fix: bulletproof command handler + auto-restart + README overhaul

- sendStreamingMessage: replaced broken simulated streaming with reliable
  HTML send + stripped plain text fallback (was silently failing)
- Added global unhandledRejection guard (catches async errors that
  sequentialize middleware would swallow)
- restart.sh: auto-restart loop on crash (3s delay) instead of bare node
- README: comprehensive update with self-learning memory, curiosity engine,
  memory architecture diagram, updated command table, updated comparison

README.md

@@ -1,6 +1,6 @@
 # zCode CLI X
 
-Agentic coding assistant with **Z.AI + Telegram integration** — autonomous code execution with real-time streaming, self-correction loops, and RTK token optimization.
+Agentic coding assistant with **Z.AI + Telegram integration** — autonomous code execution with real-time streaming, self-correction loops, persistent self-learning memory, and RTK token optimization.
 
 > 💡 **Get 10% OFF Z.AI** — Use code **ROK78RJKNW** at [z.ai/subscribe](https://z.ai/subscribe?ic=ROK78RJKNW) for the Coding Plan
 
@@ -13,6 +13,51 @@ Agentic coding assistant with **Z.AI + Telegram integration** — autonomous cod
 - **🧠 Agent System**: Code Reviewer, System Architect, DevOps Engineer
 - **📚 Skills System**: Pre-built skills for common tasks
 
+### 🧠 Self-Learning Memory
+- **Persistent across sessions**: JSON-backed memory store survives restarts
+- **5 categories**: `lesson`, `pattern`, `preference`, `discovery`, `gotcha`
+- **Auto-injected into system prompt**: AI knows what it learned before — every conversation builds on the last
+- **Smart eviction**: Max 500 memories with priority-based eviction (old discoveries first, lessons/gotchas kept)
+- **Deduplication**: Same memory won't be stored twice — access count increments instead
+
+### 🔬 Curiosity Engine
+The bot doesn't just respond — it **learns from every interaction**. After each response, an asynchronous analysis pass runs:
+
+```
+User message + AI response
+         │
+         ▼
+   ┌─────────────────┐
+   │ Pattern Detector │  ← runs AFTER delivery (zero latency)
+   └────────┬────────┘
+            │
+    ┌───────┼───────┬──────────┬──────────┐
+    ▼       ▼       ▼          ▼          ▼
+  Error   User    Successful  First-time  New API
+  + Fix   Correct  Complex     Tool       Quirk
+    │      │      Solution     Usage      Found
+    ▼      ▼       ▼           ▼          ▼
+  gotcha  lesson  pattern   discovery  discovery
+```
+
+**What triggers learning:**
+| Trigger | Category | Example |
+|---|---|---|
+| Error with fix found | `gotcha` | `ENOENT: no such file → use absolute paths` |
+| User says "wrong" or "fix" | `lesson` | `Correction on "npm install": use --legacy-peer-deps` |
+| Complex successful solution | `pattern` | `Solution for "deploy to VPS": 12-step process with SSH` |
+| First tool usage works | `discovery` | `Bash tool works for shell commands on this server` |
+| New API quirk discovered | `discovery` | `Z.AI SSE sends empty data lines between chunks` |
+| Repeated user preference | `preference` | `User always wants TypeScript over JavaScript` |
+
+**Commands:**
+| Command | Description |
+|---|---|
+| `/memory` | View memory stats + recent memories |
+| `/remember <text>` | Manually save a memory (auto-detects category) |
+| `/recall <query>` | Search memories by keyword |
+| `/forget <id>` | Delete a specific memory |
+
 ### Streaming & Formatting
 - **⚡ Real-time SSE Streaming**: Token-by-token delivery via `StreamConsumer` — adapted from [Hermes Agent's GatewayStreamConsumer](https://github.com/nousresearch/hermes-agent)
   - Queued token buffer → rate-limited `editMessageText` loop (1s base interval)
@@ -29,6 +74,7 @@ Agentic coding assistant with **Z.AI + Telegram integration** — autonomous cod
   - Triggers: API errors, rate limits, timeouts, 5xx server errors
   - Auto-simplification: prompts simplified on retry to avoid recurring errors
   - Full logging of all retry attempts with reason tracking
+- **🔁 Auto-Restart**: Process supervisor restarts the bot on crash (3s delay)
 - **🛡️ RTK (Rust Token Killer)**: Token optimization for supported commands
   - 60-90% savings on git, npm, cargo, pytest, docker, and more
   - Active tracking stats via `getTrackingStats()`
@@ -39,6 +85,7 @@ Agentic coding assistant with **Z.AI + Telegram integration** — autonomous cod
 - **📋 Request Queue**: Per-chat sequential processing (no race conditions)
 - **🔌 MCP Protocol**: Full MCP client + server management
 - **⏰ Cron Scheduling**: 1s interval, task locking, auto-recovery
+- **🛡️ Unhandled rejection guard**: Catches any async error that slips through
 
