Autonomous AI agent · Your terminal · Your rules

The AI engineer that ships
while you sleep.

Sweet runs on autopilot in your terminal — reads your codebase, plans the work, edits files, runs commands, writes tests. Give it a goal and come back to a PR.

$ npm i -g @sweet-cli/sweet
🎁 3-day free trial for every new account. Credit card required.
Start Free Trial Read the Docs

$ sweet start
One command from idea to shipped code
$1.30
to build a complete auth system with tests
3 days
free trial — full features, cancel anytime

Autonomous agents in your terminal.
Subscribe. Install. Ship.
Sweet works directly in your terminal. Subscribe to Pro or Max — both start with a 3-day free trial. Cancel anytime. We use cost-efficient models and pass those savings to you.
Step 01

Describe the outcome

Tell Sweet what you want to ship — a feature, a refactor, a bug fix, a migration. Plain English is fine.

Step 02

Sweet works autonomously

It reads your repo, makes a plan, edits files, runs commands, and iterates until the task is done. No hand-holding needed.

Step 03

Review what was built

Come back to a diff, passing tests, and a clear summary of what changed and why. Merge or ask for changes.


Real session
Watch it work.
Sweet reasons through the problem, uses tools to explore your codebase, writes the code, and runs the tests — all in one pass.
sweet — building auth system
build a JWT auth system with login, register, and protected routes

read_file package.json, src/routes/index.ts, prisma/schema.prisma read_file src/middleware/*, src/models/user.ts
💭 Reasoning: The app uses Express + Prisma. No auth middleware exists yet. I'll add bcrypt + jsonwebtoken, create the User model migration, build the auth routes, and add a protect() middleware. Tests with Jest + supertest.
write_file src/auth/jwt.ts — JWT sign/verify helpers write_file src/auth/middleware.ts — protect() route guard write_file src/routes/auth.ts — POST /login, /register run_command npx prisma migrate dev --name add_users write_file tests/auth.test.ts — 12 test cases run_command npm test
12 tests passing
6 files written  →  auth/jwt.ts, auth/middleware.ts, routes/auth.ts, migrations/…
time: 4m 38s · tokens: 218k · cost: $1.41

Works on real engineering tasks.
Sweet is built for developers who want real engineering work done while they're away. No IDE lock-in, no per-seat pricing, no hand-holding. Just results.

🔧

Build features end to end

Give Sweet a goal. It reads the existing codebase, writes the implementation, updates tests, and wires everything together.

$ sweet start "add Stripe subscription billing with webhook handling and invoice history page"
🐛

Fix bugs with context

Point Sweet at a failing test or error log. It traces the issue through your codebase and writes the fix with a regression test.

$ sweet start "users are getting logged out randomly — investigate the session handling"
🧹

Refactor safely

Break up a god class, migrate a database schema, or modernize a legacy module — with checkpoints and tests to verify correctness.

$ sweet start "refactor the payment module from callbacks to async/await, keep all tests green"

Run autopilot for hours

Set Sweet to work for a defined window. It plans a queue of tasks, executes them in sequence, and surfaces a summary when time's up.

$ sweet workfor 2h "clear the backlog: fix linting errors, update deps, add missing tests"

Why Sweet
Built for autonomous work.
Sweet doesn't just suggest code — it ships entire features while you're away.

🤖 Full Autopilot

Give Sweet a goal and walk away. It reads your codebase, plans the work, edits files, runs tests, and iterates until done — no hand-holding, no approval chains.

🔍 Deep Codebase Understanding

Sweet builds a rich map of your entire repository — cross-references, call graphs, and dependency chains — so every edit fits the architecture.

⚡ Parallel Agent Swarms

Dispatch multiple agents to work on independent tasks simultaneously. Refactor the backend while another agent builds the frontend — all coordinated from one session.

🛠️ Terminal-Native

Sweet runs where you run: in your terminal, in your repo. No IDE lock-in, no cloud dependency. Full access to your shell, your tools, your workflow.

💰 Transparent Pricing

Simple subscription pricing: $20/month Pro or $200/month Max. Cancel anytime. Transparent usage tracking so you always know where your budget stands.

🔒 Works With Your Stack

Sweet reads and writes any language, any framework. It runs your linters, your test suite, your CI — and adapts to your team's conventions, not the other way around.


Simple subscription plans.
Pro or Max. Cancel anytime. Every plan starts with a 3-day free trial.
For heavy users
$200/month
Max — ~50M tokens/month. 10× the Pro budget for production workloads and agent swarms.
Start Max Trial

███████╗██╗    ██╗███████╗███████╗████████╗   ██╗
██╔════╝██║    ██║██╔════╝██╔════╝╚══██╔══╝   ██║
███████╗██║ █╗ ██║█████╗  █████╗     ██║      ██║
╚════██║██║███╗██║██╔══╝  ██╔══╝     ██║      ╚═╝
███████║╚███╔███╔╝███████╗███████╗   ██║      ██╗
╚══════╝ ╚══╝╚══╝ ╚══════╝╚══════╝   ╚═╝      ╚═╝

Start your 3-day free trial.

Choose Pro or Max. Cancel anytime. Every new account starts with a 3-day free trial — your first task runs in under 2 minutes.

View Plans Read the Docs