AgentShield
AI agent spend firewall
What it does
Stop runaway AI agents. 7 composable spend rules, <1ms eval, pure Python stdlib. 50/50 eval gym.
A paid, fixed-scope sipi.bot implementation pilot: map one agent spending path, write enforceable rules, integrate the pre-spend decision, and validate it before launch.
We map where one production agent can trigger paid API calls, cloud jobs, purchases, or retries. Then we write the policy, wire the pre-spend decision into that path, and validate the behavior before launch. AgentShield has been consolidated into sipi.bot. The old separate plans and funnel are retired. This is the single implementation path. The pilot is implementation work, not another dashboard subscription or a generic security audit. One documented workflow showing every paid tool, provider, retry path, approval point, and failure mode in scope. Per-transaction caps, velocity limits, merchant and category rules, approval thresholds, and a clear default-deny decision where needed. The…from agentshield.fly.dev
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com