A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.

Multi-Agent Harness for Production AI

Your AI Chief of Staff — a personal operating system starter kit that adapts to your role. No coding required.

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

Self-evolving SDLC enforcement for AI coding agents — hooks, skills, and one-command setup for Claude Code. Plan before coding, test before shipping, escalate when uncertain. Measures itself getting better over time.

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

from vibe coding to agentic engineering - practice makes claude perfect

Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

The original AI Chief of Staff built on Claude Code and Obsidian. ADHD prosthetic, open to anyone. Superseded by chief-of-staff-2.

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

Playwright for coding agents. Benchmark Claude Code, Codex, Gemini, and OpenCode on your own tasks - and test that your skills, MCP servers, and CLIs work when an agent uses them. Sandboxed YAML suites, activation checks, A/B experiments, CI gates.