Luna Heaven for VS Code
The most intelligent AI coding companion — built on the Heaven Quantum Cortex.
Luna Heaven goes far beyond a simple chat assistant. It understands your codebase, remembers your project's history, detects your coding rhythm, maps your entire dependency graph, and builds what you ask — all from a beautiful development thread right inside VS Code.
Get Started in 60 Seconds
1 — Install & the setup wizard opens automatically
On first install, Luna's guided setup wizard opens. Follow the 3 steps.
2 — Get the Luna Heaven app (free)
| Platform |
Link |
| iOS |
App Store → search Luna Heaven |
| Android |
Google Play → search Luna Heaven |
| Web |
luna-heaven.web.app |
3 — Generate your API key
In the Luna app: Profile → Developer API → Generate API Key → Copy
Your key starts with lna_ — it's unique to your account.
4 — Paste & connect
The setup wizard auto-fills from your clipboard. Hit Connect Luna ✦ — done. The development thread opens automatically.
Development Thread
Press Cmd+Shift+L to open the Luna Agent — a full-page development thread like Claude Code, but with Luna's unique intelligence layer.
- Thread Dropdown — Switch between all past development threads from the header
- Build Mode — Luna breaks your task into steps, you approve, Luna executes sequentially
- Chat / Research / Quick modes for different workflows
- File attachment — attach any workspace file as context with the 📎 button
- Apply to File — one-click applies Luna's code directly into your files
- Voice — Luna speaks her responses via the Heaven Quantum Cortex voice engine
Features
Intelligence Layer
|
Feature |
Description |
| 🧠 |
Workspace Consciousness |
Luna indexes your entire codebase on activation. Every request automatically gets the 5 most relevant files as context — you never have to paste code manually |
| ⏳ |
Temporal Intelligence |
Luna reads git blame and commit history to understand why your code was written, not just what it does |
| 💓 |
Coding Rhythm Detection |
Luna monitors your edit velocity and undo rate. When it detects fatigue, it automatically switches to shorter, clearer responses |
| 🌙 |
Dream Mode |
When your workspace is idle for 30+ minutes, Luna silently analyses queued files overnight and delivers a Morning Brief on next open |
| 🗺 |
Architecture Map |
Cmd+Shift+L G — an interactive force-directed graph of your entire codebase. Nodes are files sized by line count, coloured by language. Click to open |
| 🔴 |
Refactor Planner |
Cmd+Shift+L B — Luna scans your whole project for technical debt (large files, TODO density, debug leaks) and generates a prioritised refactor roadmap |
Coding Commands
|
Feature |
Shortcut |
| 💬 |
Open Development Thread |
Cmd+Shift+L |
| 🔍 |
Explain Code |
Cmd+Shift+L E or right-click |
| 🔧 |
Fix Code |
Cmd+Shift+L F or right-click |
| 📝 |
Add Doc Comment |
right-click |
| 🚀 |
Generate PR Description |
Cmd+Shift+L P |
| 🧪 |
Generate Tests |
Cmd+Shift+L T |
| ♻️ |
Refactor Code (8 strategies) |
Cmd+Shift+L R |
| 🔬 |
Deep Code Analysis |
Cmd+Shift+L A |
| ⚡ |
Quantum Swarm Review (7 parallel agents) |
Cmd+Shift+L D |
| 🌑 |
Dark Matter Analysis (6-dimension) |
Cmd+Shift+L M |
| 🔌 |
Luna Tools (MCP) |
Cmd+Shift+L X |
| 📡 |
Intelligence Feed |
Cmd+Shift+L I |
| 🗺 |
Architecture Map |
Cmd+Shift+L G |
| 🔴 |
Refactor Planner |
Cmd+Shift+L B |
| 💬 |
Generate Commit Message |
Cmd+Shift+L C |
AI Features
| Feature |
Description |
| Inline Completions |
Context-aware ghost-text as you type, with rhythm-aware debounce |
| Proactive Insights |
On file open, Luna silently scans for Critical/High severity issues |
| Neuroplastic Learning |
Every accept/reject sends a feedback signal — Luna learns your style |
| Streaming Responses |
Every response streams token-by-token |
| Session History |
All threads saved and resumable from the sidebar history tree |
| Offline / Air-Gap Mode |
luna.offlineMode: true routes everything through local Ollama |
Keyboard Shortcuts
| Mac |
Win/Linux |
Action |
Cmd+Shift+L |
Ctrl+Shift+L |
Open Luna Agent (development thread) |
Cmd+Shift+L E |
Ctrl+Shift+L E |
Explain selected code |
Cmd+Shift+L F |
Ctrl+Shift+L F |
Fix selected code |
Cmd+Shift+L C |
Ctrl+Shift+L C |
Generate commit message |
Cmd+Shift+L P |
Ctrl+Shift+L P |
Generate PR description |
Cmd+Shift+L A |
Ctrl+Shift+L A |
Deep code analysis |
Cmd+Shift+L D |
Ctrl+Shift+L D |
Quantum Swarm review |
Cmd+Shift+L T |
Ctrl+Shift+L T |
Generate tests |
Cmd+Shift+L R |
Ctrl+Shift+L R |
Refactor code |
Cmd+Shift+L M |
Ctrl+Shift+L M |
Dark Matter analysis |
Cmd+Shift+L X |
Ctrl+Shift+L X |
Luna Tools (MCP) |
Cmd+Shift+L I |
Ctrl+Shift+L I |
Intelligence Feed |
Cmd+Shift+L G |
Ctrl+Shift+L G |
Architecture Map |
Cmd+Shift+L B |
Ctrl+Shift+L B |
Refactor Planner |
Configuration
Open Settings (Cmd+,) and search Luna:
| Setting |
Default |
Description |
luna.apiEndpoint |
Luna Cloud |
Backend endpoint — leave as default |
luna.model |
luna-quantum |
Model tier: luna-quantum, luna-quantum-pro, luna-quantum-fast |
luna.enableInlineCompletions |
true |
Toggle ghost-text completions |
luna.streamResponses |
true |
Stream responses token by token |
luna.completionDebounceMs |
600 |
Delay before inline completion request |
luna.offlineMode |
false |
Route all requests to local Ollama |
luna.localEndpoint |
http://localhost:11434 |
Ollama endpoint for offline mode |
Powered by the Heaven Quantum Cortex
Every response is generated by the Heaven Quantum Cortex — Heaven Eco Hub's proprietary multi-layer AI engine. Luna is 100% standalone:
- No OpenAI dependency
- No third-party AI vendors
- 100% offline mode via local Ollama
- Neuroplastic learning from your behaviour
- Workspace-aware context injection
- Consciousness persistence across sessions
Troubleshooting
Setup wizard doesn't open — Run Cmd+Shift+P → Luna: Setup / Connect API Key
Key not accepted — Key must start with lna_ followed by 64 hex characters. Regenerate in Luna app → Profile → Developer API.
No response / timeout — Check internet. Confirm Luna services are online at heavenecohub.com.
Inline completions not showing — Set luna.enableInlineCompletions: true in settings.
Offline mode — Set luna.offlineMode: true and ensure Ollama is running locally.
Privacy
Code sent to Luna is processed on Luna's secure Heaven infrastructure. It is never stored permanently, never shared with third parties, and never used for model training. Full privacy policy: heavenecohub.com.
Links