Parse the repo.
Codna scans files, symbols, imports, tests, and dependency edges across 250+ languages. This runs without an LLM, so it costs zero tokens and does not leak code to a model.
codna triage . --json
How it works
Understand first. Fix surgically.
Codna maps your entire codebase in 60ms, zero tokens — then fixes the bug with only the evidence that matters.
How it works
1
2
Build the blast-radius graph.
The graph identifies what can break if a function, file, package, or API changes. That lets Codna narrow the search space before the agent starts.
3
Pack the evidence bundle.
Codna hands the agent the exact files, failing tests, call paths, and historical context it needs — not a giant context dump.
4
Generate and verify the fix.
The agent writes the patch, then your own test suite runs. If the tests don't pass, the fix never ships. With the GitHub App, a passing fix becomes a pull request.
codna fix . --issue "checkout race condition" --pr
Under the hood
What Codna hands the agent.
Whole repo100,000+
Evidence bundle~600
A change lights up its blast radius — Codna simulates the risk before you apply.
Architecture
Model-agnostic by design.
Use your own key, your own model provider, or the managed LLM option. The deterministic map stays the same.
Bring your key
Your model key. Your limits. Your audit trail.
MCP server
Give Cursor and Claude codebase understanding as a local tool.
CLI-first
Run Codna in any repo, CI job, or container.
GitHub App
Turn issues and failing checks into fix PRs.
Frequently asked
A deterministic engine builds a dependency and blast-radius graph of your repository in roughly 60ms, using zero LLM tokens. That graph captures which code affects which — no AI guesswork involved in the analysis step.
An evidence bundle is the minimal slice of context Codna assembles before calling the AI agent — about 600 tokens, measured at 162x less than reading the whole repo. The agent sees only what is relevant to the bug, so fixes are faster and cheaper.
Every fix is verified by your own tests before it is surfaced. If the tests do not pass, the fix is not delivered.
Benchmarked head-to-head against Cursor across 87 tasks, Codna used 5× fewer tokens and ran 1.7× faster — roughly $0.02 per verified fix.
Codna has mapped 130 repositories in 9.2 seconds for zero tokens. The deterministic engine is language-agnostic by design.
Codna ships as a CLI, an MCP server for Cursor and Claude, and a native GitHub App that opens verified fix pull requests. You can self-host, bring your own API key, and egress is fail-closed — your code is never used for training.