3, POP3S, RTSP, SCP,…
Samples for the GMA Next-Gen SDK
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
Quickly create and run optimised Windows, macOS and Linux virtual machines
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
Discover best root apps, Magisk, KernelSu & LSPosed(xposed) modules & rooting guides
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
An autonomous agent for deep financial research
Teams-first Multi-agent orchestration for Claude Code
Embedding ML models in a programmable switch to achieve line-rate per-packet traffic classification and anomaly detection.
A dynamic in-network aggregation framework using programmable switches to optimize gradient synchronization in distributed deep learning. Supports multi-tenant environments. Compatible with PyTorch…
Ansible playbook to setup a Strix Halo to support ROCm
Unofficial Python SDK for the eToro Public API. Async-first, fully typed, built for algo trading.