Solo founders
You run the product, the backend, the bugs, and the roadmap. Keep every repo moving without living in one.
// open beta · free to start
> run your whole coding fleet from anywhere
FlareCode gives every repo a persistent cloud workspace and an agent that can plan, code, test, and open a PR. Start work from your phone, watch the fleet, and merge when the proof is good.
One repo gets an assistant. Ten repos need a control tower.
Start free →
free to start · usage billed at cost · cancel anytime
- 1Many repos, one rail
- 2Hand off a task in plain English
- 3It edits, tests, and self-verifies
- 4Review the diff, open the PR
Who it is for
Built for people running 3+ repos.
If you have one repo, use your favorite editor. If you have ten, use FlareCode.
Indie hackers
Ship the small fixes, experiments, and chores that keep getting pushed behind the main thing.
Small agencies
Hand off client repo maintenance, dependency upgrades, and test coverage while senior time stays on judgment.
OSS maintainers
Turn stale issues into normal Pull Requests with tests, diffs, and reviewable evidence.
The shift
Not another editor.
Cursor, Claude Code, and Codex make you faster at the keyboard. FlareCode is for the moment after you close it. Hand work to agents across your repos, then come back to reviewed PRs.
Your whole portfolio
One agent per repo. The whole fleet.
Point an agent at each repo and hand off the work. They run server-side and in parallel. A laptop runs one agent at a time; this runs your whole portfolio at once.
One rail is the control tower: every agent, every repo, every running task and open PR, in one place, from any device.
The loop
Plan, build, verify — then a PR.
You describe the outcome. The agent plans, writes the code, runs your tests, and fixes what breaks. Tests have to pass and it opens the app in a real browser; it shows you the proof, then opens a Pull Request for you to review.
▸ You
- 01
Connect a repo
Sign in with GitHub and install the agent on the repo you choose.
- 02
Hand off the task
Describe what you want in plain English, then close the laptop.
▸ The agent
while you're away
↳ hand off
- step 1
Plan
Reads your code and breaks the task into steps.
- step 2
Code
Edits files in an isolated, encrypted sandbox.
- step 3
Test
Runs your tests and fixes what fails — no infinite loops.
- step 4
Open PR
Pushes a branch and opens a Pull Request for you.
↳ opens a Pull Request
Every task runs in its own isolated sandbox with a per-task spend limit you set. Hit the limit and we stop the task and refund the platform fee — so the cost of every task stays predictable.
- 03
Review & merge
Approve the Pull Request from your phone or laptop — nothing merges without you.
It runs on its own
The whole loop — then a Pull Request.
Describe an outcome and the agent plans the steps, writes the code, runs your tests, and fixes what fails — inside a per-task spend cap you set.
When the checks pass it opens a Pull Request on its own branch, never your default. It proves the work; you review it.
Loops & guardrails
Point a fleet at a goal — and set the rules it runs under.
Type /loopand hand off a standing objective instead of a single task. The fleet keeps shipping toward it — on a schedule, or self-paced until it's provably done — opening a PR each iteration for you to review. Every loop is bounded by a cap you set, so it can never run away. And with hooks you bring your own guardrails: block secrets or denied hosts, gate which models and tools an agent may call, or get a webhook the moment a goal lands — enforced where the agent can't bypass them.
Memory & durable workspace
Every repo gets smarter — and never loses your work.
Each repo keeps a private memory of prior goals, files, and PR outcomes, so the next plan doesn't start from a blank slate. The workspace is encrypted and durable: it survives idle, restart, and eviction, even a brand-new project with no repo yet.
Anywhere
Review and merge from your phone.
Nothing is tied to your desk. The agent works while you're away; you get a notification, open the PR on your phone, read the diff and the test output, and merge from anywhere — or close it if it's wrong.
You stay in control
Built so it can't hurt you — not so you have to babysit it.
Your API keys never touch the agent — every model call is brokered server-side through a scoped, per-agent token, so a real key never reaches the sandbox. It works unattended in an isolated workspace, and your code is never shared or used for training. See the full security posture →
- It can't push to your default branch — rejected at three independent layers.
- It can't outspend the cap you set — the task is killed mid-stream.
- It can't merge without you — nothing ships on its own, ever.
Power workflows
Put your backlog on a fleet.
- 01Run dependency upgrades across every repo at once.
- 02Investigate a production bug while you're away from the keyboard.
- 03Open a PR for every stale issue in a small OSS project.
- 04Run nightly maintenance goals behind a human approval gate.
Built with FlareCode
“We build FlareCode with FlareCode. The agent you'll use is the one we use.”
Features land the same way yours will: a task in plain English, an isolated sandbox, and a Pull Request a human reviews and merges. This page shipped on a flarecode/task-* branch and was merged like any other change — same loop, same guardrails, no private back door.
Why FlareCode
Preview, deploy, BYOK, and the guardrails.
> See it running, ship it live
Preview the running app in your browser, then publish or deploy it.
> Bring your own key, or use ours
Kimi free on every plan; bring your own keys on any paid tier.
> Guardrails that hold
Three things the agent can't do: push to your default branch, outspend the cap, or merge without you.
> Bring your own guardrails
Block, gate, or get notified at the points the agent can't route around.
> It learns each repo
The next task on a repo picks up from what already worked, not a blank slate.
> Take the wheel when you want to
A real editor, terminal, and source control — edit, commit, and open the PR yourself.
Integrations
Works with the tools you already use.
Source control, issues, error tracking, deploys, design — the agent reads them, ships to them, and updates them while it works. Anything else plugs in through MCP.
Pricing
Inference at cost. Start free.
Start free on Kimi. Bring your own keys on any paid plan, or use bundled frontier — billed at cost, never marked up. See the plans →
Get started
Start building today.
Connect a GitHub repo, hand off a task in plain English, and get a reviewed pull request.
Start free →
free to start · usage billed at cost · cancel anytime