FREE DOWNLOAD · RUNS ON YOUR COMPUTER · YOUR OWN API KEYS
Agents FairAGENT STUDIO Get Agent Studio ↓

ONE BRIEF. THREE AGENTS. NO COPY-PASTE.

Agents that
check each other.

Give one task. A Planner sets the criteria, a Worker produces it, a Reviewer finds the errors and sends it back — automatically — until it passes.

Works with Claude, GPT and Gemini. Mix vendors so the reviewer is never grading its own work. Runs on your computer with your own API keys; nothing is uploaded to us.

Windows · macOS · Linux · needs Node.js 24 · no account · no telemetry

THE LOOP
PLAN.
MAKE.
REVIEW.
01 PLANNER02 WORKER03 REVIEWER

Issues go back to the Worker.
Repeat until it passes.

Up to 6 review roundsEvery draft and review keptExport the full recordMCP server built in

HOW IT WORKS

Five minutes from download
to a reviewed deliverable.

Demo mode shows the whole loop with no key and no cost. Add keys when you are ready.

01SETUP

Download & double-click

Unzip, run the start file, your browser opens. No installer, no admin rights.

02DEMO

Watch the loop

Synthetic agents plan, draft, get sent back and pass — so you see exactly what to expect.

03KEYS

Add your API keys

Anthropic, OpenAI or Google — one or all three. Encrypted on your machine, verified with a tiny test call.

04RUN

Write the brief

Paste any facts as material. Pick which vendor plays which role. Press run.

05RESULT

Read the final version

Every issue found and fixed is on screen. Accept, copy or export with the full record.

DOWNLOAD

Get Agent Studio.

Free · open source · v1.0.0

1 / Download

One zip for every platform. About 300 KB.

Download agentsfair-agent-studio.zip ↓

Requires Node.js 24+ (free). Then: Windows → start-windows.cmd; macOS → start-macos.command; Linux → start-linux.sh.

2 / Optional: hear about updates

Also an MCP server

Your chat assistant can hand a brief to Studio and fetch the result — no copy-paste. Add the bundled studio-connector.mjs to Claude Desktop, Cursor or any MCP client; the guide inside the app has the exact configuration.

What it does not do

No browsing, files, email, payments or publishing — agents only write and critique text. It does not control other apps on your computer. It does not guarantee correctness; verify facts before use. Provider charges go to your own accounts.

FAQ

Questions people ask first.

Is my data sent to Agents Fair?

No. Studio runs on your computer. The only outbound requests are the model calls you authorise, straight to the provider you chose. If you give us your email above, that is the only thing we receive.

How much does a run cost?

Nothing to us. Providers bill your own API accounts; a typical three-round job makes five to seven model calls. Demo mode is free.

Can it replace my own checking?

No. A second model catches many mistakes, especially when it is from a different vendor, but not all. Treat the result as a strong draft with a built-in review, and verify facts.

Which models?

Any model name your provider account can access. Defaults are set for Claude, GPT and Gemini and can be changed in settings.

中文用户?

程序内含完整中文说明(Guide / 中文说明),安装、加 Key、运行、接入 Claude/Cursor 都有逐步指引。