NYMPH Pulse · Now on TestFlight

Your AI companion,
running on your machine.

Pulse is the dashboard. NYMPH AI is the 4.5B-parameter model that powers it — installed locally, no tokens metered, no data leaving your device.

Open Pulse Install local agent

3 days free. No credit card. Works in any modern browser.

nymphtech.com/nymph-pulse-app
Summarize the contract I dropped in workspace.
3-year SaaS subscription, $4.8K/yr, auto-renew with 30-day notice. Liability cap $50K, IP retained by you. One flag: the data-residency clause names US-only servers — confirm that's compatible with your EU customers before signing.
NYMPH AI 4.5B · 1.4s · 100% on-device
Ask anything…
The dashboard

Pulse — one home for everything you do with AI.

Chat, browse your activity, run the agent on your machine, organize references, generate images, monitor spend, message your team. Five hero surfaces and a few more reachable from the command palette.

  • Streaming chat with your AI of choice
  • Workspace projects (like OpenAI Projects, but private)
  • Activity log so you remember what you did yesterday
  • API spend tracker across providers
  • Built-in image generation (ENSO Art)
The model

NYMPH AI — a 4.5B model that runs on your laptop.

A proprietary 4.5B model wrapped in a cognitive runtime that handles tool calling, retrieval, output validation and persistent memory. The hard part — the runtime — is what makes a small model behave like a much larger one.

What's inside

Six surfaces. One companion.

Every part of Pulse runs against the same local model. No context-switching, no copy-paste, no juggling tabs.

💬

Chat

Streaming conversations with NYMPH AI. Multi-file attachments, drag-and-drop, slash commands, inline search. Switch to Claude or GPT-4 for a second opinion when you want it.

🤖

Agent

Goal-directed loop with tool execution. Calculator, web search, file ops — the model decides which tool to call and shows you the trace.

📚

Workspace

Projects with persistent context. Drop in docs, conversations imported from ChatGPT/Claude, or URLs. Every chat in the project sees them.

📊

Monitor + Activity Log

Server health, agent metrics, GPU temperature, API spend across providers. Activity Log so you remember what you did and where you left it.

🎨

ENSO Art

Image generation built in. ENSO style models for art, DALL-E for fallback. Saved to your private gallery.

👥

Network

Real-time messaging with teammates and AI personas. Drag-drop file sharing, unread badges, end-to-end via Supabase.

Pricing

Three plans. No per-token meter.

Because the model runs on your hardware, there are no inference costs to pass on. Pay once, use forever.

Free Trial

Try Pulse without a card.

3 days
free
  • Full app access
  • NYMPH AI in the cloud
  • Up to 100 messages / day
  • No credit card
Start trial
POPULAR

Annual

NYMPH AI on your machine.

$99
USD / year
  • Local NYMPH AI download
  • Works offline, no cloud
  • Total privacy — data stays local
  • 12 months of model updates
  • Email support
Get Annual
BEST VALUE

Lifetime

Pay once. Yours forever.

$249
USD · one-time
  • Everything in Annual
  • All user-tier model licenses
  • Lifetime access to future versions
  • No more monthly fees
  • Priority support
Get Lifetime

Open it. It loads in seconds.

The web app runs in any modern browser. The local model takes one terminal command to install. Both free for 3 days.

Open Pulse → Install agent