GQueries
Grounded memory and authorized evidence for production AI
What it does
GQueries gives AI systems a controlled evidence layer between retrieval and the final answer. It combines persistent memory, authorization, provenance and fail-closed grounding so applications can decide not only what information was found, but whether it is actually allowed and sufficiently supported to be used. Bring your own LLM, keep your existing stack, and send only the evidence needed for the current query.
Persistent memory, authorized evidence and fail-closed grounding infrastructure for AI systems.
Give your existing AI a memory it can defend: persistent context, authorized evidence and a fail-closed boundary before unsupported claims reach customers. Reader success varies by task. Bridge containment is measured separately. On 979 frozen support questions, ASM-CM + Bridge 8.1 delivered 93.6% Recall@5 and a 66.5% diagnostic answer score while sending about 1.09K input tokens per question to the reader. At 100 distractors and top-K 10, ASM compact reached a 75% diagnostic answer score with about 2.2K p95 reader-input tokens. BM25 reached 45% with about 4.6K. At 1,000 distractors, ASM compact held 50%; BM25 ranged from 30% to 40% across the measured K values. For agent memory, selecting…from gqueries.com
Does the same job
all alternatives →
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