swain.

your open source local AI security lead. one command.

12 followers

your open source local AI security lead. one command.

12 followers

the machines write the code now. swain watches what they write. one command before you ship, local AI security review using the claude and codex CLIs you already have. no new accounts. no SaaS. no dashboard. catches auth bugs, billing bypasses, hardcoded secrets, SQL injection, XSS. ends with one thing: the exact issue blocking your launch and the exact command to fix it. nothing the machine writes passes unseen.

Free

Launch tags:Software Engineering•Developer Tools•GitHub

Launch Team / Built With

LightfieldAI-native CRM that builds itself and does work for you

Promoted

Maker

📌

hello people, me and my friend (aka. the descry labs team) built this as a product after months of thinking what to ship, we ended up making what we use. swain is a local AI security review for that moment. it runs from your repo, uses your existing claude or codex CLIs, scans the launch-risk surfaces first, and tells you what to fix before you ship. it drafts reviewable patches and learns from false positives. install: one curl command from github. first launch explains what swain reads and writes, then asks whether to use claude, codex, or hybrid mode. try swain demo for the full loop without spending quota. thank u Maciej - descry

Report

3mo ago

Maker

swain uses a fixed severity ladder: launch-risk → high → medium → ok. anything that could get you breached on day one (billing bypasses, auth holes, hardcoded secrets) sits at the top.

if two findings share the same severity, it goes by category, billing and auth before XSS before tenant isolation, because that's roughly the order a motivated attacker works in.

Report

3mo ago