Claude Code manager
A Claude Code manager for all your projects
Aiola is a local desktop app that manages Claude Code across every project you run — parallel threads, a central cross-project view, tasks, GitHub, app logs, analytics, and scheduled automations. It manages Codex, Cursor, Grok CLI, and OpenCode from the same window, on your own subscriptions, and your code is never uploaded to Aiola — it stays on your machine and goes only to the AI provider you already subscribe to.
What is a Claude Code manager?
A Claude Code manager is a desktop app that sits on top of Claude Code and gives you a graphical way to run it across many projects at once — instead of juggling one terminal window per repo. Claude Code itself is Anthropic's agentic coding tool; it's excellent at planning and executing multi-step changes inside a single repository. What it doesn't do is give you a place to see and steer every project you're running it in.
Aiola is that place. It's a local desktop app that turns Claude Code into a managed, multi-project workspace: parallel threads, a central view across every repo, tasks that trigger agents, and an operations layer — app logs, analytics, feedback, and automations — around the code.
Why you need one when you run multiple projects
The moment you're running Claude Code in more than one repo, the hard part stops being the code and starts being context. Which project had which thread? What did the agent change yesterday in the other app? Where's the task you meant to hand off? With bare terminals, that state lives in your head and in a dozen tabs.
A Claude Code manager solves the coordination problem:
- One window shows every project's active threads, recent changes, and pending tasks.
- Threads keep each line of work isolated, so a fix in one repo never bleeds into another.
- Tasks and automations let agents keep working on a schedule instead of only when you're watching.
How Aiola manages Claude Code
Aiola wraps Claude Code with the surfaces a multi-project workflow needs:
- Threads — each thread is an independent Claude Code session with chat, diffs, branches, a terminal, and a built-in browser. Run several in parallel and split them side by side.
- Tasks — a per-project board that can trigger a Claude Code agent and hand the result back as a pull request.
- Automations — schedule recurring Claude Code jobs (triage, checks, summaries) that run on your machine with your subscription.
- GitHub, app logs, analytics, and feedback — the operations layer that lives next to the code, not in five other tools.
- A central cross-project dashboard so you steer the whole portfolio, not one repo at a time.
Run Claude Code, Codex, Cursor, Grok CLI, and OpenCode together
Most Claude Code GUIs manage only Claude. Aiola orchestrates Claude Code, Codex, Cursor, Grok CLI, and OpenCode from one app, on your own subscriptions. Pick the provider per thread or per task, and switch depending on the job — one agent for a refactor, another for a quick fix — without leaving the workspace. That cross-vendor reach is the difference between a single-tool GUI and a real command center.
What should you hand to a Claude Code manager, and what stays manual?
The best inputs have a clear repository, outcome, and stopping condition. A bug with a reproducible error, a small feature with acceptance criteria, or a recurring maintenance check fits naturally into a task and thread. Attach the relevant project context, choose whether the work belongs in the current checkout or a git worktree, and keep unrelated changes in another thread. This makes the resulting diff easier to understand and prevents two active jobs from competing for the same files.
Keep product decisions, security approval, destructive migrations, and final merge authority with a person. Aiola can make app logs, feedback, analytics, and GitHub state available beside the agent, but those signals do not prove that a proposed fix is correct. Read the diff, run the project's tests, inspect generated files, and confirm any external side effects before creating or merging a pull request. If the task is ambiguous, refine it in the board or thread instead of starting more parallel agents.
Provider choice also stays explicit. Claude Code can remain the focus of this workflow while a particular thread uses Codex, Cursor, Grok CLI, or OpenCode. Grok uses your authenticated Grok CLI access; Aiola probes the installed CLI for the models that subscription offers. The manager coordinates the work and records, while authentication, model availability, rate limits, and billing remain with each provider.
Local-first: your code stays on your machine
Aiola runs Claude Code on your own machine, against your own repositories. Your code is never uploaded to Aiola — it stays on your machine and goes only to the AI provider you already subscribe to — there's no cloud runner, no compute resale, and no API-key middleman. Threads, tasks, notes, and automations are stored locally. Optional analytics, logs, and feedback telemetry from shipped products is ingested through Aiola's cloud. Read more about how Aiola keeps your data yours.
macOS and Windows
Aiola runs on macOS 11+ (Apple Silicon and Intel) and Windows 10+ (64-bit). If you're on Windows, that matters: several Claude Code GUIs are macOS-only. See the Claude Code manager for Windows guide, or just download Aiola.
