Highlights
Stars
SAF-MCP is a comprehensive security framework for documenting and mitigating threats in the AI Agent ecosystem.
A local AI agent security learning lab built around a fictional travel booking simulator.
An agentgateway workshop using a simple local agent named trendwatch
Next Generation Agentic Proxy for AI Agents and MCP servers
Manages Unified Access to Generative AI Services built on Envoy Gateway
A topic-centric list of HQ open datasets.
Rust bindings for the C++ api of PyTorch.
Claude Code skill: tighten long recordings — remove silences, ums, dead air. Preserves laughs and comedic pauses. Fast on Apple Silicon.
3D graphics rendering system for FPGA, the project contains hardware rasterizer, software geometry engine, and application middleware.
Claude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development
🛡️ MIRAGE: Open-source AI Honeypot for active defense. Detect, deceive, and study prompt injections, jailbreaks, and data exfiltration in real time with decoy LLM personas and fabricated data.
a heavily quantized LoRa GPT-2 model
LaTeX files for the Deep Learning book notation
Local-first MLOps platform built with Kubernetes, Helm, Argo CD, MLflow, Airflow, KServe, MinIO, DVC, Prometheus and Grafana. Designed to evolve from local infrastructure to cloud.
A secure low code deception runtime framework, leveraging AI for System Virtualization.
One Dollar Computer — desktop emulator / OS
Self-hosted MCP gateway and control plane for connecting, controlling, and operating MCP servers.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
A Helm Chart for ZeroClaw to deploy on Kubernetes
The Security Toolkit for LLM Interactions
A reverse proxy that provides authentication with Google, Azure, OpenID Connect and many more identity providers.