Writing

Long-form notes on
building gmux.

Honest writing about what we're making, what we've shipped, what's broken, and what we're learning while building a gesture-based terminal multiplexer for the AI-agent era.

Prefer to poke at the product? multi-agent monitor · agent flowchart · memory panel · phone app

The complete feature inventory

A full audit, accurate as of May 2026 — every shipped feature, every paused feature, every abandoned feature.

Featured Research · May 13, 2026 ~12 min read

The complete feature inventory.

40+ shipped features grouped under the three pillars — gestures, agent management, visual oversight — plus the foundation layer. Status pills on every card (ships / in progress / paused / dropped). Read this before adding a feature; you'll find it already exists.

Scannable card grid · accurate as of May 13, 2026. Read the inventory

Research articles

Deep dives: where gmux came from, how each implementation evolved, where it sits in the ecosystem.

Research · 01 · May 13 · ~8 min

How gmux changes multi-agent development.

The three pillars — gestures, agent management, visual oversight — that turn a fleet of AI agents from chaos into a workspace you can see. Big SVG visuals throughout. Demo CTAs at the top.

Best place to start if you've never seen gmux. Read overview
Research · 02 · May 13 · ~10 min

The stack we built.

Six implementations, three pillars, one stack. From the April prototype to the Tauri desktop app to gmux-brain memory. With a layered architecture diagram and the camera-broker fix that solved gestures.

For developers — covers the Tauri/PTY architecture in detail. Read the stack
Research · 03 · May 13 · ~9 min

Building gmux: the devlog.

The annoying-to-solve problem. The state-detection fix that made management work. The Wayland trap. The port collision with aria-phone. The installer freeze. The qalcode2 overlap realisation. What gets shipped next.

Personal-tone story. Best for blog / HN audiences. Read the devlog
Research · 04 · May 13 · ~8 min

Where gmux fits.

Three layers of AI tooling: orchestration (Multica, Linear), execution (qalcode2, opencode, DeepSeek-TUI), interaction (gmux). Most tools cluster around the first two. The third is empty — that's the moat.

For pitch context. The three-layer diagram is the takeaway. Read the positioning

Field notes

Shorter pieces — one idea each. The pitch, the architecture, the gesture vocabulary, the phone, the memory layer, and the roadmap.

7 short essays · one page

The traffic light, the layers, the gestures, the phone, the memory, the scope, the roadmap.

Seven short field notes about gmux, written for the homepage reader who wants to understand the product in one continuous read. Calm, opinionated, illustrated.

5-minute read total. All seven are on one page with deep links.
  • 01The traffic light for your AI fleet
  • 02Three layers that fail independently
  • 03The gesture vocabulary
  • 04Pocket-sized mission control
  • 05Agents that remember the last session
  • 06What gmux isn't
  • 07Coming soon — multi-camera, scheduled prompts
Read the field notes

More writing arrives as we ship — the next piece will be a launch note when the Tauri app passes its five-criterion install gate. Sign up to find out first.