Miriel Engineering

Notes from the engine room

Deep dives, design decisions, and field notes from the team building the context engine for AI-native development.

LatestEngineeringJuly 17, 2026 · 17 min read

From 40 Million Tokens to a 450K-Token Graph: How Miriel Distills What It Learns

Every document Miriel learns is distilled into knowledge-graph triples by a small model, once, at write time. The result is ~89x compression of a whole mailbox for about $10, retrieval that joins facts across sources the way similarity search can't, and a memory that strengthens with use and fades without it.

AndyRead post

All posts 9

July 14, 2026Autodev
Code against the environment you need
A sneak peek at where we're taking autodev preview deployments: compose any set of services into one environment, and source each one exactly how you need it — a hermetic sandbox,…
Jason Chew5 min read
July 8, 2026Product
You Shouldn't Need a $1,000 Consultant to Change Your Own Website
Editing your own WordPress site still means paying an agency four figures and waiting weeks. In the age of AI, that's absurd. NexusBuild understands your site, migrates it somewhere you control, and lets you make the changes yourself — starting with WordPress.
Miriel3 min read
July 8, 2026Labs
Nora at Work: A Visual Tour of the Floodlight Preview
We've written about how Nora is built — a reactive Voice and a deliberative Supervisor meeting at a blackboard. This time, we show her working: files as a navigable space, terminals and browsers as windows in that space, coding delegated mid-conversation, and interfaces synthesized on demand.
Miriel4 min read
July 3, 2026Research
Separating Dialogue from Deliberation: Nora's Two-Process Architecture
A conversational agent that also does long-horizon work has to reconcile two incompatible clocks. Nora — the agent inside Floodlight — resolves it the way an operating system does: a reactive Voice and a deliberative Supervisor that meet only at a blackboard.
The Miriel Team13 min read
June 29, 2026Autodev
Augmenting your AI coding agent with Miriel
An autodev agent reads your repo and GitHub for free; the things it gets wrong live everywhere else. Here's the integration pattern, and a reproducible side-by-side of the same task run with and without the Miriel context engine.
Jason Chew5 min read
June 25, 2026Engineering
Scaling Homomorphically Encrypted Face Search to 10 Million Vectors on GPUs
Building on an FHE facial-matching pipeline, we fixed a recall bug in the GPU search path, cut single-query latency by 3.4x, and scaled the search to 10 million encrypted vectors at about 1.2 seconds, validated against an exact brute-force baseline.
Madison Bratina8 min read
June 19, 2026Video Embeddings
Accelerating Video-to-Vector Ingest to 8,000 Vectors per Second per Node
Accelerating Video-to-Vector Ingest to 8,000 Vectors per Second per Node By Madison Bratina Video now makes up the majority of the world's data, and making it searchable means…
Madison Bratina8 min read
June 9, 2026Research
Searching 100 Billion Encrypted Video Vectors: Why Search Latency Didn't Budge With Scale
How we scaled Miriel's confidential video search from one machine to a 20-node fleet, ingested 100 billion vectors at 37.5 million/sec, and kept search latency flat the whole way…
Madison Bratina10 min read

Notes from the engine room

From 40 Million Tokens to a 450K-Token Graph: How Miriel Distills What It Learns

All posts 9

Code against the environment you need

You Shouldn't Need a $1,000 Consultant to Change Your Own Website

Nora at Work: A Visual Tour of the Floodlight Preview

Separating Dialogue from Deliberation: Nora's Two-Process Architecture

Augmenting your AI coding agent with Miriel

Scaling Homomorphically Encrypted Face Search to 10 Million Vectors on GPUs

Accelerating Video-to-Vector Ingest to 8,000 Vectors per Second per Node

Searching 100 Billion Encrypted Video Vectors: Why Search Latency Didn't Budge With Scale