BRINGING IDEAS TO LIFE
We are builders. Small team. AI-native. Shipping open source from zero.
Bootstrapped. No VC. We create open source tools to solve real problems and selectively partner with teams building meaningful things.
What We Do
Three pillars of how we operate
Build Open Source
We create tools and ship them in the open. From AI runtimes to deployment tools — if we need it, we build it and share it.
AI-Native Workflow
Small team, massive output. AI is core to everything we do — not a bolt-on feature but how we actually work every day.
Partner Selectively
Premium partnerships with teams building meaningful things. Not an agency. Not cheap. Selective and high-quality.
Things We've Built
Open source tools shipped by our team
For Builders
Follow our journey. Read the blog. Use our open source tools. Learn how a small team ships with AI-native workflows.
Read the blogFor Teams
Need a builder's perspective? We selectively partner with teams that value quality and want proven execution on meaningful projects.
Let's talkLatest from the Blog
Building in public. Sharing what we learn.
One SQLite File, 1 Hz, Zero Cloud: The Local-First Architecture of a Mac Time Tracker
A grounded design guide to building a local-first desktop app: why one embedded SQLite file beats a cloud DB for a single user, how 1 Hz raw samples roll up into human sessions, schema design for time intervals, WAL and crash safety, and the honest tradeoffs of owning your own data.
Why We Run Speech Recognition Fully On-Device: The Latency and Privacy Math
Cloud speech-to-text loses on a budget you can compute on a napkin. Here is the round-trip math that forced Vext to run both the speech model and the cleanup LLM on-device, plus a cloud-vs-local decision framework for your own audio feature.
Lessons From Building a Unified LLM Provider Layer in Rust
What we learned shipping octolib, the Rust LLM library behind our AI stack: how to abstract multiple LLM providers, normalize tool calls and token usage, and survive the day a model's thinking format returned a 400.