Field notes · roughly monthly

Notes from building Vehla.

Less "AI is the future". More what we learned on the actual ship.

I Got Tired of Stacking Mac Utilities — So I Built One Command Center

A founder essay on why Vehla is a local-first Mac command center — keyboard palette, clipboard, windows, and AI in one hotkey — instead of another single-purpose utility stack.

Read on Medium

Vehla vs Raycast vs SuperCmd: which Mac command center fits you?

A sourced comparison of three different approaches: built-in local-first workflows, a mature launcher ecosystem, and a free open-source Raycast-compatible alternative.

Read the comparison

Best Raycast alternatives for Mac.

A practical guide to launcher and command-center alternatives, including Vehla, Alfred, SuperCmd, LaunchBar, and focused utility stacks.

Read the guide

Local AI on Mac without a subscription.

How MLX, Gemma, Ollama, LM Studio, BYOK cloud keys, and Vehla's local routes fit together on Apple Silicon.

Read the post

What an MCP client means on a Mac.

A guide to connecting tools, reviewing permissions, and keeping agent workflows understandable from a local command center.

Read the post

AI clipboard OCR for Mac.

How local OCR, image clipboard history, QR detection, and AI transforms make copied screenshots more useful.

Read the post

Vehla vs Raycast: which Mac command palette should you use?

Raycast is a polished launcher with a large extension ecosystem. Vehla is a native Mac command center with AI, local models, file actions, clipboard history, and workflows built in.

Read the post

Vehla vs Alfred: a modern Mac command center with AI built in.

Alfred is a classic Mac power-user launcher. Vehla brings the keyboard-first idea forward with AI, local models, native actions, and iCloud-synced workflows.

Read the post

Why we made local-first the default — and what it cost us.

Cloud inference is faster, cheaper to ship, and easier to support. We made the harder choice. Here's the math, the missteps, and the moment we knew it was right.

Read the post

Notes on Gemma 4 E4B at 4-bit on Apple Silicon.

How Vehla thinks about Gemma 4 models, default local inference, and the trade-offs between speed, quality, and download size.

Read the post

11 rewrite tones, 1 prompt skeleton.

The structure behind every Rewrite — Professional, Casual, Confident, and the rest. What works, what flatters the model, and what we threw away.

Read the post

Designing a command palette you actually use.

Spotlight, Alfred, Raycast, Linear — every great palette has the same five details right. We rebuilt ours three times to get there.

Read the post

What shipping v1.0 actually felt like.

What shipping a menu-bar AI assistant taught us about shortcuts, permissions, local models, and support.

Read the post

We removed telemetry.

What we learned about trust as a feature, and why Vehla does not collect prompts, outputs, or product analytics.

Read the post