Claw FleetAdd a thought. Keep moving.
Send a follow-up while a Fleet task runs, or continue the conversation once it stops. Your work stays with the project.
Give it the work.
Make the calls.
Take the results.
Your personal AI workspace.
Bring Claude Code, Codex and dsh together. Move work forward by project, review what needs your judgment, and keep the results within reach.
Download Claw FleetSee the workflow Free & open source. Bring your own AI tools and accounts.
Start with a task. Or just a conversation.
Choose a project and an AI tool. Add the context, give it a direction, and come back to the same workspace to continue.
The material belongs beside the decision.
Look at a proposal, image or document, then give the task its next direction. Questions and answers stay connected to the work.
A result you can open, keep and share.
Browse deliverables by project. Preview documents and media, add a note, save a favorite, or export the file.
Current interface · Illustrative data
Keep the whole
piece of work together.
The project, the conversation, the next decision, and what came out of it.
Make an informed call.
Review the material an agent brings back: a proposal, an image, a document. Choose a direction without reconstructing the whole conversation.
Put the result to use.
Open a deliverable, export it, and return to it later. Keep reusable conclusions in a versioned project wiki.
Current mobile interface · Illustrative data
Away from your desk.
Still part of the work.
An idea doesn’t have to wait until you get home. Start a task from your phone, choose the project and device, and come back when a decision needs you.
- Type a brief, or edit a voice transcription.
- See tasks and decisions from paired devices together.
- Preview, download or share supported deliverables.
Give the next step
somewhere to go.
For the work that takes more than a conversation.
Projects, not loose threads
Keep tasks with their workspace. Reach project files, Git and a terminal when you need to look closer.
Knowledge you can reuse
Find a previous report, check its version and reference it in the next task.
Work that can continue
Use plans and handoff briefs for longer tasks. Schedule recurring work, or wait for a condition before continuing.
Claude Code, Codex, and dsh
Choose the tools and models you already use. dsh can connect to configured model providers. Each tool keeps its own account and access requirements.More of the workspace.
48 capabilities, grouped by how you use them. Open a section when you need it.
Start and continue
6 capabilities
Three agent tools
Use Claude Code, Codex and dsh in one workspace.
Model and reasoning controls
Choose an available model, reasoning effort and permission mode.
File and image context
Attach source material and reference images to a brief.
Follow-ups while work runs
Add another instruction without waiting for the task to finish.
Task tabs
Move between tasks while keeping each conversation in place.
Cross-session search
Find previous work by title, plan or conversation text.
See the work as it happens
6 capabilities
List and gallery views
See multiple sessions and their current states together.
Live activity
Distinguish thinking, tool execution, output and waiting for input.
Full conversation timeline
Inspect thinking, tool calls and code changes.
Subagents and workflows
Follow parent sessions, subagent work and workflow relationships.
Interrupt and stop
Take control of a stuck or no-longer-needed session.
Session organization
Rename, mark and filter sessions to keep useful work easy to find.
Keep a person in the loop
6 capabilities
One decision queue
Handle questions, permissions and plan approvals together.
Materials beside the decision
Review documents, images and HTML previews alongside a decision.
Options and structured forms
Use single choice, multiple choice, free text and form fields.
Pre-execution guard
Review risk analysis before supported commands run.
Editable plan approval
Read and edit a proposed plan before approving it.
Decision history
Keep questions, choices and feedback for later review.
Keep longer work moving
6 capabilities
Durable plans and task trees
Track phases and keep the plan with the work.
Context handoffs
Start a successor session with a handoff brief.
Visible handoff chains
Trace the sessions that carried a piece of work forward.
One-time schedules
Start a task at a specified time.
Recurring tasks
Repeat checks or routine work on a schedule.
Condition-based runs
Wait for an event and run the agent only when the condition is met.
Keep the output and the knowledge
6 capabilities
Multi-format previews
Preview PDFs, Office files, images, video and web documents.
Export deliverables
Download finished files or hand them to someone else.
