Stars
Capture Kubernetes cluster state to a portable archive and replay it through a mock API server — use kubectl against a customer's environment without live cluster access.
Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
Open Science is an open-source, local-first, model-agnostic AI research workbench for scientific discovery.
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"
🥧 Savoury implementation of the QUIC transport protocol and HTTP/3
Experimental Linux microvm setup with a TypeScript Control Plane as Agent Sandbox
Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.
Tyzen automatically generates type-safe TypeScript bindings from Rust code. Built with Tauri in mind, it syncs your data structures, commands, and events in milliseconds without the manual boilerpl…
A programmable Mixture-of-Models router for heterogeneous LLM inference
Enhanced (but compatible) version of the classic ttyrec
Terminal pixel-art office for AI coding agents
Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.
Open-source adversarial testing engine, SDK, and CLI for AI agents. Runs locally or against the Humanbound Platform.
droast - a dockerfile linter that actually has opinions 🔥
Measuring frontier coding agents on original, long-horizon engineering tasks
Unified CLI for local skills, external CLIs, and terminal AI chat.
Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.
A macOS command-line tool to work with default apps
Manage worktrees without managing worktrees.
A smarter cd command. Supports all major shells.
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Go.
Write tests against structured configuration data using the Open Policy Agent Rego query language
Phishing Domains, urls websites and threats database. We use the PyFunceble testing tool to validate the status of all known Phishing domains and provide stats to reveal how many unique domains use…