AXIOMINFERENCE Get Axiom

AxiomInference

The AI Lab for
local‑first
intelligence.

AxiomInference builds practical AI tools that run entirely on your own hardware, and researches small model architectures that adapt instead of just scaling. No subscriptions. No data leaving your device.

Latest release

Axiom V1.6

Self-hosted inference endpoints, a rebuilt context-compaction system for long conversations, OAuth connectors for Gmail, Drive, GitHub and Todoist, and a hardened, encrypted local data layer.

Continue reading

Latest releases

All repositories →
AXIOM · V1.6 Self-Hosted Inference & Reliability Release Bring-your-own inference endpoints, Hybrid Local mode, and a fixed context-compaction system. AXIOM CLI · v1.6.0 Cross-platform terminal council, in step with the desktop app Architect → Builder → Critic coding agent for Windows, macOS, and Linux. RESEARCH · DESIGN PHASE Project Kestrel — a small, adaptively-learning architecture Research survey and full architecture spec published; implementation phases not yet started.

What we build

Two products, one research thread.

Axiom and Axiom CLI are free, everyday AI tools — a Windows desktop assistant and a cross-platform terminal coding agent, both built around the same Architect / Builder / Critic council pipeline.

Project Kestrel is our research arm: a from-scratch small-model architecture designed to close the gap with frozen, oversized models through adaptive compute and continual memory, not just parameter count.

Why local-first

You own the hardware. You own the data.

Most AI tools send your conversations to a server. Axiom runs local GGUF models on your own machine by default, with optional cloud models when you want more power — always with your own API key, never a subscription.

Every product here also supports pointing at your own self-hosted inference server, so the same philosophy extends to hardware you run yourself, anywhere.