It only looks
Pleni never starts, stops, or types into a session, and it never changes the files it reads.
Pleni puts your Claude Code, Codex, Grok and Kimi Code sessions on one live map: who started whom, what each one is doing, and the work they hand to each other. It only reads the files those tools already write, and nothing leaves your computer.
Free and source-available. Windows, macOS and Linux, with Node.js 22.12 or newer.
Lines light up when work goes down to a helper and when a report comes back up. Pleni never moves a tile on its own, so things stay where you put them.
A session that asks a question, wants a plan approved, or waits for permission to use a tool shows Needs you. The notice stays at the top of the page until you answer it or dismiss it.
The list groups your sessions by project, with a filter for each state.
See each piece of work a session hands to a helper, and each report that comes back.
Filter to the work handed out, the reports back, or the errors.
Click a tile to see what the session is doing now, its recent steps, its AI model and effort, and who it reports to.
Drag a tile onto another to change who it reports to.
If your sessions pass work to each other through a shared mailbox folder, Pleni lists each task, its state, and the ones that need a look.
Screens from Pleni's demo. The sessions in them are made up.
Pleni never starts, stops, or types into a session, and it never changes the files it reads.
It opens only on your own computer and sends nothing anywhere. No account, no sign-in, no tracking.
Link your own devices privately with Tailscale, then open Pleni on your phone or laptop.
Say who reports to whom, and pick the titles you like: plain, military, or company.
npx pleni
No sessions yet? Run npx pleni --demo to look around with made-up ones.
Pleni only watches for now. Answering questions and approving plans from your browser is planned. To run it from the source instead, follow the Pleni guide.
Read the Pleni guide
Plenipo for Windows
Hire agents for the roles you need. A coordinator brings their work together across AI providers, with model and effort choices guided by policies you control.
Pleni watches the sessions you run yourself. Plenipo runs a team for you: it starts the workers, checks their permissions, and keeps a record of what they did.
Plenipo for Windows is no longer being updated. New work goes into Pleni. You can still download the last version, v1.28.0.
Free to start. Your AI tools use your own sign-ins. v1.28.0
Follow a sample website project from your brief to the coordinator, developer, reviewer, and writer. Explore their handoffs and make the next call.
Illustrated sample. No real AI runs, sign-in, or saved changes.
You ask for a clear services page. Development Manager plans the work. Website Supervisor coordinates a developer, reviewer, and writer. The team prepares a draft and review notes, then brings the decision back to you.
Sample conversation: “Where are we with the website?” — “The page draft is ready. The reviewer is checking the links and layout before we send it back to you.”
This is an illustrated website example, not the desktop app. AI tools and approval rules in the app depend on your setup.
Start as you would with a human team: choose roles, set responsibilities, and explain the result you want. Plenipo connects those roles to your AI tools.
Start with Plenipo's suggested role policies. Automatic agents use those policies to select from your available models, with an explanation of the choice.
Adjust model choices and reasoning effort for your organization, department, role, or agent. Set first choices, backups, and providers to exclude. Where you leave effort unset, the model or AI tool's default applies.
How model choices work
Give each role clear permissions and project folder limits.
Actions set to ask wait for your approval. See what a worker wants to do, then approve or deny the request.
Learn about permissions
Follow your team's work through its activity, results, and approvals.
Your activity record stays on your PC, so you can return to the details behind a result.
Explore the product
You set the outcome. The coordinator connects the work.
FOR EXAMPLE: BUILD A SERVICES PAGE
Give your supervisor a brief: “Build a services page for our website.” Hire a developer to implement it, a reviewer to check it, and a writer to document it. The supervisor coordinates their tasks and brings back the changes and findings.
Your policies could put the developer on Claude Code and the reviewer on Codex, with a different effort level for each. The roles stay the same when you change the model choices. You review the result and decide what happens next.
Illustrative workflow. Available models and actions depend on your connected tools and permissions.
Bring your supported AI tools together, using your own sign-ins.
Claude CodeAnthropic
CodexOpenAI
GrokxAI
KimiMoonshot AI
Also works with Ollama cloud models for text conversations.
A coordinator delegates to the team's roles and receives their results. Workers can use different AI providers within the same project.
For a second perspective, set a review policy to prefer or require another provider. Permissions, approvals, and the activity record stay under your control on your PC.
AI requests still go to your selected AI company. Its plan and usage limits apply.
Explore supported AI tools
Follow the code, run commands, and inspect the result alongside your agents.
Development work uses Git branches and working copies, with changes and review findings brought back together.
Open your own terminal on your PC or a configured Linux or Unix server, beside the team's work.
Follow a worker's file changes in the read-only Watch view. Streaming detail depends on the AI tool.
Inspect changes, test results, approvals, and task history before deciding the next step.
Start with Free. No account or card needed.
Paid plans add room for your business and your clients.
| Free | Pro |
|---|---|
| 1 organization | 3 organizations · more with Partner |
| 1 department · 1 project | Unlimited departments and projects |
| 3 workers at a time | 4 workers at a time in each organization |
| Development department | Development and business departments |
| All supported AI tools | All supported AI tools |
| All permissions and safety controls | All permissions and safety controls |
These limits ship from v1.18. Paid purchases are not open yet.
View Pro and Partner plans.
Compare all edition features
Create an account or manage your account. An account is optional for Free.
Plenipo for Windows
This release turns the GitHub connection on. When you set up a project, you can now pick its repository from a list of your own. Plenipo by 8 West Ventures, LLC.
See the sessions you already run, live in your browser.
Windows, macOS and Linux · Node.js 22.12 or newer
What Pleni reads, and what it never doesHire a team of AI workers and give it a goal. No longer being updated.
Windows 11 · x64 · v1.28.0
Read the terms of service and privacy statement before using Plenipo.
Release notes and other downloadsUse Pleni if you already run Claude Code, Codex, Grok, or Kimi Code yourself and want to see all your sessions in one place. It only watches, and it works on Windows, macOS, and Linux. Plenipo for Windows, an app that hires and runs a team of AI workers for you, is no longer being updated: new work goes into Pleni, and the last Windows version stays available to download. Both are made by 8 West Ventures, LLC.
You add an AI agent to a role in your organization, with responsibilities, instructions, and permissions. Like staffing a team, you decide what the role is there to do and who it reports to. A supervisor coordinates the work; the connected AI model performs it.
Automatic agents follow model policies. Plenipo supplies starting role preferences, such as preferring another provider for code review. You can adjust choices for the organization, department, role, or individual agent, or fix an agent to a particular tool and model. Selection considers your rules and tool availability, and records why a model was chosen. Supported effort levels follow your settings, then model or tool defaults.
Yes. Free needs no account or card and includes one organization, one department, one project, and three workers at a time. Pro and Partner increase those limits; paid purchases are not open yet. See the account site for plans. Your AI tools use your own accounts; their subscriptions and usage limits are separate.
No. Plenipo runs on your PC and keeps its permissions, approvals, and activity record locally. AI requests go to the AI companies you choose, so supported cloud tools need an internet connection.
The current installer supports Windows 11 on x64 PCs. Check the latest release for available downloads and release notes.
A worker can do the things allowed by its role's permissions and project folder limits. Actions set to ask wait for your approval; blocked actions stay blocked. Optional settings can allow sending, buying, or signing in without asking on allowed websites. These settings start off. You can review requests, revoke permissions, take over, or stop work from the app.
Yes. Plenipo is source-available under the Elastic License 2.0, and so is Pleni. You can read the source, build it, and change it for your own use, subject to the license terms.