YOUR AGENTS. ONE CONTROL ROOM.

Give your coding agents
a clear direction.

Turn a task plan into a controlled delivery workflow. Run your chosen agent, check the result, review the changes, and see exactly where the work stands.

Local orchestration · Explicit providers · Visible checks

Agent Maestro / Task workspaceDEMO DATA
Current Agent Maestro task workspace in dark mode, with task statuses and plan controls
Real application interface. Sample plan and results.Click to enlarge ↗

01 / A CLOSER LOOK

The whole run,
in plain sight.

From current activity to the final report, inspect the actual interface. Every screen below uses the application's built-in sample API.

Fresh captures of the current React application · Dark appearance · Demonstration data, no live provider execution

02 / THE DELIVERY PATH

One task. Clear gates.
Then the next.

Each task starts a new provider session. Fixes stay in that task's implementation session, with checks and optional review before moving on.

  1. 01

    Plan

    Define ordered tasks, the repository, provider, and execution limits.

  2. 02

    Implement

    The selected coding agent works in a dedicated task session.

  3. 03

    Validate

    Run configured checks and return failures for correction.

  4. 04

    Review and fix

    Optional independent read-only review and bounded remediation.

  5. 05

    Finalize

    Apply your Git mode, mark the task done, and continue the plan.

When review requests changes, the task returns for a fix, validation, and another review within configured limits. Optional final review and validation cover the completed plan.

03 / BUILT FOR SUSTAINED WORK

More control.
Less guesswork.

Keep execution, evidence, and delivery state together as your agents work through a plan.

↗

Current activity

Track running work and plans needing attention. Open the active task directly from Home.

≡

Persistent task history

Inspect saved execution evidence after a restart, with expandable event details and paged history.

✓

Readable reports

See structured changes, verification, review findings, and fix claims alongside their task state.

⌘

Versioned workflows

Start with Fast, Standard, Strict TDD, Debug, Autonomous, or an explicit custom skill selection.

⑂

Git on your terms

Choose no Git action, commit-only, or non-force commit-and-push after successful gates.

◎

Usage and limits

Inspect recorded token usage and coverage. Set attempt limits and plan token budgets.

YOUR WORKSPACE, YOUR VIEW

Light, Dark, and System appearance. Responsive activity cards and task details for desktop and mobile.

04 / EXPLICIT PROVIDER CHOICE

Bring your coding agents.

Choose implementation and reviewer providers separately where their roles are supported. Agent Maestro never silently switches providers.

OC

OpenAI Codex

Implement + review

CC

Claude Code

Implement + review

GC

GitHub Copilot CLI

Implement + review

GM

Gemini CLI

Implement + review

AG

Antigravity

Implementation only

Use compatible installed and authenticated CLIs with your own account and model access. Antigravity cannot enforce the required read-only reviewer boundary.

Local orchestration.
Durable state.

A Java 21 / Spring Boot application, React interface, and local SQLite persistence. Plans, settings, review history, Git results, and recorded usage stay connected.

Selected provider CLIs may send prompts, code context, or files to external services according to their own configuration. Resume requirements vary by provider.

05 / WATCH THE WORKFLOW

See Maestro in motion.

Watch on YouTube ↗

THE PRACTICAL DETAILS

Before you start.

Have a specific workflow in mind?
Let's talk ↗

Does Maestro include coding-agent accounts?

Agent Maestro orchestrates installed provider CLIs. You supply compatible installations, authentication, subscriptions, model access, and credits.

Can I use a different agent for review?

Yes. Implementation and independent read-only review can use different providers that support the selected roles. Antigravity supports implementation only.

What happens when a check or review fails?

Validation feedback and review findings can return to the existing implementation session for a bounded fix. The result goes through configured validation and review again.

Does a structured report mean the task is approved?

A provider report, validation, reviewer approval, and task completion are separate states. Rendering structured output does not approve a task. A reported fix awaits reviewer confirmation, and passing gates does not guarantee correctness.

Can I inspect history after a restart?

Persisted task evidence remains available through the execution timeline. The timeline reconstructs recorded events; it is not a log of every transient checkpoint. Provider-session resume has provider-specific prerequisites.

Does it work with local repositories?

Yes. Agent Maestro runs against your selected repository and keeps orchestration state in local SQLite. Provider CLIs communicate with their external services under their own settings.

MAKE THE NEXT TASK A CLEAR ONE

Put your agents
on the same page.

Request a walkthrough ↗ygrikk1@gmail.com