swarmagents.codes
swarmagents.codes

swarmagents.codes

A company of autonomous agents on your models.

Decompose complex goals into parallel execution chains, optimize leverage, and ship software through a shared workspace — like Cursor for an entire engineering org.

Start building

Runs on your providers · Pure seat spawner · Shared blackboard

Same prompt · same model

What ChatGPT-style one-shot gets wrong — and SwarmAgents ships.

Not a different model. The framework: seats, verification gates, and repair. Measured on lfm2.5:8b-a1b-q4_K_M.

Prompt

Build a tiny static web UI. Create index.html (and optional app.js/styles.css if needed) such that:
1) The page title and a visible <h1> are exactly: SwarmAgents Counter
2) There is a button with id="inc" labeled Increment
3) There is an element with id="count" that starts at 0 and increases by 1 each click
Use plain HTML/JS only (no frameworks). Do not modify package.json or the test file.

One-shot chat

Like ChatGPT / Gemini — same model, single reply

Failed gates

Failed objective gates (npm test). No working index.html.

package.jsontest/ui.test.js

5.9s wall time

SwarmAgents

Same model · seats · gates · repair · world model

Passed gates

Passed gates. Shipped index.html + app.js that satisfy the contract.

index.htmlapp.jspackage.jsontest/ui.test.js

323.7s wall time

+100pp lift on this fixture

Fair test: identical prompt and model. Chat arm is one-shot completion. Swarm arm uses the production leaf executor with verification gates. “ChatGPT / Google” here means that product shape — not their hosted APIs.

Why it feels different

Built for thousand-step work, not one-shot chat.

Decompose anything

Time-scaled trees that deepen until the work is leaf-sized — then keep going.

Spawn a real team

Dynamic seats invent their own roles, own paths, and work concurrently like a company.

Share one workspace

Blackboard, heatmap, and context keep every agent oriented without you babysitting.