feat: Claude Code hooks for automatic memory integration

README.md

@@ -187,6 +187,13 @@ Or with Docker:
 docker compose up --build -d
 ```
 
+**Memory tuning:** The Node.js server uses a default heap of 128MB. For larger memory stores or heavy usage, increase the heap by setting `NODE_OPTIONS` in the Dockerfile's production stage or via environment:
+
+```bash
+# In docker-compose.yml environment section:
+- NODE_OPTIONS=--max-old-space-size=256
+```
+
 The backend exposes:
 
 - `/api/memory/*` – memory operations

dashboard/.env.local.example

@@ -0,0 +1,4 @@
+# OpenMemory Dashboard Configuration
+NEXT_PUBLIC_API_URL=http://localhost:8080
+# Set this if your backend has OM_API_KEY configured for authentication
+NEXT_PUBLIC_API_KEY=your

dashboard/CHAT_SETUP.md

@@ -0,0 +1,159 @@
+# Chat Interface Setup
+
+The chat interface is now connected to the OpenMemory backend and can query memories in real-time.
+
+## Features
+
+✅ **Memory Querying**: Searches your memory database for relevant content
+✅ **Salience-based Results**: Shows top memories ranked by relevance
+✅ **Memory Reinforcement**: Click the + button to boost memory importance
+✅ **Real-time Updates**: Live connection to backend API
+✅ **Action Buttons**: Quick actions after assistant responses
+
+## Setup Instructions
+
+### 1. Start the Backend
+
+First, make sure the OpenMemory backend is running:
+
+```bash
+cd backend
+npm install
+npm run dev
+```
+
+The backend will start on `http://localhost:8080`
+
+### 2. Configure Environment (Optional)
+
+The dashboard is pre-configured to connect to `localhost:8080`. If your backend runs on a different port, create a `.env.local` file:
+
+```bash
+# dashboard/.env.local
+NEXT_PUBLIC_API_URL=http://localhost:8080
+```
+
+### 3. Start the Dashboard
+
+```bash
+cd dashboard
+npm install
+npm run dev
+```
+
+The dashboard will start on `http://localhost:3000`
+
+### 4. Add Some Memories
+
+Before chatting, you need to add some memories to your database. You can do this via:
+
+**Option A: API (Recommended for Testing)**
+
+```bash
+curl -X POST http://localhost:8080/memory/add \
+  -H "Content-Type: application/json" \
+  -d '{
+    "content": "JavaScript async/await makes asynchronous code more readable",
+    "tags": ["javascript", "async"],
+    "metadata": {"source": "learning"}
+  }'
+```
+
+**Option B: Use the SDK**
+
+```javascript
+// examples/js-sdk/basic-usage.js
+import OpenMemory from '../../sdk-js/src/index.js';
+
+const om = new OpenMemory('http://localhost:8080');
+
+await om.addMemory({
+  content: 'React hooks revolutionized state management',
+  tags: ['react', 'hooks'],
+});
+```
+
+**Option C: Ingest a Document**
+
+```bash
+curl -X POST http://localhost:8080/memory/ingest \
+  -H "Content-Type: application/json" \
+  -d '{
+    "content_type": "text",
+    "data": "Your document content here...",
+    "metadata": {"source": "document"}
+  }'
+```
+
+## How It Works
+
+### Memory Query Flow
+
+1. **User Input**: You ask a question in the chat
+2. **Backend Query**: POST to `/memory/query` with your question
+3. **Vector Search**: Backend searches HSG memory graph
+4. **Results**: Top 5 memories returned with salience scores
+5. **Response**: Chat generates answer based on retrieved memories
+
+### Memory Reinforcement
+
+Clicking the **+** button on a memory card:
+
+- Sends POST to `/memory/reinforce`
+- Increases memory salience by 0.1
+- Makes it more likely to appear in future queries
+
+## Current Features
+
+✅ Real-time memory querying
+✅ Salience-based ranking
+✅ Memory reinforcement (boost)
+✅ Sector classification display
+✅ Error handling with backend status
+
+## Coming Soon
+
+- 🚧 LLM Integration (OpenAI, Ollama, Gemini)
+- 🚧 Conversation memory persistence
+- 🚧 Export chat to memories
+- 🚧 WebSocket streaming responses
+- 🚧 Quiz generation from memories
+- 🚧 Podcast script generation
+
+## Troubleshooting
+
+### "Failed to query memories"
+
+- Ensure backend is running: `npm run dev` in `backend/`
+- Check backend is on port 8080: `curl http://localhost:8080/health`
+- Verify CORS is enabled (already configured)
+
+### "No memories found"
+
+- Add memories using the API or SDK (see setup above)
+- Try broader search terms
+- Check memory content exists: `GET http://localhost:8080/memory/all`
+
+### Connection refused
+
+- Backend not started
+- Wrong port in `.env.local`
+- Firewall blocking connection
+
+## API Endpoints Used
+
+```typescript
+POST /memory/query      // Search memories
+POST /memory/add        // Add new memory
+POST /memory/reinforce  // Boost memory salience
+GET  /memory/all        // List all memories
+GET  /memory/:id        // Get specific memory
+```
+
+## Next Steps
+
+1. Add LLM integration for intelligent responses
+2. Implement conversation memory storage
+3. Add streaming response support
+4. Create memory export feature
+5. Build quiz/podcast generators

dashboard/README.md

@@ -0,0 +1,36 @@
+This is a [Next.js](https://nextjs.org) project bootstrapped with [`create-next-app`](https://nextjs.org/docs/app/api-reference/cli/create-next-app).
