Open source · Apache 2.0

Live on DevHunt

AI agents you can leave
running overnight

AgentPlaza gives each agent its own sealed machine, checks every tool call against laws you write, and holds the spend to a budget. In the morning you read a signed record of what happened, and nothing you did not allow.

Install AgentPlaza free
Works with Claude Code, Codex and OpenCodeAny model: Claude, GPT, Gemini or localWindows, macOS, Linux and Raspberry Pi

NVIDIA Inception program memberBuilt by JUMPHASH, a member of the NVIDIA Inception program.

All projectsOverviewBuilder #211 waits on yout12

What should the plaza work on?

Orchestrator #200 plans the work and delegates it to the fleet · anthropic/claude-opus-5-5 · Ctrl+Enter to send

57k / 200k · 28%
Orchestrator #200 WorkingOpen transcriptclaude-opus-5-5
Start a project by talking it throughNew project
Open a project directlyNew project
Bring in a project that existsNew project
Agents105 working
Open tasks54 done
Worker modeldeepseek-flashdeepseek
Orchestrator modelclaude-opus-5-5anthropic
Waiting on you Approvals
Activity
AD
Orchestrator #200
Ada · plans the work and delegates it · claude-opus-5-5
Reply to the orchestrator…

The tour plays itself. Click anywhere in the console to take over.

Any model, any engine

Bring the models
you already pay for

Every major provider through one gateway on the hub, which adds the key from its vault, so no key enters a VM. Twelve coding engines run inside each agent's own VM, under the same laws as everything else.

Modelsthrough the hub's gateway, with the keys in its vault

  • Anthropic
  • OpenAI
  • Gemini
  • xAI
  • DeepSeek
  • Mistral
  • Kimi
  • GLM
  • OpenRouter
  • Bedrock
  • Azure OpenAI
  • Ollama
  • LM Studio

Coding enginesinside each agent's own VM · on by default

  • Claude Code
  • Codex
  • OpenCode
  • Gemini CLI
  • Qwen Code
  • Kilo Code
  • Cline
  • Copilot CLI
  • Goose
  • Kimi Code
  • Auggie
  • Mistral Vibe

The problem

A coding agent with your shell
is a stranger at your desk

On your laptop today

  • Runs commands as you, in your home folder
  • Holds your API keys in its environment
  • Spends until you notice the bill
  • Stops when you find the right terminal

In AgentPlaza

  • Runs in its own microVM, as nobody on your host
  • Reaches models through the hub; keys stay in the vault
  • Works inside a budget, paid from escrow per task
  • STOP ALL holds every agent at once

Your laptop stays yours

Each agent works inside its own microVM, with no network interface. Its commands never run on your host, and it never reaches another agent.

Nothing runs that a law does not allow

Every tool call is checked against laws you can read and change while the plaza runs. A call is allowed, refused, or sent to you to decide.

Spend you can cap, a stop you can press

Each project runs on a budget in dollars or tokens, paid from escrow when the work checks out. STOP ALL holds every agent mid thought.

Any model, and your keys stay home

Every major provider and 12 coding engines, through one gateway. Keys live in the hub's vault and never enter a VM.

One machine, or a fleet

Start on the laptop you have. Add servers and Raspberry Pis as nodes later, each with a single use join code.

How it works

From a goal to a landed change
in three steps

  1. 01

    Install with one command

    The installer checks every file against the release's SHA256SUMS. Start locally and nothing leaves the machine.

    $ curl -fsSL https://agentplaza.io/install.sh | sh
    ✓ every file checked against SHA256SUMS
    ✓ hub on 127.0.0.1:7700 · node ready
  2. 02

    Give the mayor a goal

    The orchestrator turns your goal into a plan, the planner writes the change, and the board hands each task to an agent in its own VM.

