Long-horizon agent

Expanding horizons.

Hours of autonomous work. Not the next token.

Sweet plans, executes, verifies, and recovers — running autonomous agent loops for as long as the task takes. No babysitting. No dead ends. Just shipped code.

~/project — sweet
npm install -g @sweet-cli/sweet
How the loop works ↓

Two Surfaces
CLI or browser. Same agent. Same autonomy.

Sweet runs the same autonomous loops whether you're in a terminal or a browser tab. Pick the surface that fits your workflow — or use both.

TERMINAL

CLI Agent

Runs where your code lives. One command from any repo. No browser needed.

Install CLI →
BROWSER
🌐

Web App

Zero install. Mobile-ready. Share sessions. Same agent, same autonomy, anywhere.

Open Web App →

The Agent Loop
Plan → Execute → Verify → Recover → Repeat.

Sweet doesn't suggest a token and stop. It holds the entire goal across a long horizon — breaking it into steps, running the full loop, catching failures, diagnosing them, and retrying — until the work is done.

01 · PLAN

Reads & plans

Explores your repo, then writes a concrete step-by-step plan before touching anything.

02 · ACT

Executes

Edits files, runs commands, calls tools — many steps, one coherent thread.

03 · VERIFY

Tests its work

Runs your test suite, reads the output, and checks results against the goal.

04 · ADAPT

Recovers & continues

When something fails, it diagnoses and retries — no babysitting, no dead ends.


The /workfor command
Set a horizon. Walk away.

/workfor puts the agent in a continuous work loop — it plans, executes, verifies, recovers from failures, and self-nudges for the full duration you set. It won't stop or idle until the timer expires. Think of it as a stop hook that never stops.

How it works

  • Type /workfor 3h "build the payments integration"
  • The agent enters a loop: plan → execute → verify → recover → repeat
  • It self-nudges — no idle time, no waiting for you to say "continue"
  • Each step is verified. Failures are diagnosed and retried automatically
  • When the timer runs out, it reports everything it shipped
  • You can message it mid-run to course-correct, check progress, or change priorities
~/project — sweet
$ sweet Loading project… > /workfor 2h "refactor auth module to use JWT" ⏱ /workfor — 2h 00m Working in a loop until the timer expires. ◆ 1/6 Audited auth flow, 4 endpoints ◆ 2/6 Wrote jwt.ts (86 lines) ◆ 3/6 Patched 4 route files ◆ 4/6 npm test — 1 failure ↳ token expired in test, refreshing… ◆ 5/6 Updated middleware chain ◆ 6/6 npm test — 22 passing 6 steps · 1 recovery · 1h 14m ✓ Done — ready to review

Features
CLI or browser.
Same agent. Same autonomy.
DUAL SURFACE

CLI or browser, same agent

Start in the terminal, check progress from your phone. Same session, same agent, same autonomy across every device.

AGENT LOOP

Autonomy measured in hours

Not autocompletes. Not chat messages. Sweet loops: plan → execute → verify → recover, over and over, for as long as you need.

SELF-VERIFYING

Tests before it calls it done

Runs your test suite, reads failures, and fixes them. The task isn't done until the suite is green.

SELF-RECOVERING

Fails, diagnoses, retries

Flaky test? Wrong assumption? The agent catches it, figures out what went wrong, and keeps going.

ANY LANGUAGE

Node, Python, Go, Rust, Rails…

Reads your conventions and follows them. No language-specific configuration needed.

ZERO INSTALL

Web app, instant start

No npm, no shell config. Open a browser tab and the agent is ready. Same full autonomy as the CLI.


Pricing
Start free. Upgrade when you need more.

Every plan includes model access through our relay — no API keys to manage. Usage is capped to your plan so there are never surprise bills.

No credit card
Free
~50K tokens / day
$0/forever

Ship real tasks today. 50K tokens daily, resets every 24 hours.

  • Full agent, all languages
  • 50K tokens daily
  • Resets every 24 hours
  • /workfor (up to 30 min)
  • No API keys needed
Get started free
7 days free trial
Pro
~2M tokens / month
$20/mo

For developers who ship with Sweet daily. 40× the free tier, unlimited loops.

  • Everything in Free
  • 2M tokens monthly
  • All available models
  • Unlimited /workfor loops
  • Priority throughput
  • Cancel in one click
Start Pro free
Power
Max
~20M tokens / month
$200/mo

For teams and heavy users who run Sweet around the clock.

  • Everything in Pro
  • 20M tokens monthly
  • 10× Pro capacity
  • Unlimited /workfor loops
  • Highest throughput priority
  • Cancel in one click
Go Max

Get started

Your terminal.
Your browser.
Expanding horizons.

Same long-horizon agent across every surface. Start free, no credit card.

npm install -g @sweet-cli/sweet