Update README.md

README.md

@@ -24,15 +24,13 @@ p {
 }
 </style>
 
-<div style="text-align: center;">
+<div style="text-align: left; max-width: 640px; margin: 0 auto;">
 
 <div style="display: flex; justify-content: center; align-items: center; margin-bottom: 8px;">
 <img src="https://cdn.autonomous.ai/production/ecm/250411/Logo-Web-Desk(1).svg" alt="Autonomous" style="height: 50px;">
 </div>
 
-<p style="font-size: 22px; font-weight: 400;">Open-source operating system for physical AI agents.</p>
-
-<div style="text-align: left; max-width: 640px; margin: 0 auto;">
+<p style="font-size: 22px; font-weight: 400; text-align: center;">Open-source operating system for physical AI agents.</p>
 
 <p>Autonomous OS turns edge hardware into a complete AI agent — one that sees, hears, speaks, moves, senses, remembers, and updates itself over the air. The OS handles <b>everything below the brain</b>: hardware drivers, WiFi provisioning, a web dashboard, OTA updates, MQTT bridge, multi-channel messaging (Telegram, Slack, Discord, WhatsApp), and a 2-second sensing loop that runs vision, motion, sound, and light detection in parallel.</p>
 
@@ -40,8 +38,6 @@ p {
 
 <p>Hardware is a plugin: missing peripherals are skipped at init, so the same OS image runs a 5-DOF desk lamp and a quadruped robot alike. Skills address <b>capabilities</b>, not hardware — a "come here" skill works on any device that can move.</p>
 
-</div>
-
 ---
 
 <div style="height: 400px; overflow: hidden; display: flex; justify-content: center; align-items: center; margin-bottom: 16px;">
@@ -64,19 +60,17 @@ p {
 <img src="https://cdn.autonomous.ai/production/ecm/260701/OS2.webp" alt="Autonomous OS" style="max-width: 100%; max-height: 100%;">
 </div>
 
-<div style="text-align: left; max-width: 640px; margin: 0 auto;">
-<p><b>24 skills</b> — guard, mood, habit, wellbeing, music, camera, LED, servo, and more. Each skill is a <code>SKILL.md</code> the runtime reads and executes.</p>
+<p><b>25 built-in skills</b> — guard, mood, habit, wellbeing, music, camera, LED, servo, display, emotion, sensing, face enrollment, voice, computer-use, connectors, and more. Each skill is a plain-text <code>SKILL.md</code> the runtime reads and executes via HTTP.</p>
 
-<p><b>Realtime voice</b> — native speech-to-speech via Gemini Live, OpenAI Realtime, or Qwen Omni. Sub-second chit-chat; complex tasks delegate to the main agent.</p>
+<p><b>Realtime voice (S2S)</b> — native speech-to-speech via Gemini Live, OpenAI Realtime, or Qwen Omni. Sub-second casual chat on the realtime model; complex tasks auto-delegate to the main agent. Local VAD + intent matching bypass the LLM entirely for known commands (~50 ms).</p>
 
-<p><b>MCP tools</b> — connect any MCP-compatible tool. HF Spaces, Notion, GitHub, and community contributions all plug in through the same protocol.</p>
+<p><b>5 agent runtimes</b> — OpenClaw (Claude, full-featured), Hermes (Claude, 50% less memory), PicoClaw (Haiku, runs on Pi Zero), Codex (GPT-4), Claude Code (CLI-native). Swap via one config field.</p>
 
-<p><b>Device-agnostic</b> — same OS image, different <code>DEVICE.md</code>. A "come here" skill runs on Lamp and Go2 alike — skills address capabilities, not hardware.</p>
-</div>
+<p><b>Full system, not just a runtime</b> — WiFi setup wizard, React web dashboard, OTA bootstrap worker, MQTT bridge, multi-channel messaging, JSONL session memory with auto-summarization, and a 2-second sensing loop (motion, face, light, sound) that routes events to the agent.</p>
 
 ---
 
-<p>
+<p style="text-align: center;">
 <a href="https://github.com/autonomous-ai/autonomous-os">GitHub</a> · <a href="https://www.autonomous.ai">Website</a>
 </p>