Skip to content
View DUBSOpenHub's full-sized avatar
  • GitHub Staff
  • 07:31 (UTC -08:00)

Block or report DUBSOpenHub

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DUBSOpenHub/README.md

Mission Control: a live radar of 37 projects by Gregg Cochran (@DUBSOpenHub), sorted by lane and recency. I build systems that help AI agents do real work, and prove it.

01 — Choose your lane

Learn: First Light helps anyone build a first AI agent with GitHub Copilot, with no coding.Build: Dark Factory turns a short goal into a production-grade pull request with sealed-envelope testing and human approval.Orchestrate: Terminal Stampede runs up to 20 AI coding agents in parallel in your terminal.Prove: Havoc Hackathon pits AI models against each other, scores them with sealed judges and crowns a winner.

Copy the install commands
# FIRST LIGHT: Build your first AI agent with GitHub Copilot
curl -fsSL https://raw.githubusercontent.com/DUBSOpenHub/copilot-first-light/main/install.sh | bash

# DARK FACTORY: Run inside GitHub Copilot CLI
/skills add DUBSOpenHub/dark-factory

# TERMINAL STAMPEDE: Run up to 20 AI coding agents in tmux panes
curl -fsSL https://raw.githubusercontent.com/DUBSOpenHub/terminal-stampede/main/quickstart.sh | bash

# HAVOC HACKATHON: Run inside GitHub Copilot CLI
/skills add DUBSOpenHub/havoc-hackathon

02 — Flight log: the latest pushes

looper (BUILD): Small, verified steps in a bounded 20-pass loop. Last pushed Nov 04. copilot-skills (LEARN): Voice-friendly skills for GitHub Copilot CLI. Last pushed Nov 04. havoc-hackathon (PROVE): Pit AI models against each other. Score them sealed. Last pushed Nov 01. dark-factory (BUILD): Sealed-envelope tests. Human-approved delivery. Last pushed Oct 31. shadow-score-spec (PROVE): A framework-agnostic metric for AI code quality. Last pushed Oct 27.


The standard: the question isn’t how many agents you can launch, it’s what they can prove they accomplished.

Built in the open with GitHub Copilot · Updated 2026-11-04 · All 37 projects →

Pinned Loading

  1. dark-factory dark-factory Public

    🏭 Agentic dark factory for AI building with sealed-envelope testing

    TypeScript 26 3

  2. havoc-hackathon havoc-hackathon Public

    Pit AI models against each other. Score them sealed. Crown a winner. All built using the GitHub Copilot CLI. ⚡

    Python 5 3

  3. groundhog-day groundhog-day Public

    🐿️ Autonomous backup agent for Copilot CLI skills. Your laptop will crash. Your skills won't. Watches, syncs, pushes. Starts on boot, runs forever, zero interaction.

    Shell 5 1

  4. swarm-command swarm-command Public

    🐝 Swarm Command — Multi-model consensus swarm orchestrator for Copilot CLI. Instantly launch up to 250 agents across 16 models with shadow scoring.

    CSS 5 2

  5. terminal-stampede terminal-stampede Public

    A parallel agent runtime for your terminal. Run up to 20 AI coding agents simultaneously in tmux panes. Works with any CLI agent.

    Shell 4 1

  6. copilot-cli-agent-pulse copilot-cli-agent-pulse Public

    ⚡ Copilot CLI Agent Pulse — Real-time agent tracking dashboard for the GitHub Copilot CLI.

    Python 4 3