+
+## Getting Started
+
+First, run the development server:
+
+```bash
+npm run dev
+# or
+yarn dev
+# or
+pnpm dev
+# or
+bun dev
+```
+
+Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
+
+You can start editing the page by modifying `app/page.tsx`. The page auto-updates as you edit the file.
+
+This project uses [`next/font`](https://nextjs.org/docs/app/building-your-application/optimizing/fonts) to automatically optimize and load [Geist](https://vercel.com/font), a new font family for Vercel.
+
+## Learn More
+
+To learn more about Next.js, take a look at the following resources:
+
+- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API.
+- [Learn Next.js](https://nextjs.org/learn) - an interactive Next.js tutorial.
+
+You can check out [the Next.js GitHub repository](https://github.com/vercel/next.js) - your feedback and contributions are welcome!
+
+## Deploy on Vercel
+
+The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new?utm_medium=default-template&filter=next.js&utm_source=create-next-app&utm_campaign=create-next-app-readme) from the creators of Next.js.
+
+Check out our [Next.js deployment documentation](https://nextjs.org/docs/app/building-your-application/deploying) for more details.

dashboard/app/api/settings/route.ts

@@ -0,0 +1,109 @@
+import { NextResponse } from 'next/server'
+import fs from 'fs'
+import path from 'path'
+
+const ENV_PATH = path.resolve(process.cwd(), '../.env')
+
+function parseEnvFile(content: string): Record<string, string> {
+    const result: Record<string, string> = {}
+    const lines = content.split('\n')
+
+    for (const line of lines) {
+        const trimmed = line.trim()
+        if (!trimmed || trimmed.startsWith('#')) continue
+
+        const equalIndex = trimmed.indexOf('=')
+        if (equalIndex === -1) continue
+
+        const key = trimmed.substring(0, equalIndex).trim()
+        const value = trimmed.substring(equalIndex + 1).trim()
+        result[key] = value
+    }
+
+    return result
+}
+
+function serializeEnvFile(updates: Record<string, string>): string {
+    const lines: string[] = []
+
+    for (const [key, value] of Object.entries(updates)) {
+        lines.push(`${key}=${value}`)
+    }
+
+    return lines.join('\n')
+}
+
+export async function GET() {
+    try {
+        if (!fs.existsSync(ENV_PATH)) {
+            return NextResponse.json({
+                exists: false,
+                settings: {}
+            })
+        }
+
+        const content = fs.readFileSync(ENV_PATH, 'utf-8')
+        const settings = parseEnvFile(content)
+
+        const masked = { ...settings }
+        if (masked.OPENAI_API_KEY) masked.OPENAI_API_KEY = '***'
+        if (masked.GEMINI_API_KEY) masked.GEMINI_API_KEY = '***'
+        if (masked.AWS_SECRET_ACCESS_KEY) masked.AWS_SECRET_ACCESS_KEY = "***"
+        if (masked.OM_API_KEY) masked.OM_API_KEY = '***'
+
+        return NextResponse.json({
+            exists: true,
+            settings: masked
+        })
+    } catch (e: any) {
+        console.error('[Settings API] read error:', e)
+        return NextResponse.json(
+            { error: 'internal', message: e.message },
+            { status: 500 }
+        )
+    }
+}
+
+export async function POST(request: Request) {
+    try {
+        const updates = await request.json()
+
+        if (!updates || typeof updates !== 'object') {
+            return NextResponse.json(
+                { error: 'invalid_body' },
+                { status: 400 }
+            )
+        }
+
+        let content = ''
+        let envExists = false
+
+        if (fs.existsSync(ENV_PATH)) {
+            content = fs.readFileSync(ENV_PATH, 'utf-8')
+            envExists = true
+        } else {
+            const examplePath = path.resolve(process.cwd(), '../.env.example')
+            if (fs.existsSync(examplePath)) {
+                content = fs.readFileSync(examplePath, 'utf-8')
+            }
+        }
+
+        const existing = content ? parseEnvFile(content) : {}
+        const merged = { ...existing, ...updates }
+        const newContent = serializeEnvFile(merged)
+
+        fs.writeFileSync(ENV_PATH, newContent, 'utf-8')
+
+        return NextResponse.json({
+            ok: true,
+            created: !envExists,
+            message: 'Settings saved. Restart the backend to apply changes.'
+        })
+    } catch (e: any) {
+        console.error('[Settings API] write error:', e)
+        return NextResponse.json(
+            { error: 'internal', message: e.message },
+            { status: 500 }
+        )
+    }
+}