What is o8?

o8 is a local-first macOS app that runs a team of AI coding agents under one orchestrator, with a governance layer that reviews every change before it merges.

The short version

o8 is a control room for autonomous engineering. You describe what you want; one orchestrator decomposes the work, dispatches it to a fleet of coding agents, and a review gate sits between those agents and your main branch. Nothing merges unreviewed, and nothing risky merges without your sign-off. It runs on your own Mac, against your own model keys.

It is the layer abovethe coding tools, not another editor. If a developer asks “what runs a team of coding agents locally, with a review gate,” that is what o8 is built to be.

How it works

The orchestrator breaks a task into packets and dispatches each one to a worker agent running in its own isolated git worktree. The agents can’t reach each other and can’t touch main until the gate allows it. Run ten at once — when two reach for the same file, you see the collision before anyone ships.

• Orchestrator — decomposes your intent, dispatches the fleet, and reports back.
• Parallel fleet — every agent works in a sealed-off git worktree.
• Review gate — every diff queues for review; approval is a decision, not a default.
• Merge gate — rebase, typecheck, and head-SHA lock, then merge in order.
• Conflict detection — collisions between lanes surface before anyone ships.
• Engineering Brain — agents ask the repo instead of grepping; answers come with citations.
• Organizational memory — when the same fix lands three times, o8 proposes a rule you accept or reject.
• Audit trail — every packet, merge, and event is recorded and replayable.
• Mobile approval — read transcripts and approve or reject from your phone.
• Symon — a voice operator that dispatches through the same gate.

What makes it different

Tools like Cursor, Copilot, and Claude Code put one model inside your editor. o8 coordinates many agents and adds the part they leave out: a governance layer — approvals, audit, and organizational memory — so you can let agents run without losing oversight. The agents do the work; you run the room.

Which models it runs

o8 is model-agnostic. It talks to Claude, OpenAI (Codex), Google Gemini, and opencode through one adapter, so you’re never locked to a single provider. You bring your own API keys or subscriptions — o8 doesn’t proxy your requests or mark up usage.

Where it runs, and what it costs

o8 runs on macOS 14+ today. The current build is Intel and runs on Apple Silicon via Rosetta (Windows and Linux are planned). The app is free forever with your own keys — the full app, the governance gate, the Engineering Brain, the canvas. Not a trial, not a crippled tier. An optional one-time Founding Operator edition adds a managed inference layer for those who want the fast version run for them.

Your code, prompts, and the work your agents produce stay on your machine — o8 keeps its state in a local database (~/.o8) and only talks to the AI providers you choose to configure. More in the docs, pricing, and FAQ.