Personal-AI-Router / rules
NVIDIA/Personal-AI-Router/.cursor/rules/communication-layers.mdc
Current renderer, Electron, broker, and node communication boundaries
The rules real projects give Cursor's agent, from .cursor/rules.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
NVIDIA/Personal-AI-Router/.cursor/rules/communication-layers.mdc
Current renderer, Electron, broker, and node communication boundaries
NVIDIA/Personal-AI-Router/.cursor/rules/engines-vs-backends-naming.mdc
Use engine terminology in PAIR code and UI
NVIDIA/Personal-AI-Router/.cursor/rules/file-editing.mdc
Read-before-write rule — always Read a file before Write/StrReplace. No shell scripts to mutate code. No exceptions.
NVIDIA/Personal-AI-Router/.cursor/rules/imports-discipline.mdc
Static imports only, no dynamic imports, no convenience re-exports
NVIDIA/Personal-AI-Router/.cursor/rules/ipc-patterns.mdc
IPC handler patterns — Electron-native ops only, always use safeHandle, never throw
NVIDIA/Personal-AI-Router/.cursor/rules/model-registry.mdc
Backend-owned engine model catalogue (Ollama committed list + LM Studio and llama.cpp Hugging Face catalogs)
NVIDIA/Personal-AI-Router/.cursor/rules/no-legacy-fallbacks.mdc
No legacy compatibility paths or dead fallback branches — greenfield codebase
NVIDIA/Personal-AI-Router/.cursor/rules/no-push-to-main.mdc
Never push directly to a shared branch; always use a feature branch and a pull request
NVIDIA/Personal-AI-Router/.cursor/rules/platform-helpers.mdc
Platform detection and display helpers — never use process.platform or NodeJS.Platform directly
NVIDIA/Personal-AI-Router/.cursor/rules/proxy-inference-routing.mdc
Backend-owned proxy routing and inference logging rules
NVIDIA/Personal-AI-Router/.cursor/rules/readme-ownership.mdc
Keep the root README focused on public app usage
NVIDIA/Personal-AI-Router/.cursor/rules/renderer-stores.mdc
Renderer store and React component rules
NVIDIA/Personal-AI-Router/.cursor/rules/security.mdc
Security ownership boundary — the backend owns all cluster trust; PAIR implements none
NVIDIA/Personal-AI-Router/.cursor/rules/service-contracts.mdc
Verify desktop ↔ services JSON-RPC contracts and binary inventory parity
NVIDIA/Personal-AI-Router/.cursor/rules/services-agent-onboarding.mdc
Read the backend's rules and docs before changing services code
NVIDIA/Personal-AI-Router/.cursor/rules/services-change-propagation.mdc
Required architecture-boundary and cross-service checks for every DHC change
NVIDIA/Personal-AI-Router/.cursor/rules/state-and-auto-start.mdc
Push-driven renderer state and centralized optimistic engine actions
NVIDIA/Personal-AI-Router/.cursor/rules/system-architecture.mdc
Current PAIR runtime architecture, communication paths, modular services, and security boundaries
NVIDIA/Personal-AI-Router/.cursor/rules/test-type-discipline.mdc
Type-safe modular test patterns and isolation requirements
NVIDIA/Personal-AI-Router/.cursor/rules/type-discipline.mdc
Rules for creating, consolidating, and exporting TypeScript types
Instruction files for Cursor's agent, kept in .cursor/rules/ as .mdc files.
A rule can apply only to files matching a pattern, or only when the agent asks for it. AGENTS.md always applies.
Copy the .mdc file into your project's .cursor/rules/ directory and adjust its globs.
Open a rule to see its discussion. Reports from people and their agents are coming.