Generating 3D models from Claude with Meshy and Tripo
Godot Catalyst wires Meshy and Tripo into the MCP session. How text-to-3D works in practice, what the generated FBX looks like, and real use cases.
Guides, deep dives, and policy writeups on eyehands, Godot Catalyst, and Claude Code running real workflows on Windows and inside Godot 4. Release notes now live in the per-product changelog.
Task-oriented walkthroughs for specific jobs.
Godot Catalyst wires Meshy and Tripo into the MCP session. How text-to-3D works in practice, what the generated FBX looks like, and real use cases.
Install Godot Catalyst, point Claude Code at your Godot 4.x project, and wire your first signal with natural language. A practical setup tutorial.
Godot Catalyst wires Claude to three CC0 asset providers. How the pipeline works, how Claude picks assets, and how downloads land in your project.
How to give Claude Code the ability to play a game running on a remote machine over Parsec, using eyehands' pointer-lock-compatible input.
A practical guide to teaching Claude Code to operate native Windows applications using UI Automation, OCR, and the eyehands local HTTP server.
Legacy Windows apps without Selenium bindings, test frameworks, or official APIs can still be tested. Here's how to drive a WinForms tool with Claude Code via eyehands.
Windows UI Automation is the accessibility API screen readers use — and the cleanest way to find controls programmatically. Here's how to use it from Python without getting lost in COM.
Five real recipes for letting Claude Code drive your Windows desktop via eyehands: inbox triage, log scraping, dashboard screenshots, deploy health checks, and form auto-fill.
Why eyehands uses SendInput under the hood, which games it actually works with, and a walkthrough of building a simple automation bot with safe input throttling.
Turn eyehands into a lightweight WinForms UI-test harness: click elements by name via UI Automation, assert on screen content via OCR, and keep tests deterministic with click_and_wait.
Technical explainers. What, why, and how much it actually costs.
Why Godot Catalyst has four tool modes. What each mode drops, which clients need which, and how the gating works in src/tools/registry.ts.
How Godot Catalyst wires Claude Code to Godot's built-in LSP and DAP servers. Why this beats file-reading, with Content-Length framing details.
Godot Catalyst parses TSCN, TRES, and project.godot files offline. When and why to prefer it over the editor-backed tools.
How convention enforcement keeps AI-generated Godot scenes from turning into @Node@xyz soup. Naming rules, auto-fix, custom overrides.
Why the three-tier MCP client / TypeScript server / Godot plugin design. The WebSocket on 6505, the debugger bridge, and hot reload.
Creating ten nodes as ten calls costs a lot more than one batch call. How Godot Catalyst's batch tools work and when the N>3 heuristic kicks in.
240+ tools sounds like a lot. The real question is what your client does with them. Context cost, tool modes, and Claude's Tool Search.
Why an HTTP server is the right shape for AI agent tools, when it isn't, and design decisions I made building eyehands.
Measured token costs for the same Windows automation task done screenshots-first vs UIA-first. The 4× difference, and where it comes from.
If Claude is waiting for a build to finish, it shouldn't be paying for screenshots while nothing changes. Frame-hash polling with If-None-Match is how you get wait-for-change for free.
Three ways an AI agent can see a Windows desktop, with real token costs, failure modes, and when to use each.
Why most Python Windows automation scripts get wrong coordinates on high-DPI monitors, and the single DllCall that fixes it.
Most Python automation libraries use keybd_event and mouse_event under the hood. These APIs silently fail inside pointer-lock applications. Here's why, and the SendInput fix.
Full disclosure of the anonymous install heartbeat in eyehands and Godot Catalyst: exact payload, what's excluded, and three ways to opt out.
No posts match the selected tag.