r&d — hev mind

development

The products. Each has its own site and its own lifecycle — this is the status board, not the pitch.

active Launching now. The machinery behind “one guy, many agents,” packaged.

hev factory

A crew of coding agents on a Mac you own — a front desk that takes the work, a loop that breaks an approved plan into tasks, and a worker per task in its own session.

Stop prompting Claude directly. Reception takes the work, the loop plans it against an approved RFC, and every worker is a tmux session you can attach to mid-task and take over by typing. Approval happens in Linear; the factory reports what needs you. It ships no model and never sees your API keys — everything runs on the claude login you already hold.

hevfactory.com hev/factory

active The lead bet, and where most of the build time goes. In design preview with partner teams.

hev layer

A transparent, turbopuffer-shaped proxy that makes an existing vector store better without changing client code.

Your application keeps speaking the wire it already speaks; the gateway sits in the middle and adds retrieval. Automatic query routing reads the shape of a query and picks vector, lexical, or hybrid with RRF fusion per request. Typo-tolerant surfacing returns near-misses with a badge saying why. Query by id, radius scans, and point-in-time search round it out.

hevlayer.com hev/layer

experiment An open question about what docs owe agents, shipped far enough to install today.

hev ask

A ⌘K search overlay for docs readers, and the same docs as a markdown tree an agent can tree, cat, and grep.

hev ask distills a docs site into a committed ask digest — markdown a coding agent reads directly, and the index the overlay answers readers from. A Go core with an Astro adapter, published as the npm package @hevmind/ask. Free and open source. Astro is wired end to end; other framework adapters are designed, not shipped.

hevask.com hev/ask

archived No longer under development. The CLI still works.

vibe check

A YAML-first eval framework for any LLM — compare models, mix string matching with semantic and LLM-judge checks, run it from the command line.

Built for the tightest feedback loop I could get on a prompt change: did this get better or worse, and on which models? The CLI ships on npm as vibecheck-cli and the DSL still runs. The hosted preview is winding down — what it taught me about eval design went into how I run evals on client engagements instead.

Read the case study hev/vibecheck

showcase

Not a hev product and not a client engagement — a whole site, one operator directing a fleet of agents, kept deliberately outside the hev design system because the range is the point.

travels with charlie

A travel publication, built whole — destination guides, illustrated art direction, search, accounts. Next up: an agentic trip app builder.

One operator directing a fleet of agents, and the brief is a whole product rather than a feature. It is deliberately not in the hev design system: when the brand calls for loud, ship loud.

-> travels-with-charlie.com

research

I build source-available tools for benchmarking, comparing and evaluating database infrastructure, to help developers, IT leaders and entrepreneurs make decisions about technology. No content here is ever sponsored — but I do work with vendors to help them isolate and improve the performance of their products. Get in touch if that's interesting to you.

Opening one takes a free account — name, title, and what you're working on. That last field is how I pick what to build next. Sign up.

calculator Aug 2026

Vector index cost calculator

What a vector index actually costs, month 1 to month 36 — starting from how much data you have, not how many vectors you think you'll store.

Vendor calculators quote a month you will never have: they ask for a vector count nobody knows and price the steady state. The bill that surprises people is writes — how much data your index actually creates, once, and then keeps forever, times every re-index. Five inputs, 36 months, list prices, every constant shown. Queries are deliberately not modelled: they scale with traffic rather than corpus size, and they are not what surprises anyone on the invoice.

Built for a Maven Lightning Lesson with Doug Turnbull, August 2026.

Open the calculator hev/vector-cost free account · sign up

the filter

Why these problems and not others: I only take on R&D that clears three bars.

Hard enough to be worth money. Difficult enough that an enterprise would rather pay to have it solved than solve it themselves.
Interesting enough to hold five to seven years of focus. Not a feature, not a trend. Something worth staying on long after the novelty wears off.
Shaped for open core. The concept scales down so an individual uses it for free, and up so an enterprise pays. If the free tier is a crippled demo rather than a genuinely useful thing, the shape is wrong.

All three, not two of three. What that leaves runs in two halves. Development is the products above. Research is the tools I build to answer a question and publish so you can check the answer.