I built Raincast, describe an app, get a tauri desktop app #15186
tihiera
started this conversation in
Show and tell
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hey everyone! I've been working on Raincast, an AI-powered app generator that builds real, shippable Tauri 2 applications from natural language.
You describe what you want in plain English, and Raincast generates the full app: React frontend, Rust backend commands, and Tauri config. Not a mockup — a compiled, distributable binary.
What it generates:
Result from prompt:
"Build a local AI chat app that connects to a llama.cpp server running on my machine. Chat interface with streamed responses, a model picker, and a collapsible dev console showing connection status and server logs."
The interesting Rust bit: In dev mode, Raincast builds a proxy binary. It parses the generated Rust source using AST extraction to find every #[tauri::command] function, then generates a standalone CLI that dispatches to the same functions via stdin/stdout. So the preview behaves like the real app (file system, shell, system info all work) without compiling the full Tauri binary each time.
AI providers: Claude Sonnet 4.6, Gemini 3.1 Pro, more coming (PRs welcome for OpenAI Codex, xAI, DeepSeek, Mistral)
Install (macOS):
curl -fsSL https://raw.githubusercontent.com/tihiera/raincast/main/scripts/install-macos.sh | bashWindows and Linux binaries on the releases page.
Links:
Built with Tauri 2, React 19, TypeScript, and Rust. Free and open source (MIT).
Would love feedback from the Tauri/Rust community, especially on the proxy binary approach and the generated Rust command patterns.
One question: Has anyone explored embedding a Rust compiler (or a subset of it) inside a Rust binary so that end users can compile generated apps without needing a separate Rust toolchain installed?
Beta Was this translation helpful? Give feedback.
All reactions