1
Map for zero tokens
Codna builds a dependency and blast-radius graph of the repository from its import patterns. No model call, zero tokens.
Comparison
Codna vs Devin
Devin is an autonomous agent. Codna is a deterministic understanding layer with a scoped agent behind it: zero tokens to map, a fix that explains itself, and a pull request you merge.
The problem
Autonomy without a map means the agent explores.
An autonomous agent that discovers the codebase as it goes spends tokens and time on the discovery. Codna computes the dependency and blast-radius graph first, without a model, and keeps the agent inside the evidence.
How Codna fixes it
How Codna works
2
Hand over evidence, not the repo
The agent receives an evidence bundle scoped to the issue: the suspect files, the call paths, the failing test. Codna prints the raw-to-bundle token size on every run.
3
Report, gate, open the PR
Every fix reports root cause, confidence, blast radius and regression risk, and passes a risk gate before it is applied or a pull request opens. With --open-pr, or through the GitHub App, the pull request states the issue, the root cause, the symbols touched and a confidence score, and asks for review before merging. Codna never merges.
codna fix https://github.com/org/repo --issue "the checkout test is failing" --open-pr
What you get
What you get
A map that is computed, not described
Codna builds a dependency and blast-radius graph of the repository from its import patterns. No model call, zero tokens.
A pull request you review
With --open-pr, or through the GitHub App, the pull request states the issue, the root cause, the symbols touched and a confidence score, and asks for review before merging. Codna never merges.
Yours to run
The CLI and the Action run on your machines with your own key. The GitHub App is hosted and uses per-job, repository-scoped, short-lived tokens.
The proof
Fewer tokens. Faster. Verified.
Frequently asked
The only measured head-to-head Codna publishes is against Cursor: 87 matched bug-fix cases on identical checkouts, 5× fewer tokens, 1.7× faster, 87 of 87 verified, about $0.02 per fix. Everything else on this page describes Codna's own behaviour, not Devin's internals.
Codna runs an agent, but a scoped one: it works from the evidence bundle the deterministic map produced, reports root cause and risk, and opens a pull request for your review. It never merges.
Codna's CLI and Action run on your own machines with your own key. Understanding is offline. Only the evidence bundle reaches your model provider.
Yes. Codna is a CLI, an MCP server, a GitHub Action and a GitHub App. Add it where it helps and keep the rest of your workflow.
Bring a key from Anthropic, OpenAI, Google Gemini, Groq, Mistral, OpenRouter or xAI, stored in your OS keychain with codna key set, or sign in and use the managed allowance. The repository map is built from import patterns, so it is not tied to one language. On-device recall covers Python, JavaScript, TypeScript, Go, Rust, Java, C, C++, C#, PHP and Ruby. Your own test command verifies the fix.
Understanding runs on your machine and spends no tokens. Only the evidence bundle or the diff reaches your model provider, with your key from the OS keychain. Set privacy.egress to fail-closed in codna.yaml and Codna runs your tests only under kernel-level network denial. Secret redaction is always on. On 87 matched bug-fix cases against Cursor, Codna averaged 16,159 total tokens and about $0.02 of model spend per verified fix, 5× fewer tokens and 1.7× faster. With your own key you pay your provider directly.
Related
