We use cookies for analytics (GA4) and marketing. Choose essential only or allow all.

Skip to content
Optamus Code 0.9.0 is now available for macOS, Windows and Linux.Get it now →
OOptamus

One keyEvery model

The AI software engineer for your desktop.

Optamus Code reads your repos, writes the code, runs the tests in a sandbox, verifies in a real browser, and opens the pull request. It runs on the Optamus API — one key that routes to gpt-4o, claude-3-5-sonnet, and every model in between.

MIT-licensed · releases on GitHub · agent backend: https://api.optamus.cloud/v1 · op- keys

optamus-code · task #a3f9 · dashboard dark mode
$ optamus --task "Add dark mode toggle to dashboard.tsx"
— plan —
▸ phase 1 — plan · reads 12 files · flags 2 risks
— edit —
+ dashboard.tsx +38 −6
+ const [darkMode, setDarkMode] = useState(false);
+ <Toggle checked={darkMode} onChange={setDarkMode} />
~ theme.ts +12 −0 // tokens added
▸ phase 2 — edit · 2 files touched
— run —
$ npm run test
✓ all 11 tests passed in 1.2s
▸ phase 3 — run · sandboxed shell
— open PR —
browser: toggle persists across reload
✓ verified · opening PR #4183
awaiting approval…
4 phases · 47s · 0.41M tokens · $0.0041
OpenAI-compatible · Bifrost gateway · 5-minute cache · per-key rate limits · PII redaction · circuit breaker

Three products, one gateway

Code, Coworker, and the API behind both

Optamus Code — the AI software engineer

Reads your repo, plans the change, edits files, runs tests in a sandbox, verifies in a real browser, and opens the pull request. Four phases · 47s · 0.41M tokens · $0.0041.

Explore Code →
optamus-code · task #a3f9 · dashboard dark mode
$ optamus --task "Add dark mode toggle to dashboard.tsx"
— plan —
▸ phase 1 — plan · reads 12 files · flags 2 risks
— edit —
+ dashboard.tsx +38 −6
+ const [darkMode, setDarkMode] = useState(false);
+ <Toggle checked={darkMode} onChange={setDarkMode} />
~ theme.ts +12 −0 // tokens added
▸ phase 2 — edit · 2 files touched
— run —
$ npm run test
✓ all 11 tests passed in 1.2s
▸ phase 3 — run · sandboxed shell
— open PR —
browser: toggle persists across reload
✓ verified · opening PR #4183
awaiting approval…
4 phases · 47s · 0.41M tokens · $0.0041
ai-coworker · session #7c2e
inbox — 3 drafts
1
spreadsheet — Q3
2
calendar
3
slides — review deck
4
planning 3 steps · waiting for approval

"Consolidate the Q3 numbers into the deck before the 2pm review."

AI Coworker — sees your screen

Watches your screen in real time, understands any application, clicks and types the way a human would — with approval gates on every sensitive action. Sessions recorded for replay.

See Coworker →

API Platform — one key

OpenAI-compatible gateway to GPT-4o, Claude, and 100+ open models — per-token billing, per-second features. POST /v1/chat/completions · GET /v1/models · 200 ok · 214ms.

Explore API →
api.optamus.cloud · request200 ok · 214ms
POST/v1/chat/completions
{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello"}],
"stream": true
}
Authorization: Bearer op-••••200 ok · 214ms · model gpt-4o
OpenAI-compatible · live OpenAPI spec · Stripe billing
1
API key for every provider
Bifrost gateway · api.optamus.cloud
op-
key prefix, minted in your console
app.optamus.cloud → API Keys
5
minute response cache
Bifrost gateway · request path
6
rate-card models across 2 families
usage_logs cost engine

From the blog

All posts →