Laravel is a PHP workable choice for streaming / event-driven. GreatCTO auto-detects both — adds the streaming archetype overlay, wires streaming-specific gates, and runs 34 specialist agents around your existing Laravel workflow.
GreatCTO reads your composer.json and detects laravel + streaming archetype from signals: imports, file structure, env vars, README hints.
Attaches the streaming archetype overlay: archetype-specific reviewer + compliance gates. Override if your specifics differ; the defaults are sensible for Laravel-style projects.
qa-engineer runs phpstan / phpunit / psalm; security-officer checks SQL injection + Laravel CSRF; performance-engineer reviews query N+1 + Redis cache patterns.
Bugs you've hit before in other Laravel projects (connection-pool exhaustion, ORM N+1 queries, retry storms) — the agent's Step 0 includes the prior detection order. MTTR drops 94 % on second occurrence (methodology).
$ cd my-laravel-app && npx great-cto init ✓ scanning manifests… found manifest ✓ stack: laravel (PHP) ✓ archetype: streaming ⚠ archetype + stack combo is unusual — review overlay manually ✓ 34 agents ready $ /start "add streaming feature" ▸ architect drafting ARCH-streaming.md… ▸ pm decomposing into beads tasks… ⚐ gate:plan — your approval needed
Approve → 3 senior-devs run in parallel worktrees → 5 reviewers fan out in parallel → gate:ship → deploy. One real run walked stage-by-stage: /proof.
Laravel (PHP) is not a typical fit for streaming / event-driven. The archetype overlay still attaches, but you may want to override defaults more aggressively. Check the streaming archetype page for the typical stack list and decide if your case is the right tool / right archetype.
No black-box "AI does it all" loop. GreatCTO is a deterministic state machine — 8 stages, 22 nodes, 2 human gates. Every node maps to a real agent on GitHub. Inspect the state machine →
$ npx great-cto init
Free, MIT, runs locally. Works in Claude Code, Cursor, OpenAI Codex CLI, Aider, and Continue.