cross-platform AI programming orchestration app built with **Tauri 2** (React 18 frontend + pure Rust backend, no Python sidecar). It manages LLM-powered task execution with features like agent management
never ships code the repo hasn't typechecked, built, and tested.
**The stance is frontend-opinionated, backend-agnostic — preserve it.** The frontend
is one fixed, curated stack you *compose* from
each validated slice as soon as it is coherent over waiting to batch unrelated frontend, SDK, and documentation changes together.
## Website Architecture
**Next.js 16 (App Router)** + React 19 + TypeScript. Note
Bulletproof Frontend — When to Use
**Invoke this skill (`/bulletproof-frontend`) before writing or modifying any CSS, HTML, or Blade template code.** Don't wait to be asked — if the task touches
Only `SERVER_MESSAGES` (channel UI strings) are localized (fr/en, others fall back to en). Frontend locales: `public/locales/` (fr, en). No linting or formatting tools configured.
## Commands
```bash
# One-command bootstrap
powered terminal emulator built with Tauri 2 (Rust backend, React 19 frontend).
## About This Project
This is **Qbit's own codebase**. If you are Qbit, then
declarative generative UI protocol. The agent generates JSON describing UI components, and the frontend renders them.
### Response Format
Agent responses include text plus A2UI JSON after a delimiter:
```
Here
Commands
- `pnpm dev` — start dev server (port 5173)
- `pnpm dev:all` — start both frontend (port 5173) and local API server (port 3001)
- `pnpm typecheck` — type-check all sources
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.