Sweet runs autonomous agent loops — it plans, writes, tests, and fixes its own work, running for as long as the task takes. No babysitting. No dead ends.
npm install -g @sweet-cli/sweet
Sweet doesn't suggest a line and stop. It holds the entire goal, breaks it into steps, and runs the full loop — catching failures, diagnosing them, and retrying — until the work is done.
Explores your repo, then writes a concrete step-by-step plan before touching anything.
Edits files, runs commands, calls tools — many steps, one coherent thread.
Runs your test suite, reads the output, and checks results against the goal.
When something fails, it diagnoses and retries — no babysitting, no dead ends.
/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.
/workfor 3h "build the payments integration"No browser, no dashboard. sweet "build me a REST API" and it goes to work right where your code lives.
Not autocompletes. Not chat messages. Sweet loops: plan → execute → verify → recover, over and over, for as long as you need.
Runs your test suite, reads failures, and fixes them. The task isn't done until the suite is green.
Flaky test? Wrong assumption? The agent catches it, figures out what went wrong, and keeps going.
Reads your conventions and follows them. No language-specific configuration needed.
Runs in your terminal. No repo storage on our servers. No training on your source.
Full agent, all languages. Model access through our relay — no API keys to manage.
Full agent. No credit card. Install and go.
More power for serious daily use.
Unlimited. For teams and power users.
One install. Every repo. No API keys needed. Start free, upgrade anytime.
npm install -g @sweet-cli/sweet