Stop waiting for your AI agent to finish. Run them all at once.

Each agent gets its own git branch and worktree. Nothing touches main until you say so.

You ask Claude Code to refactor auth. It works for 10 minutes. You wait. Then you ask it to add notifications. It works for 8 minutes. You wait. Then rate limiting. More waiting.

What if all three ran at the same time — each on its own branch — and you just picked the results?

$ agex create --prompt "Refactor auth to JWT"
$ agex create --prompt "Add push notifications"
$ agex create --prompt "Add API rate limiting"

# Go get coffee. Come back to:
$ agex summary --human

  agex · 3 tasks · 3 completed

  ┃ ✓  a1b2c3  completed  12.4s  3/3  +47 -12  JWT auth
  ┃ ✓  d4e5f6  completed   9.2s  3/3  +31 -8   Push notifications
  ┃ ✓  g7h8i9  completed  15.1s  3/3  +62 -19  Rate limiting

$ agex accept a1b2c3 d4e5f6 g7h8i9   # merge all three

That's agex. Parallel AI agents, isolated branches, nothing touches main until you say so.

Works with Claude Code, Codex CLI, Copilot CLI, and any agent that runs shell commands.

# Install (pick one)
brew install ruban-24/tap/agex
npm install -g @ruban24/agex

# Start using it immediately — no setup required
cd your-project
agex create --prompt "Add JWT auth with refresh tokens"
agex create --prompt "Add session-based auth with Redis"

That's it. agex create works in any git repo — no agex init needed. It bootstraps the workspace automatically on first use.

Want verification, agent hooks, or provisioning? Run agex init to configure them:

agex init   # auto-detects project, sets up verify commands and agent skill files

Then just tell your agent:

"Use agex to try 2 different approaches to refactor the auth module, then verify both and merge the best one."

# Check in whenever you want
agex summary --human

# Verify, review, and ship the winner
agex verify <id> --human
agex review <id> --human
agex accept <id> --human

Requires Node.js >= 20 and git.

AI coding agents are fast — but they work on your branch, one task at a time. You're serializing work that could be parallel.

The real cost isn't the agent's time. It's yours — sitting idle while it finishes.

agex gives each agent its own git worktree and branch. They work simultaneously, can't interfere with each other, and nothing merges until you verify and approve.

No cloud. No accounts. No team buy-in needed. Install it, use it. Everything lives locally.

agex uses worktrees under the hood, but handles what raw worktrees don't — environment setup (.env, secrets), dependency management (node_modules symlinking), port isolation, automated verification, side-by-side comparison, and cleanup.

Without agex	With agex

You already use an AI coding agent and you've hit one of these walls:

• "I have 4 features to ship and my agent does them one at a time" — fan them all out in parallel
• "My agent broke main again" — every task is isolated, nothing merges until tests pass
• "I want to try 3 approaches and pick the best" — verify all three, merge the winner

Not for trivial single-file edits, strictly sequential tasks, or non-git projects.

agex init drops a skill file into your repo so your agent discovers agex automatically. Or install just the skill file with npx skills:

npx skills add ruban-24/agex --skill agex

Any agent that can run shell commands works with agex via subprocess mode (--cmd).

Real-time activity capture is Claude Code only. agex activity <id> shows per-turn tool calls (Read/Edit/Bash/Grep…) for Claude Code sessions via its hook API. Codex and Copilot tasks still record lifecycle events (create, exec, verify, finish, subagent start/stop), but the per-tool timeline won't be populated.

# Review mode: auto (agent merges on verify pass) or manual (agent asks before merging)
review: manual

# Commands to verify task results
verify:
  - "npm test"
  - "npm run lint"
  - "npm run build"

# Files to copy into each worktree (e.g., secrets not in git)
copy:
  - ".env"
  - "config/local.json"

# Directories to symlink into worktrees (shared, not copied)
symlink:
  - "node_modules"

# Commands to run after workspace creation
setup:
  - "npm install"

# Example: pnpm monorepo
copy:
  - .env
  - packages/api/.env
  - packages/web/.env

symlink: []  # avoid symlinking node_modules in monorepos

setup:
  - pnpm install

verify:
  - pnpm run lint
  - pnpm run test
  - pnpm run build

# Fan out 3 different agents on the same task
agex run --prompt "JWT auth (Claude)" \
  --cmd "claude -p 'refactor auth to use JWT'" --wait &
agex run --prompt "JWT auth (Codex)" \
  --cmd "codex -q 'refactor auth to use JWT'" --wait &
agex run --prompt "JWT auth (Copilot)" \
  --cmd "copilot-cli 'refactor auth to use JWT'" --wait &
wait

# Compare all three, accept the best
agex compare $(agex list --json | jq -r '.[].id' | tr '\n' ' ')
agex accept <best-id> --reviewed
agex clean

{
  "mcpServers": {
    "agex": {
      "command": "agex-mcp",
      "args": []
    }
  }
}

See CONTRIBUTING.md for development setup and guidelines.

If agex saves you time, star the repo — it helps others find it.

MIT