ignite runs ai coding agents on your code.

start as many as you need. each one works in its own copy of your repo and comes back with a pull request. it keeps what it learns from you, so later conversations need less explaining.

needs git and node 22.18 or newer
done working !needs you

the work.

how code gets written, tested and merged without you babysitting it.

01 · worktrees

every agent gets its own copy.

each conversation works in its own git worktree, on its own branch. node_modules, builds and .env come along as copy-on-write clones, so it starts straight away.

run as many as you like. you keep coding in your folder the whole time, and nothing lands there until you merge.

02 · tools

it uses the tools you do.

a terminal next to the conversation that it can read. chrome to open your app, click through it and take screenshots. desktop apps when it needs them. side work goes to subagents, in parallel.

skills and mcp servers come over from claude code, codex, cursor and claude desktop in one click.

03 · github

it handles the github part too.

commits, pushes and pull requests wait for your ok. every changed file opens as a diff, and a comment on a line goes straight back to the agent.

once the pull request is up it keeps watching. failed checks, conflicts and review comments come back to it, and it fixes them. your folder updates when you merge.

the learning.

how it gets better every time you use it, so the hundredth conversation goes better than the first.

04 · memory

it remembers what happened.

after every run it writes down what was built, fixed or decided in that folder. the next conversation starts already knowing it, and can look up more when it needs to.

notes about the same file get merged over time. the ones the code proves wrong are retired, so it doesn't act on stale facts.

05 · lessons

it doesn't make the same mistake twice.

when you correct it, it writes a lesson in the same turn. lessons go into every later conversation in that folder, or in all of them.

some lessons are checks. the next time it reaches for the same wrong command or file, the call is stopped before it runs, with the lesson as the reason.

06 · reflector

it picks up how you like to work.

from your replies, your notes on its questions and the things you turn down, it learns how you want it to report, ask, plan and deliver.

each point keeps the words that taught it, and you can edit or delete any of them. say something twice and it moves up the list.

07 · procedures

it remembers how it got unstuck.

when a command fails and it finds the way past it, the working steps are saved. next time they're already there, so it skips the trial and error.

tell it the order you like for a kind of task and it keeps that too, and plans by it from then on. all of it is listed in settings and saved on your computer.

08 · android

there's an android app.

pair it with your computer to check on agents, answer their questions, approve a push or start new work while you're away from your desk.

it also works on its own, on your claude or chatgpt subscription, with nothing running at home.

also in there.

tasksline up work. the agent plans each one, does it and brings back a pull request.
sandboxcommands run in an os sandbox. they write only in the project and can't read your credentials. risky ones ask.
modelsclaude and chatgpt on your own subscriptions, or api keys. router picks the model and effort, or you choose.
drawingmark up a screenshot or a page to show what you mean.
⌘Kjump to any conversation, file or folder, or start a new conversation from what you typed.

download ignite.

needs git and node 22.18 or newer. a claude subscription also needs claude code installed. ignite updates itself.