Show HN: Keep your credentials out of the AI agents you use and build
Security should be free! I was getting mad that all the security tools that meant to guard your agents are not local and those who are, just cost a fortune. So I’ve built Weir. You can watch you sensitive data flow, your traces and your egress tools calls. It doesn’t stop your ADLC, it only watch it locally (no egress). The agents you use - I’ve set a Claude code hook that stripe your known keys from tool output before the model sees them. The agents you build - Weir plants fake keys, runs your
Read original source
Source record
Recorded metrics
points · 1 votes
2026-10-28 19:45:17.154Z
cumulative since publication
Research analysis
Project record
Repository: IdoGol24/weir. Source account: Security should be free! I was getting mad that all the security tools that meant to guard your agents are not local and those who are, just cost a fortune. So I’ve built Weir. You can watch you sensitive data flow, your traces and your egress tools calls. It doesn’t stop your ADLC, it only watch it locally (no egress). The agents you use - I’ve set a Claude code hook that stripe your known keys from tool output before the model sees them. The agents you build - Weir plants fake keys, runs your
Observed adoption & comparisons
Source votes: 1 votes (Oct 28, 2026 UTC; cumulative since publication); previous same-scope observation: 1 (Oct 28, 2026 UTC). These observations do not establish demand growth. Recent records to compare: “Show HN: Cerea – yet another self-hosted LLM chat front end” (Show HN, Nov 5, 2026); “Show HN: Lantern Lattice – the call graph from your compiler, for coding agents” (Show HN, Nov 5, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.