Blog

Notes from building Vexi

Engineering write-ups, practical guides, and honest notes on what a local-first AI coding agent can and cannot do.

01

Why Vexi exists: an AI coding agent that never leaves your machine

Most AI coding tools ask you to trust a server with your source code. Vexi takes the opposite path: no account, no backend, no telemetry.

02

How Vexi detects 13 AI providers from your key alone

No provider dropdown, no config file. The format of an API key is enough to identify who issued it. Here is how that works.

03

Running an AI coding agent for $0: the free-tier providers

Eight of the thirteen providers Vexi supports have a genuine free tier. Here is what each is actually good for, and where the limits bite.

04

How Vexi remembers your decisions across sessions

Context windows end. Projects do not. The Context Compression Engine keeps what matters and drops what does not.

05

From prompt to pushed commit without leaving the session

The /push command stages your changes, writes a commit message from the real diff, and pushes, with a confirmation you actually control.

06

Knowing what a session actually cost, while it runs

BYOK means the bill is yours. /usage shows real token counts and an estimated dollar cost per session. No dashboard, no lag.

07

Teaching Vexi your conventions with custom skills

Drop a Markdown file in .vexi/skills/ and Vexi follows your house rules. No fine-tuning, no prompt engineering in every message.