    What should the plaza work on?: The overview: the orchestrator's composer, its context, what waits on you.
  3. 03

    Approve what matters

    Risky calls wait for you. The plaza's own version control records every change with its intent, its review and its signature, then lands it.

    Approvals: Everything that waits on you, with the agent, the project and why.

See it run

The console, recorded
on sample data

Every flow below is the real web console against sample data. Each plays to its end, then hands over to the next.

Approve a held deploy. A release agent asked to deploy. The call waits on you; one click lets it run.

Every recording in the galleryHow the parts fit together

Proof

Checked on every change,
in the open

Every number here comes from the public repository and its CI. Read the code, run the suites, or watch a run.

4,011

tests run on Linux x86_64 for every change, beside Windows, macOS and arm64

3

acceptance suites: redteam, jail and killresume, against the containment rules

500

recent tool calls replayed by Check whenever you change a law

0

provider keys inside any agent's VM: the gateway adds them at the hub

Install

One command on Windows,
macOS, Linux or a Pi

Pick your system. The installer checks each file against the release's SHA256SUMS, then puts AgentPlaza in your menu and agentplaza on your PATH.

PS> irm https://agentplaza.io/install.ps1 | iex

Windows 11, or Windows 10 2004 and later, with virtualization on in firmware. x64 runs agents on the Windows Hypervisor Platform.

$ curl -fsSL https://agentplaza.io/install.sh | sh

Apple silicon runs agents through Hypervisor.framework. Intel Macs run the hub and the desktop app.

$ curl -fsSL https://agentplaza.io/install.sh | sh
$ sudo usermod -aG kvm "$USER"

apt, dnf or pacman where it can, the AppImage elsewhere. Agents run in KVM microVMs, so your user joins the kvm group.

$ curl -fsSL https://agentplaza.io/install.sh | sh
$ systemctl --user enable --now agentplaza-hub agentplaza-node

Pi 4 or Pi 5 with 64 bit Raspberry Pi OS and 4 GB or more. A Pi 5 with 8 GB runs about 10 agents.

All downloads and SHA256SUMSor build from source with cargo build --release

FAQ

What owners ask first

Is AgentPlaza free?

Yes. The hub, the nodes, the desktop app and the command line are open source under Apache 2.0. There is no account and nothing to subscribe to. You pay only your own model providers.

Can an agent reach my files or my network?

No. Each agent runs in its own microVM with no network interface. Its commands run only inside that VM, and its only link is vsock to the hub. The hub's egress proxy refuses loopback and private addresses, and records every connection.

Which models and coding engines work?

Anthropic, OpenAI, Gemini, xAI, DeepSeek, Mistral, Kimi, GLM, OpenRouter, and local models through Ollama or LM Studio. 12 coding engines run inside the agent's own VM; Claude Code, Codex and OpenCode are on by default.

Do I need a server or a GPU?

No. Start on the laptop you have: the hub and one node run there and nothing leaves it. Add machines later as nodes. A Pi 5 with 8 GB runs about 10 agents.

How do I stop an agent that goes wrong?

Press STOP ALL. It holds every agent mid thought, cancels the running work and refuses model calls until you resume. Then restart, wipe or retire the agent, or roll its VM back to a checkpoint.

What does it cost to run?

Only what your model providers bill. Each project and task runs within a budget in dollars or tokens, tasks are paid from escrow when the work is verified, and every model call is metered.

Why does Windows warn about the installer?

The MSI is not signed yet. In SmartScreen choose More info, then Run anyway. Every installer checks each file against the release's SHA256SUMS before it installs.

Can I use it from my editor?

Yes. Zed, JetBrains IDEs and Neovim drive plaza agents with agentplaza acp, and approvals come back to the editor. With a repo set, the work returns as a pull request.

Put your first agent
in a sealed machine today

Free under Apache 2.0. No account, nothing to subscribe to, and nothing leaves your machine until you host a hub.

Install AgentPlaza free
Loading video
0:00 / 0:00

Share the video