01
Install on repos
Pick the repositories Codna can map. Self-host the engine, bring your own key, and keep egress fail-closed.
GitHub App
From issue to fix PR.
Open a GitHub issue. Codna maps the blast radius in ~60ms for zero tokens, writes the fix from a ~600-token evidence bundle, runs your test suite, and opens a verified pull request.
How it works
From first issue to merged fix.
02
Triage issues
Codna maps the repo and comments with suspect files, root cause, and recommended next steps.
03
Open fix PRs
Trigger from a label, a comment, or a failing check. A pull request opens only after your own test suite passes.
04
Keep control
Require review, branch protections, test gates, and approval before merge.
Comment to run Codna.
Trigger a fix directly in GitHub while keeping the full trail in the issue.
@codna fix this @codna explain blast radius @codna open-pr
Every PR explains itself.
Every PR ships with root cause, the test plan, and the passing test run — so reviewers see the evidence, not just a diff.
Root causesession race
Confidence91%
RiskLow
Frequently asked
Codna's deterministic engine maps the relevant code in ~60ms for zero LLM tokens, then an AI agent works from a ~600-token evidence bundle to write the fix. Your own tests verify it before the pull request opens.
No. Codna only opens an automated fix pull request when the fix passes your test suite. If verification fails, nothing is merged and nothing is opened.
Because the AI agent works from a ~600-token evidence bundle — 162x less context than reading the whole repo — a verified fix runs about $0.037 in measured testing, where a typical agentic edit that reads the whole repo costs roughly $1.
No. You self-host the engine, bring your own API key, and egress is fail-closed. Your code is never used for training.
Codna has mapped 130 repos in 9.2 seconds for zero tokens, so coverage is broad by design.
In head-to-head testing against Cursor across 87 tasks, Codna used 5× fewer tokens and ran 1.7× faster, with every fix verified by a passing test.