Stars
CMP 170HX technical wiki: silicon, firmware, the community unlock, procedures and open problems. 55 pages.
GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 437 tok/s single-user, 841 tok/s at 8 users, 262K context, TP4 or PP4, one-command container install
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, r…
RigMark benchmarks local AI the way coding agents actually use it.
Orchis is a [Material Design](https://material.io) theme for GNOME/GTK based desktop environments.
VSCode Remote Development: Open any folder on a remote machine using SSH.
Open-source, self-hosted logs and traces with full-text search directly on S3-compatible object storage.
DeepSeek V4.1 Flash on 4x RTX PRO 6000 Blackwell: native weights, DSpark, vision, NVMe or locked RAM Engram offload.
Build Virtual Machine Image from Dockerfile or Docker image
A one-page guide and a ready-made prompt for cleaning up an Android TV over ADB. No root, every step reversible, ten languages.
Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK
High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.
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.
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.
API-first multi-agent coding assistant with CodeAct tool calling and first-class terminal support.
A proxy for minimax-m2, enabling interleaved thinking, and tool calls.
High-performance safetensors model loader
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
"Complete setup guide for multi-GPU vLLM inference on NVIDIA Blackwell RTX Pro 6000 cards with Ubuntu 24.04, CUDA 12.8, and NCCL optimization"
Orchestrate Claude, Codex and Grok in one app. Open-source (MIT), reuses the subscriptions you already pay for.
🪄 Spin up ready-to-code, disposable dev environments on your own servers. Self-hosted alternative to Gitpod and Github Codespaces.
A vulnerability scanner for container images and filesystems
Use Claude Agent SDK from any ACP client
A Model Context Protocol (MCP) server that provides AI assistants with secure, read-only access to your ShadowGit repositories. This enables powerful debugging and code analysis capabilities by giv…
ZeroFS: A log-structured filesystem for S3. ZeroFS serves S3-compatible buckets as POSIX filesystems over NFS and 9P, or as raw block devices over NBD.
Lightweight coding agent that runs in your terminal