Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini PC.

Reverse engineer anything with agents, from app behavior down to native binaries.

LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context

Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing link, and gufo TP2 integration

Local AI coding agent for AMD Strix Halo (Ryzen AI Max+ 395): Qwen3.8 125B on the Radeon 8060S iGPU via llama.cpp, small models on the NPU, crash recovery, logged benchmarks. No API key needed, clo…

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.

High-performance single-GPU inference for selected model checkpoints and GPUs.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering…

A repository to explore the feasibility of Plonky3 verification in Plutus.

Solidity verifier for the Spartan-WHIR SNARK over the KoalaBear field

llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both

Public challenge to find optimal qLDPC codes.

ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬

Supplemental materials for the ECDSA.Fail paper

Strix Halo inference engine. Qwen Flash Next Q4_K_XL: 1,702.93pp, 65.25tg single user, 184.74 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2

C++ and Python support for the CUDA Quantum programming model for heterogeneous quantum-classical workflows

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

Design with Intent: A collection of specialized AI agents and skills for experience design and strategy.

The practices that made software work didn't stop working. They stopped keeping up. PAAD brings them back at AI speed.

Framework for specifying and proving properties—such as robustness, fairness, and interpretability—of machine learning models using Lean 4.

Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

Automated Penetration Testing Agentic Framework Powered by Large Language Models

An IR language for fault-tolerant quantum programming

The Language-Integrated Quantum Operations (LIQUi|>) Simulator

基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works w…