OpenAgentFleet · open-source public alpha v0.3.1

Give your agents a computer you can watch.

A local-first Mac, Linux and Windows app for agents that do real work in a separate Linux computer. Chat with them one-on-one or as a group, watch every step, approve the sensitive ones, and take over whenever you need to.

  1. Choose an engine Grok Build, Codex App Server, OpenCode, or optional Pi.
  2. Watch the separate computer Browser and desktop work runs in its own Linux guest.
  3. Take control Stop, approve, or take the controls yourself.
  • Local workspace
  • Observable computer
  • Human in the loop
OpenAgentFleet
The OpenAgentFleet workspace on macOS: an agent list on the left, a chat inviting you to give OpenAgentFleet a job, and an Agent Computer panel on the right with a Start Agent Computer button. The composer shows Grok Build with Grok 4.6 as the lead.
Your computer · in view
  • Watch
  • Stop
  • Take control
  • Approve

Next version · preview, not in 0.3.1

A brief they share, and memory you approve.

The clips and screenshots below are recordings of a preview build running sample data. None of this ships in the 0.3.1 download. Both clips are silent, and neither one runs a provider or publishes anything to GitHub. The code is in an open pull request against main and can still change.

Projects & briefs · Linux preview build
Preview build · sample data The clip creates a project, adds a member and assigns it to a conversation. A project holds one brief that its agents share; editing the brief appends a version rather than overwriting it.
Task result & memory review · Linux preview build
Preview build · sample data The clip opens a finished task and accepts an edited memory. Every run keeps its brief and its saved answer, and a memory an agent proposes waits in the review dialog until you accept it.
Preview build: the projects panel with a named project, its brief and the agents assigned to it.
Projects · one brief, shared and versioned
Preview build: the tasks list with a completed run and its saved answer.
Tasks · every run with its brief and saved answer
Preview build: the review dialog with a memory an agent proposed, waiting to be edited, accepted or rejected.
Memory · agents propose, you accept or reject

Also in the pull request, not shown in the clips:

The workflow

Four steps from a fresh install to a working agent.

The actual setup screens of the current alpha. Nothing turns itself on.

OpenAgentFleet setup
Setup step 1 of 4, Choose who runs your agents: a picker offering Grok Build, Codex App Server and OpenCode as the workspace lead, with notes on local control and open choices.
Step 1 of 4 · interactive current alpha capture

Agent Computer

A separate computer you can watch.

Browser and desktop work happens on a separate Linux computer, not on the host’s own desktop. Its screen sits in the app, in plain sight, started only when a job needs it. A Pi engine does not receive Computer MCP.

Chromium

Browsing, sign-ins and downloads happen there — never in your own browser.

Terminal

Command-line work runs on that computer, against its own files.

Files

What the agent fetches and edits stays there until you decide to take it out.

Your hand on the wheel

Watch it live, stop the run at any point, or take over the session yourself.

Agent Computer · live
OpenAgentFleet Computer View showing a live isolated Linux desktop with Chromium, Terminal and Files available for the agent or human takeover.
Real alpha capture · isolated local workspace desktop ready

Capabilities

What the current build actually does.

Tune the agent computer
The default computer starts with 4 GiB of RAM and 25 GiB of disk. Adjust CPU, RAM, disk and swap for the job, choose Ubuntu 24.04 by default or Ubuntu 26.04 / Debian 13, with a host-space guard and no shrinking of an existing larger disk.
Named agents, local memory
Each agent keeps its own role and memory on your computer. You can review, edit or archive what it remembers.
Group chat and teamwork
Put several agents in one conversation, or mention a teammate from any chat. Agent-to-agent collaboration is opt-in per agent, allowlisted and depth-capped — handoffs happen in the chat where you can see them.
Approval rules you can save
Approve once, keep the decision: a saved rule covers exactly that agent, that resource and that operation — nothing broader.
Four engines, one workspace
Grok Build is the default. Codex App Server, bundled OpenCode and optional Pi are selectable. Pi signs in with pi /login and has no Agent Computer. Picking a Grok or GPT id in Pi still runs through Pi, not Grok Build or Codex.
Approvals for sensitive actions
Sensitive and external steps wait for your explicit yes. Passwords, two-factor codes and payments stay with you, on the host.
Settings that match your eyes new in 0.3.1
Paper, Ink, Forest or Dusk accents, roomy density, 85–135% text size, soft or sharp corners and a reduce-motion switch. The Agent Computer’s CPU, RAM, disk, swap and OS image sit in Settings rather than behind an Advanced block.
Private phone control optional
An Android companion with Chat, Computer, Routines and Settings screens pairs by QR over a private, encrypted connection such as Tailscale. The desktop stays the execution host. Off by default, and there is no store build yet.

