Code review on every push.
A bot in your CI that reads each pull request with the files around it, flags bugs and style problems, and suggests fixes before a person looks. It runs on every push, not just the ones you remember to ask about.
Pre-launch. Accounts are open; the API and checkout open soon.
How it runs.
01
Run it in CI.
A workflow sends the diff and the files around it to the model on every push.
02
It comments.
Findings land as review comments, with suggested changes.
03
People decide.
Your team still approves; the bot catches the easy things first.
Why lanes fit it.
Every push, not a sample.
Reviewing everything costs the same as reviewing a few PRs a week.
Context without a bill.
Send the whole file, the tests and the callers, not just the diff.
Busy weeks are included.
A release week with fifty PRs a day doesn’t raise the bill.
Works with what you use.
OpenAI Python
python
import osfrom openai import OpenAI client = OpenAI( base_url="https://api.voidstone.net/v1", api_key=os.environ["VOIDSTONE_API_KEY"],) stream = client.chat.completions.create( model="kimi-k3", messages=[{"role": "user", "content": "Explain this stack trace."}], stream=True,)for chunk in stream: print(chunk.choices[0].delta.content or "", end="")