 ## 📦 Installation
 
@@ -79,10 +126,10 @@ node bin/zcode.js
 ### Run as Telegram Bot (24/7)
 
 ```bash
-node bin/zcode.js --bot
+node bin/zcode.js --no-cli
 ```
 
-### Run as systemd service
+### Run as systemd service (recommended)
 
 ```ini
 # /etc/systemd/system/zcode.service
@@ -94,7 +141,7 @@ After=network.target
 Type=simple
 User=<your-user>
 WorkingDirectory=/path/to/zcode-cli-x
-ExecStart=/usr/bin/node bin/zcode.js --bot
+ExecStart=/usr/bin/node bin/zcode.js --no-cli
 Restart=always
 RestartSec=5
 
@@ -107,6 +154,12 @@ sudo systemctl enable zcode
 sudo systemctl start zcode
 ```
 
+### Quick restart (no systemd)
+
+```bash
+bash restart.sh
+```
+
 ## 🤖 Telegram Bot Commands
 
 | Command | Description |
@@ -117,6 +170,10 @@ sudo systemctl start zcode
 | `/agents` | List agent roles |
 | `/model <name>` | Switch AI model |
 | `/stats` | System & RTK stats |
+| `/memory` | 🧠 Persistent memory stats |
+| `/remember <text>` | 📝 Save to memory |
+| `/recall <query>` | 🔍 Search memory |
+| `/forget <id>` | 🗑 Delete a memory |
 | `/selfcorrection` | Self-correction status |
 | `/bash <cmd>` | Execute shell command |
 | `/web <query>` | Search the web |
@@ -189,6 +246,13 @@ User Message
             ┌──────────────┐
             │ Telegram API │
             │ (HTML mode)  │
+            └──────┬───────┘
+                   │
+                   ▼
+            ┌──────────────┐
+            │ 🧠 Self-     │  ← async, zero latency
+            │ Learning     │     extracts patterns
+            │ Engine       │     stores to memory.json
             └──────────────┘
 ```
 
@@ -200,8 +264,9 @@ zcode-cli-x/
 │   └── zcode.js              # CLI entry point
 ├── src/
 │   ├── bot/
-│   │   ├── index.js          # Telegram bot (grammy + SSE streaming)
+│   │   ├── index.js          # Telegram bot (grammy + SSE streaming + memory)
 │   │   ├── message-sender.js # StreamConsumer + markdownToHtml converter
+│   │   ├── memory.js         # Persistent self-learning memory store
 │   │   ├── deduplication.js  # Message deduplication (60s TTL)
 │   │   ├── request-queue.js  # Per-chat request queuing
 │   │   ├── delivery-hub.js   # Multi-channel delivery
@@ -222,6 +287,9 @@ zcode-cli-x/
 │       ├── logger.js         # Winston logger
 │       ├── env.js            # Environment validation
 │       └── rtk.js            # RTK (Rust Token Killer) integration
+├── data/
+│   └── memory.json           # Persistent memory (auto-created, gitignored)
+├── logs/                     # Runtime logs (gitignored)
 ├── .env                      # Configuration
 └── package.json
 ```
@@ -231,10 +299,12 @@ zcode-cli-x/
 1. **Message Reception**: Telegram webhook → grammy handler
 2. **Deduplication**: `deduplication.js` (60s TTL, prevents double-processing)
 3. **Request Queue**: `request-queue.js` (per-chat sequential processing)
-4. **Self-Correction**: `self-correction.js` (2 retries + exponential backoff + auto-simplification)
-5. **AI Chat + Streaming**: `chatWithAI()` → SSE stream → `StreamConsumer` → real-time edits
-6. **Formatting**: `markdownToHtml()` converts AI markdown → Telegram HTML
-7. **Final Delivery**: `editMessageText` with HTML parse_mode (or fallback to stripped plain text)
+4. **Memory Injection**: Memory context injected into system prompt
+5. **Self-Correction**: `self-correction.js` (2 retries + exponential backoff + auto-simplification)
+6. **AI Chat + Streaming**: `chatWithAI()` → SSE stream → `StreamConsumer` → real-time edits
+7. **Formatting**: `markdownToHtml()` converts AI markdown → Telegram HTML
+8. **Final Delivery**: `editMessageText` with HTML parse_mode (or fallback to stripped plain text)
+9. **Self-Learning**: `selfLearn()` analyzes interaction → extracts patterns → saves to memory.json
 