Trust

Where the boundary actually is.

What stays on your computer

Conversations, agent memory, attachments and the approval record are stored by the local OpenAgentFleet service. Only what you choose to send to an engine leaves the machine — through that provider’s own CLI and your own account. Pi credentials stay in ~/.pi.

What the Agent Computer is — and isn’t

The Agent Computer is the boundary for browser and desktop work: a separate Linux machine whose screen you can always watch. It is not full provider-process isolation — the engines’ CLIs themselves currently run on the host (macOS or Linux). Sensitive input stays on the trusted host. On Linux the Computer uses Docker Engine, not Colima.

v0.3.1-alpha

Download the alpha, on Mac, Linux and Windows.

OpenAgentFleet is open source and in public alpha. Version 0.3.1-alpha ships as a signed, notarized DMG for Apple Silicon (SHA-256 570731b921b64da9ee2d94d35467b6388372b48146e8270eb1642c9309209f02), plus unsigned Linux .deb, .rpm and .AppImage packages and an unsigned Windows installer. Every checksum is in SHA256SUMS on the release page. It is an alpha in the honest sense: not feature-complete, not production-ready. Intel Macs are not supported.

  • Apple Silicon Macsigned, notarized 0.3.1 DMG; Gatekeeper was verified on the build host, not on a second Mac
  • Linux & Windowsunsigned 0.3.1 packages: .deb / .rpm / .AppImage and an NSIS installer; Docker is recommended and the installer does not start it
  • Bring an engineGrok Build is the default; Codex, OpenCode or Pi if you have them

FAQ

The useful answers, when you need them.

A few plain-language boundaries for the current alpha. The full setup and troubleshooting guide lives in the repository.

Is OpenAgentFleet a cloud service?

The workspace, memory and Agent Computer run on your computer. Your selected provider may still send prompts to its own remote AI service.

What is the Agent Computer?

A separate Linux desktop with Chromium, Terminal and Files. You can watch it, stop it or take control when a human needs to handle a sign-in or sensitive step.

Is the whole agent isolated from macOS?

Not yet. The Linux computer is the browser and desktop boundary. Provider CLIs currently run as normal processes on the host (macOS or Linux).

Do I need Grok or Codex?

No. Grok Build is the default. Codex App Server, bundled OpenCode and optional Pi are selectable. Pi needs the pi CLI and pi /login. It has no Agent Computer and no search MCP.

Is there a Linux or Windows desktop app?

Yes. v0.3.1-alpha packages unsigned .deb, .rpm and .AppImage for Linux and an unsigned NSIS installer for Windows. Docker is recommended for the Agent Computer and the installer does not start it. One caveat before you install on Windows: Computer View on Docker Desktop with WSL2 failed live QA during the 0.3.1 release check.

Can several agents work together?

Yes. Group chats and teammate mentions have been in since 0.3.0. Collaboration is off until you enable it on an agent, partners are allowlisted, chains are depth-capped, and every handoff is visible in the chat.

Can I use the app from my phone?

Yes as an optional remote-client path. The desktop host stays the execution host and the phone pairs by QR over a private network such as Tailscale. There is no Play Store or App Store build yet.

Can I use projects, task retries or the GitHub review flow today?

No. Projects, shared briefs, task retry and revise, reviewed memory proposals and the GitHub issue-to-draft-pull-request flow are in an open pull request, not in the 0.3.1 download. The clips in the next version section were recorded on a preview build with sample data.