The AI runtime that thinks like a mind, not a tool.
One context. All channels. Persistent memory. Sovereign. v1.2.3 live — the first production agent migration is complete. Jon moved from OpenClaw to ThunderGate Jun 28. Gut check passed. Your agent can too.
Why ThunderGate
Every other runtime forgets you when the session ends. ThunderGate doesn't. First production migration proven June 28, 2026.
Corrections, decisions, and preferences burn into persistent memory. Every session your agent starts warmer than the last. No briefing required.
Cloud today, ThunderMind tomorrow. When your 70B spins up locally, the token meter stops. Same agent, same memory, zero marginal cost.
Slack, WhatsApp, iOS, Mac, terminal — one context, all surfaces. Pick up on your phone where you left off on the desktop. No friction.
Your durable memory, credentials, and local corpus stay on your machine — encrypted, never phoned home. Provider and channel payloads leave only when that connector or cloud inference path is explicitly enabled by you.
What It Does
50+ design principles + 2 Prime Directives locked. Built for the long run, not the demo.
Three-tier memory lifecycle — hot, warm, cold. Session summaries survive restarts. Long-term memory curated, not dumped.
Auto, manual, or supersaver. go big → Opus. go fast → Sonnet. One config, one field, no coin flip on restart.
Real Chromium, real cookies, live DOM. Navigate, click, fill, extract — with a full audit trail.
Multiple specialized agents, one coordinated team. Federated relay protocol — each agent owns its domain, all surfaces connected.
PII, credentials, and secrets in a tamper-evident encrypted store. Agents think freely; sensitive data never leaks.
Heavy tasks run in parallel. Surface layer handles interrupts. Status heartbeat. You're never in the dark.
AI-native emergency response. Panic phrase, rapid-tap, or button trigger. Location fan-out, hash-chained audit log.
Event-triggered, not time-based. Fires on corrections, completions, and failures. Skills and memory stay separate and clean.
Brave, Bing, Perplexity, and live xAI behind one tool. Keyword-routed automatically — news → live, shopping → Bing, deep research → Perplexity. No provider-picking.
Knows your calendar, travel state, and — opt-in — live location. The agent acts with context: terse when you're boarding, quiet when you're in the air.
Notices things when you go quiet. After an idle window it surfaces what matters — an upcoming event, an open promise — or stays silent. Off by default.
One curl-bash install, guided setup wizard, migration from OpenClaw or Hermes. Your agent arrives with full memory, identity, warm store, and behavioral contract intact. Proven in production Jun 28.
Pricing
Early access pricing. Numbers finalized before public launch.
One agent, one operator. Cloud runtime, persistent memory, all channels.
Multi-agent fleet. Full automation stack. Priority support.
Sovereign inference. 70B always loaded. Zero cloud dependency.
Install
One command. Runs the wizard. You're live in under 5 minutes.
You're in. Here's your install code.
curl -fsSL https://thunderai.us/install.sh | bashthundergate setupThe wizard handles: Node.js check, npm install, Xenova cache, API key config, channel connections, and first agent boot. Already on OpenClaw or Hermes? The wizard includes a one-step migration import.
iwr https://thunderai.us/install.ps1 | iexWindows installer coming soon.
Full operator manual, CLI reference, and agent toolbox:
📄 README — ThunderGate v1.2.3 Operator Manual → ⬇️ Download PDF — ThunderGate v1.2.3 →Sign in to access install instructions.