Agent Studio Coming Soon

Run Claude agents in a desktop workspace

Agent Studio is a native desktop app for running, scheduling, and managing Claude-powered agent conversations.
Keep tool approvals, project context, skills, usage, and audit history in one focused workspace.

Available for macOS and Windows.

Agent Studio desktop workspace

Built for real agent work on your computer

What is Agent Studio?

Agent Studio brings Claude agent conversations, tool calls, approvals, scheduled tasks, project context, skills, usage tracking, and audit history into one native desktop workspace.

Run agents with context

Start chat-style agent runs that stream responses, reasoning, tool calls, and task history inside a focused desktop app.

Approve tool use safely

Review tool calls before they run, choose permission behavior, and keep sensitive actions visible.

Schedule recurring work

Create repeatable agent workflows for daily briefs, weekly reviews, inbox triage, and repository watches.

Customize with skills

Shape how Agent Studio works with you through projects, instructions, skills, connectors, plugins, and agents.

Why use Agent Studio

Agent Studio is designed for knowledge workers who want Claude to do real work while keeping context, approvals, and history organized.

Group conversations by project, carry instructions forward, and keep recurring workflows close to the work they support.

How Agent Studio fits your workflow

Start with Claude access, add project context, then run or schedule agent work from the desktop app.

1

Connect Claude

Add your Anthropic API key or compatible endpoint, then choose the default model for new conversations.

2

Create a project

Add instructions, memory, files, and context so the agent understands the work before it starts.

3

Run or schedule agents

Start a task immediately, approve tool calls as needed, or turn repeatable prompts into scheduled workflows.

4

Review the record

Track task history, usage, approvals, and audit events so agent work stays understandable after it finishes.

Agent Studio core features

Built on the Claude Agent SDK, a Tauri desktop shell, and a Bun sidecar, Agent Studio keeps agent runs, approvals, schedules, and records in one local workspace.

Agent conversations

Streaming responses, reasoning, tool calls, and replayable task history for long-running Claude agent work.

Human approvals

Approval cards for mutation tools, backed by workspace sandboxing, allowed tools, and destructive-command guardrails.

Scheduled tasks

Run recurring work such as daily briefs, weekly reviews, inbox triage, and repository watches.

Projects and context

Group project instructions, memory, local folders, links, scheduled tasks, and related conversations.

Skills and customization

Shape the app with personal skills, built-in skills, connectors, plugins, and agent configuration.

Usage and audit

Track token and cost signals, tool activity, approvals, and redacted audit events with local event history.

Built around concrete product capabilities

No inflated customer counts or unsupported claims — just the facts Agent Studio is designed around.

2 desktop platforms: macOS and Windows

2

desktop platforms: macOS and Windows

3 runtime layers: React UI, Tauri shell, Bun sidecar

3

runtime layers: React UI, Tauri shell, Bun sidecar

1 workspace for tasks, projects, schedules, usage, and audit

1

workspace for tasks, projects, schedules, usage, and audit

Workflows Agent Studio is built for

Use Agent Studio wherever Claude needs context, tools, approvals, and repeatable execution.

Watch repositories, summarize failures, prepare maintenance notes, and keep review context in one project workspace.

Engineering teams, Repository workflows

Engineering teams

Repository workflows

Schedule daily briefs, weekly reviews, inbox triage, and status summaries without re-running the same prompt by hand.

Operators, Recurring briefs

Operators

Recurring briefs

Use projects, files, memory, and skills to keep multi-step research tasks grounded in the right context.

Researchers, Long-context work

Researchers

Long-context work

Work with reports, spreadsheets, slide outlines, summaries, and other outputs while keeping the agent process visible.

Knowledge workers, Document workflows

Knowledge workers

Document workflows

Prototype permission-aware agent workflows with real tool calls, reusable skills, and auditable execution history.

AI builders, Agent prototyping

AI builders

Agent prototyping

Turn repeated personal workflows into scheduled agent runs while keeping approvals and always-allowed tools under your control.

Power users, Personal automation

Power users

Personal automation

Frequently asked questions

The essentials before you start using Agent Studio.







Bring Claude agents into a focused desktop workspace

Run agent conversations, approve tool use, schedule recurring workflows, and keep project context organized.

Agent Studio