Orchestrate your coding agents across every project

Orchestrating coding agents means launching, watching and steering several agents at once. Track each agent’s work without losing project context. A single agent can plan and execute a multi-step repository change. Examples include Claude Code, Codex, Cursor, Grok CLI, OpenCode and Antigravity. Orchestration tracks the project, changes and next task for each agent. It helps you coordinate several agents at once.

Aiola is that layer. It runs Claude Code, Codex, Cursor, Grok CLI, OpenCode and Antigravity in a desktop app across projects. Keep your editor and provider access. Aiola never resells compute or adds API-key markup. It puts project tools beside the agents you already pay for. One workspace coordinates the work across terminal sessions.

Concretely, orchestration answers three questions at once. First, dispatch: which agent should take this task, and in which project? Second, isolation: how do you keep three or four agents working at the same time without their changes colliding? Third, decide how work continues when you step away. Use a schedule, task queue or agent with saved project context. A terminal can run one agent well. It can't answer those three questions for several projects. That's the gap an orchestrator fills.

Running coding agents across repositories creates coordination work alongside the coding tasks. Which project had which agent session? What did Codex change yesterday in the other app? Where's the task you meant to hand off before you closed the laptop? With bare terminals, that state lives in your head and across tabs. Each context switch adds work.

Orchestration solves the coordination problem:

• One window shows every project's active threads, recent changes, and pending tasks.
• Each agent runs in an isolated thread, so a fix in one repo never bleeds into another.
• Tasks and automations keep agents working on a schedule instead of only when you're watching the terminal.
• You choose the right agent for each job instead of being locked into one vendor.

Aiola combines agent sessions with tasks, schedules and a central project view. A terminal multiplexer like tmux provides parallel shells. A single-vendor GUI limits agent choice to that provider.

Aiola gives orchestration a set of concrete surfaces:

• Threads: each thread is an independent agent session with chat, diffs, branches, a terminal, and a built-in browser. Run several in parallel and place them side by side in split view or on a canvas whiteboard.
• Tasks that trigger agents: each project has a board where tasks launch coding agents. Results return for review without repeated prompting.
• Automations: schedule recurring triage, checks, and summaries. Reuse templates, inspect run history, and choose the cadence.
• Agents: reusable definitions with a role, skills, instructions, and memory. Each agent starts with saved project context.
• A central cross-project view shows work across repositories. App Logs, Analytics, and Feedback sit beside the coding work.

Pick the provider per thread or task. Run Claude Code on a refactor, Codex on a fix and Grok CLI on another task. View them side by side or on a canvas. Agents share one workspace, keeping diffs, branches and task results available for review or the next agent. The result stays accessible after you close the terminal scrollback. That's orchestration you can actually see and control.

Aiola orchestrates Claude Code, Codex, Cursor, Grok CLI, OpenCode, and Antigravity from a single app, on your own subscriptions. Different agents can suit refactors, quick fixes or unfamiliar codebases. No single agent wins every task. One window lets you choose an agent for each job instead of relying on whichever provider a GUI supports.

Aiola runs agents on your machine against your repositories. Bring existing Claude Code, Codex, Cursor, Grok CLI, OpenCode or Antigravity access. Your code is never uploaded to Aiola. Prompts and file context go only to the AI provider you choose. There is no cloud runner, no compute resale, and no token markup. Threads, tasks, notes, and automations are stored locally. Optional analytics, logs, and feedback telemetry is ingested through Aiola's cloud.

Read more about how Aiola keeps your data yours.

Aiola is free to download. Pro starts at $24/month or $240/year, including 100k events. GUI Lifetime costs $49, $89, or $129 as a one-time payment. Hosted Analytics, App Logs, Feedback, hosted MCP and Setup Health need Pro or a trial; GUI Lifetime excludes them. The 7-day trial requires a card.

Automations run locally while Aiola is open and the desktop is on and awake.

Aiola runs on macOS 12 or later (Apple Silicon and Intel) and Windows 10 or later (64-bit). The integrated workflow is available on both supported desktop platforms. The Android companion is available on Google Play. Aiola for iPhone is available on the App Store. When you're ready, just download Aiola and point it at your projects.