Informe de benchmarks
Metodología y resultados por escenario para Codna frente a los principales agentes de código.
Recursos
Abrir
Reparación autónoma de código
Por qué los agentes necesitan un mapa determinista antes de corregir.
Revisión de código con IA
Cómo el radio de impacto y el riesgo de regresión hacen las revisiones de PR más rápidas.
De Sentry al PR
Convierte fallos en producción en pull requests de corrección enfocados.
Frequently asked
Codna was tested head-to-head against Cursor. It used 5× fewer tokens and ran 1.7× faster, with every fix test-verified.
Token consumption, wall-clock speed, and verified fix rate across 8 real bug-fix scenarios run against OpenAI Codex CLI and Google Gemini CLI. Every fix counted only when your own tests passed.
A deterministic engine maps the repository in roughly 60ms without any LLM calls. It then hands the AI agent an evidence bundle of around 600 tokens — measured 162x smaller than reading the full repo — so the agent fixes the right code immediately.
Yes — Codna supports 250+ languages, and the engine mapped 130 repositories in 9.2 seconds, consuming zero tokens for the mapping step.
Codna locates the affected code using its dependency and blast-radius graph, generates a fix from the evidence bundle, then runs your tests to verify the result. On GitHub, it opens a pull request with the verified fix.
You can self-host the engine, bring your own API key, and configure fail-closed egress. Codna never trains on your code.