Show HN: We Gave AI Coding Agents Production Memory

Hacker News Show2026-11-10 01:310 views

Hi HN, I’m building Codela to help coding agents learn from what happens after their code ships.

I realized that my AI agent writes a change, the tests pass, and it gets deployed. Then in production a problem happens, I fix it, but what it did wrong and why never reaches the agent, so futures session usually make the same mistake.

Codela checks every deploy against how your app actually behaves in production, learns from the ones that broke it, and teaches your agents so they don’t repeat the mistake.

Would love any feedback on this, thanks!

Comments URL: https://news.ycombinator.com/item?id=50428670

Points: 1

# Comments: 0

Source：https://usecodela.com/

My favorites

PreviousShow HN: Face analysis tools with on-device photo processing NextShow HN: Annotated – a public annotation layer for the web

SwarmEvolve: How Latent-Space Agent Swarms Cut Scientific Program Search Time from 60 Minutes to 8

SwarmEvolve: How Latent-Space Agent Swarms Cut Scientific Program Search Time from 60 Minutes to 8 Most multi-agent AI s

0dev.to Machine Learning

Evaluating Machine Learning in Security Products: A Framework

A detection arrives with a score of 0.93. Your SOAR playbook isolates the host because someone set the auto-containment

0dev.to Machine Learning

13 papers on AI agent memory: the biggest lesson is to keep the originals

Why I read them I'm building Folio Continuity, a shared project memory that AI agents read from and write to. One design

0dev.to Machine Learning

Vom Paper ins Protein: Wie ich BRP in VR begriffen habe – und warum das für jeden Structural Biologist wichtig ist

Vom Paper ins Protein: Wie ich BRP in VR begriffen habe – und warum das für jeden Structural Biologist wichtig ist Letzt

0dev.to Machine Learning

AI Designed the Protein. Does It Stay Folded?

If an AI model gives you a convincing protein design, I’d want to know what happens once someone actually makes it. Does

0dev.to Machine Learning

One split said 70%. Five folds said 57%.

One split said 70%. Five folds said 57%. Tiny AI Maker trains a small text classifier in the browser. Until this week it

0dev.to Machine Learning

Show HN: We Gave AI Coding Agents Production Memory

Related posts

SwarmEvolve: How Latent-Space Agent Swarms Cut Scientific Program Search Time from 60 Minutes to 8

Evaluating Machine Learning in Security Products: A Framework

13 papers on AI agent memory: the biggest lesson is to keep the originals

Vom Paper ins Protein: Wie ich BRP in VR begriffen habe – und warum das für jeden Structural Biologist wichtig ist

AI Designed the Protein. Does It Stay Folded?

One split said 70%. Five folds said 57%.