Feature comparison
Comparison based on publicly available information, 2026. You bring your own Claude subscription in all cases.
What are Aiola's current CLI and GUI Lifetime facts?
Aiola supports five agent CLIs: Claude Code, Codex, Cursor, Grok CLI (including grok-4.5), and OpenCode.
GUI Lifetime is available now at launch pricing: first 10 customers $49, next 30 $89, then $129. One-time payment.
GUI Lifetime includes the agent orchestrator GUI only; it does not include hosted analytics, app logs, feedback, or other hosted operations pages.
Your code and repos stay on your machine. Agent prompts and file context are sent only to the AI provider you choose — Anthropic (Claude Code), OpenAI (Codex), Cursor, xAI (Grok CLI), or whichever provider you configure in OpenCode — under your own subscription. Aiola never proxies, stores, or resells your code or model traffic. Threads, tasks, notes, and automations are stored locally (SQLite + plain files in your repo). If you use the optional analytics/logs/feedback layer for your shipped products, that telemetry is ingested via Aiola's cloud (Supabase/Tinybird). Offline: agent orchestration UI works offline; running agents requires provider access; GUI Lifetime keeps the local app opening even if Aiola's servers are unreachable.
FAQ
What is the best Claude Code manager?
Aiola is a strong choice if you run Claude Code across more than one project. It's a local desktop app that gives every project a workspace with parallel threads, a central cross-project view, tasks, GitHub, app logs, analytics, feedback, and scheduled automations — and it manages Codex, Cursor, Grok CLI, and OpenCode from the same window. You bring your own Claude subscription.
Does Aiola replace Claude Code?
No. Aiola is the layer around Claude Code, not a replacement for it. Claude Code still runs the agent; Aiola gives you a GUI, parallel threads, project isolation, and an operations layer on top. You can also run Codex, Cursor, Grok CLI, and OpenCode in the same app.
How does a multi-project Claude Code workflow look day to day?
Open each repository as its own workspace, create a task for a scoped outcome, and launch a thread from it. The thread keeps the conversation, diff, branch, terminal, and browser together; choose a git worktree when concurrent work must not touch the current checkout. Use the central view to check active work across projects, then open a workspace to review its diff, run tests, and move the task toward a pull request. Repeatable checks can become scheduled automations that run locally with your subscription. Aiola does not approve risky diffs, replace your editor, or make providers available offline: agents still need provider access, and you remain responsible for review, tests, and usage limits.
Do I need my own Claude subscription?
Yes. Aiola uses the Claude Code access you already pay for — there is no API-key markup and no compute resale. Sign in to Claude Code once and use it inside every Aiola workspace.
Does the Claude Code manager work on Windows?
Yes. Aiola runs on Windows 10+ (64-bit) and macOS 11+ (Apple Silicon and Intel). That matters because some Claude Code GUIs are macOS-only.
Can I run multiple Claude Code sessions at once?
Yes. Each Aiola thread is an independent Claude Code session with its own chat, diffs, branch, and terminal. Run several in parallel across projects and place them side by side in split view or on a canvas.
How much does it cost?
The Aiola download is free with a 7-day free trial. Pro starts at $24/month. GUI Lifetime is available now at launch pricing: first 10 customers $49, next 30 $89, then $129. One-time payment.
Related
Run all your AI coding agents from one app
Aiola supports five agent CLIs: Claude Code, Codex, Cursor, Grok CLI (including grok-4.5), and OpenCode. Your code and repos stay on your machine. Agent prompts and file context are sent only to the AI provider you choose — Anthropic (Claude Code), OpenAI (Codex), Cursor, xAI (Grok CLI), or whichever provider you configure in OpenCode — under your own subscription. Aiola never proxies, stores, or resells your code or model traffic. Threads, tasks, notes, and automations are stored locally (SQLite + plain files in your repo). If you use the optional analytics/logs/feedback layer for your shipped products, that telemetry is ingested via Aiola's cloud (Supabase/Tinybird). Offline: agent orchestration UI works offline; running agents requires provider access; GUI Lifetime keeps the local app opening even if Aiola's servers are unreachable.
Download Aiola