Favorites, notes and project filters
Organize deliverables without relying on filenames alone.
Project wiki publishing
Keep reusable HTML reports and Markdown documents.
Wiki search and cross-links
Search full text and reference conclusions across documents and sessions.
Document version history
Update a document while keeping earlier versions available.
Connect projects and devices
6 capabilities
File explorer
Browse project files, images and source code.
Git status and diffs
Inspect changes and pull or push from the interface.
Terminal and processes
Run commands and inspect terminal output and process state.
SSH workspaces
Connect projects and agent environments on another machine.
Browser access and self-hosting
Run Fleet Web UI on your own always-on machine.
QR pairing and multiple devices
Pair a phone with desktop Fleet and switch between devices.
Understand usage and execution
6 capabilities
Account quota windows
See supported account quotas and reset windows.
Tokens and estimated cost
Review per-session consumption and estimated totals.
Live speed and spend trends
Watch output speed and changes in spend.
Daily work reports
Summarize sessions, output and work that needs attention.
Command auditing
Review executed commands by risk category.
Environment setup and diagnostics
Check installation, versions, sign-in and tool availability.
Make it work your way
6 capabilities
Skill browsing and sync
Inspect skills and synchronize them across supported tools.
Plugins and marketplaces
Browse, install and manage plugin sources.
Memory rules and history
Inspect project memory, revision history and rule scope.
Start and review from a phone
Start tasks, add instructions and answer decisions from a phone.
Voice transcription and image input
Turn speech into editable text and add images to a brief.
Notifications, sounds and speech
Choose how Fleet gets your attention.
Your next project
starts here.
Install the desktop app, connect your AI tools, and give your next piece of work a home.
Screens show the current development interface. Downloads below are the latest stable release; mobile layout may differ.
GitHub downloads are available now. A China mirror will appear here when it is enabled.
Release notes & all downloads
On Linux, download the binary for your processor, then run:
chmod +x fleet-linux-x64
./fleet-linux-x64 webuiOpen http://127.0.0.1:4571 in your browser. For ARM64, replace x64 with arm64 in both commands.
Get your workspace ready.
Connect your AI tools
Use Settings to check or install supported tools, then sign in or configure their provider credentials. Model subscriptions and API usage are separate.
Give it the first brief
Choose a project, or start in chat mode. Add context, pick your tool and model, and describe the work.
Take it with you
Enable Mobile and pair your phone. Keep the machine running Fleet online so you can reach its tasks and decisions.
A few things to know.
Which AI tools can I use?
Fleet connects to Claude Code, Codex and dsh. Install and configure the tools you want to use. dsh can select models from configured providers; availability depends on those providers and your credentials.
Is it free?
Claw Fleet is free and open source under AGPL-3.0. Your AI tools, model subscriptions and API usage are separate. Usage costs shown in Fleet are estimates.
Does my computer have to stay on?
The machine running the task must stay online. If your phone is paired with Fleet on your computer, keep that computer and Fleet running. You can also deploy fleet webui on another machine that stays online.
Can I speak to it from my phone?
Voice input transcribes speech into text that you can edit before sending. Availability depends on your browser or device speech service and microphone permission. It is not a two-way voice call.
Are all results saved automatically?
The deliverables view contains files added by an agent or the artifact command. Supported files can be previewed and exported. Mobile relay previews have a 16 MiB limit; use the desktop for larger files.
What happens on a long task?
Fleet supports plans, handoff briefs, schedules and condition-based waits. Handoffs start a fresh session with a brief; they do not provide unlimited context. These workflows depend on setup and agent support.
Where does my data go?
Fleet monitors local session data. AI tools connect to their configured providers. Phone access uses a relay when paired with a desktop; self-hosting is also possible. Fleet does not include a model account or a hosted cloud workspace subscription.
How do I download in China?
When a China mirror is enabled, select it above. GitHub Releases remains the alternative. Mobile access currently starts from the pairing link in Fleet; these downloads do not include native mobile app packages.