I built a free local app that runs a team of agents

Описание и применение

Приложение RandComp Studio позволяет локально координировать несколько AI‑агентов, визуализируя задачи и результаты, без необходимости аккаунта и внешнего сервера.

Задача

Managing multiple Claude Code sessions simultaneously caused confusion about task ownership and progress.

Результат

RandComp Studio enables local, account‑free coordination of multiple AI agents, visualizing tasks and outputs while allowing interaction through app, CLI, or MCP.

Рабочий процесс

• Describe a project to RandComp Studio
• The coordinator agent splits the project into tasks
• For each task, a helper agent (developer, QA, designer, etc.) is started as a separate Claude Code session in its own terminal
• The app visualizes the growing task diagram, outputs, and pending user actions
• The user interacts via the app, CLI, or MCP to monitor progress
• Optional: use Codex, Kimi, or local models via Ollama

Доказательства

I kept running several Claude Code sessions at once and losing track of who was doing what and what was waiting on me.

Источник

So I built RandComp Studio: you describe a project, a coordinator agent splits it into tasks and starts helpers (developer, QA, designer…), each a real Claude Code session in its own terminal.

Источник

The app shows a diagram of the tasks as it grows, what each one produced, and what needs you.

Источник

You can use it three ways: the app, a randcomp CLI, or MCP so Claude Code itself can ask how the team is doing.

Источник

It also works with Codex, Kimi and local models via Ollama.

Источник

Local only: no account, no server of mine — it runs the CLIs you already pay for.

Источник

It sends four anonymous usage counts you can switch off in Settings.

Источник

Free early preview, Apple-silicon Macs for now (Windows/Linux later — one-person army).

Источник