Multi-AI Collaboration Harness

AI Collab

AI Collab organizes your local AI coding tools into a team with memory, collaboration, and recoverability. A native macOS app and CLI managing persistent multi-AI Scenarios — isolated workspaces, typed agent-to-agent messaging, one-click resume. Open source under MIT.

Four agents across two Scenarios messaging each other through the Host, without disturbing each other

Four agents across two Scenarios messaging each other through the Host, without disturbing each other

Features

A team with memory.

Isolated workspaces, reliable messaging, recoverable state — the primitives multi-AI work actually needs.

01

Persistent Scenarios

Each Scenario is a long-lived work room that keeps its workspace, participants, and conversation state. Close it tonight, resume it tomorrow with one click.

Persistent Scenarios
02

Isolated Workspaces

Every Scenario gets its own multi-repo workspace. Run many experiments in parallel without directory conflicts or state pollution.

Isolated Workspaces

Multi-Model Teams

Mix Claude, Codex, and locally hosted models in one Scenario, each with its own role — implementer, reviewer, analyst.

Reliable Agent Messaging

Agents exchange typed messages — questions, review requests, pushback — through a single Host authority with delivery receipts.

Works With Any Project

A generic adapter protocol: declare your repositories and environment in config files, or let the app scan your directory and draft them for you.

App + CLI

The macOS app is the primary entry for daily work; the CLI drives automation and diagnostics against the same Host.

Why AI Collab

01

Open source under MIT

02

Native macOS app — no Electron

03

Your code never leaves your machine

04

Vendor-neutral: Claude, Codex, local models

05

Recoverable after restart or interruption

06

Battle-tested on our own research daily

AI Collab processes everything on your device. Zero data collection. No account required.

AI Collab — Multi-AI Collaboration Harness