Minesweeper: agent loop + grounding

A fast demo on a browser game. Glasswarp is eyes and hands; the solver or LLM is the brain (example code).

observe → think (CV+solver or Gemini) → click_target → verify → repeat

Platform vs agent: observe / click_target are Glasswarp. Board CV, solve(), and LLM prompts are example code under sdk/python/examples/ — the pattern to copy for your own tasks.

Prerequisites

Online, API-enabled rig

Install the host → Console → Rigs → API access on.

SDK

pip install "glasswarp[grounding]"
export GLASSWARP_API_KEY=gw_live_sk_...

Run (deterministic think — fastest)

pip install "glasswarp[demos]"
export GLASSWARP_API_KEY=gw_live_sk_...
glasswarp-demo minesweeper

Repo checkout:

python sdk/python/examples/minesweeper_solver_demo.py

Launches Chrome → Google Minesweeper (Medium) → plays to a win. Watch Console → Sessions → Eye.

Run (LLM think — Gemini + SoM)

export GEMINI_API_KEY=...
python sdk/python/examples/gemini_agent_loop.py

Same eyes/hands; Gemini picks a Set-of-Mark cell id each step.

Platform vs agent

Step	Owner
Observe (`observe`)	Platform
Think (CV + solver, or model)	Your agent / example code
Act (`click_target`)	Platform
Verify (re-observe)	Your loop + platform eyes

Canonical shape: Build an agent loop. Skeleton: sdk/python/templates/observe_think_act/.

Tuning

Env var	Default	Purpose
`DEMO_BOOTSTRAP_CHROME`	`1`	`0` if the game is already open
`TOTAL_MINES`	`40`	Google Medium
`CLICK_PAUSE_S`	`0.12`	Delay between clicks

Templates

Outcome-named starters.

Grounding

SoM + click_target.

Get started

Setup

Concepts

Guides

Examples

Help

Minesweeper: agent loop + grounding

Prerequisites

Run (deterministic think — fastest)

Run (LLM think — Gemini + SoM)

Platform vs agent

Tuning

Templates

Grounding

​Prerequisites

​Run (deterministic think — fastest)

​Run (LLM think — Gemini + SoM)

​Platform vs agent

​Tuning

Templates

Grounding

Prerequisites

Run (deterministic think — fastest)

Run (LLM think — Gemini + SoM)

Platform vs agent

Tuning