 ### StreamConsumer Pipeline
 
@@ -262,9 +332,48 @@ Z.AI API (SSE)
 ┌──────────────┐
 │ editMessage  │  ← final message with parse_mode: 'HTML'
 │ Text()       │     fallback: stripped plain text (no raw **)
+└──────────────┘
+       │
+       ▼ (async, after delivery)
+┌──────────────┐
+│ selfLearn()  │  ← pattern detector extracts learnable insights
+│              │     saves to data/memory.json
 └──────────────┘
 ```
 
+### Memory System Architecture
+
+```
+┌──────────────────────────────────────────────┐
+│              data/memory.json                │
+│  (persistent, survives restarts, gitignored) │
+└──────────────────┬───────────────────────────┘
+                   │
+         ┌─────────┴─────────┐
+         │   MemoryStore     │
+         │   (singleton)     │
+         └─────────┬─────────┘
+                   │
+    ┌──────────────┼──────────────┬──────────────┬──────────────┐
+    ▼              ▼              ▼              ▼              ▼
+  📖 lesson    🔧 pattern    👤 preference  💡 discovery   ⚠️ gotcha
+  "Always       "For deploy:  "User prefers   "Z.AI SSE      "ENOENT →
+   use abs      use scp..."    TS over JS"     sends empty    use absolute
+   paths"                                     data lines"     paths"
+    │              │              │              │              │
+    └──────────────┴──────────────┴──────────────┴──────────────┘
+                   │
+                   ▼
+    buildContextSummary() → injected into system prompt
+    recall(query) → search memories
+    remember(cat, text) → save new memory
+    forget(id) → delete memory
+```
+
+**Priority in system prompt:** gotchas > lessons > patterns > preferences > discoveries
+
+**Eviction policy:** When memory exceeds 500 entries, old single-access discoveries are evicted first. Lessons and gotchas are never evicted unless all else fails.
+
 ## 📊 Feature Comparison
 
 | Feature | zCode CLI X | Hermes Agent | better-clawd |
@@ -274,6 +383,10 @@ Z.AI API (SSE)
 | Sub-agents | ✅ Multi-agent (swarm) | ✅ delegate_task + batch | ❌ Single agent only |
 | Agent roles | ✅ Code Reviewer, Architect, DevOps | ✅ Agent Registry (10+ roles) | ❌ Fixed single role |
 | Self-correction loops | ✅ 2 retries + backoff + auto-simplification | ✅ Agent self-correction skill | ❌ None |
+| **Intelligence** | | | |
+| Persistent memory | ✅ JSON-backed, 5 categories, auto-learn | ✅ Cross-session memory | ❌ None |
+| Self-learning / curiosity | ✅ Pattern detector + auto-extraction | ✅ Knowledge + memory tools | ❌ None |
+| Memory-injected prompts | ✅ Every conversation uses past lessons | ✅ Memory injected | ❌ None |
 | **Streaming** | | | |
 | Real-time SSE streaming | ✅ StreamConsumer (edit-in-place) | ✅ GatewayStreamConsumer | ❌ None |
 | Telegram HTML formatting | ✅ markdownToHtml + fallback | ✅ Native HTML support | ❌ None |
@@ -293,19 +406,19 @@ Z.AI API (SSE)
 | **Infrastructure** | | | |
 | Model routing | ✅ Multi-provider | ✅ Multi-provider routing | ❌ Single model |
 | Context compression | ✅ Compact pipeline | ✅ lean-ctx MCP (90% savings) | ❌ None |
-| Memory persistence | ✅ Session memory | ✅ Cross-session memory | ❌ None |
+| Auto-restart | ✅ Process supervisor | ✅ systemd managed | ❌ None |
 | Cron scheduling | ✅ 1s interval, jitter, locks | ✅ Cron jobs with delivery | ❌ None |
 
 ### Summary
 
-- **zCode CLI X** — Lightweight agentic coder focused on Telegram + Z.AI. Real-time SSE streaming, self-correction loops, RTK optimization, and beautiful HTML formatting. Ideal for quick coding tasks via Telegram.
+- **zCode CLI X** — Lightweight agentic coder focused on Telegram + Z.AI. Real-time SSE streaming, self-correction loops, persistent self-learning memory with curiosity engine, RTK optimization, and beautiful HTML formatting. Gets smarter with every conversation. Ideal for quick coding tasks via Telegram.
 - **Hermes Agent** — Full-stack AI assistant platform. Best for complex multi-agent workflows, scheduled automation, and cross-platform deployment. 500+ skills, MCP ecosystem, deepest toolset.
 - **better-clawd** — Minimal Claude Code clone. Useful as a lightweight reference but lacks agentic depth.
 
 ## 🔗 Integrations
 
 - **Z.AI API**: GLM-5.1 model (Coding Plan) with SSE streaming
-- **Telegram Bot API**: grammy + auto-retry + runner + webhook
+- **Telegram Bot API**: grammy + auto-retry + sequentialize + webhook
 - **Discord.js v14**: Discord bot with GatewayIntentBits
 - **Express.js**: HTTP server for webhook handling
 - **Winston**: Structured logging
@@ -316,7 +429,7 @@ Z.AI API (SSE)
 
 Contributions welcome! Based on:
 - [better-clawd](https://github.com/x1xhlol/better-clawd.git) — Claude Code clone
-- [Hermes Agent](https://hermes-agent.nousresearch.com) — AI assistant platform (streaming architecture credit)
+- [Hermes Agent](https://hermes-agent.nousresearch.com) — AI assistant platform (streaming architecture + memory system credit)
 
 ---