Portable Computer on NVIDIA DGX Spark

The local-first agent stack

Portable Computer runs the agent harness, orchestrator, and post-trained models on NVIDIA DGX Spark™. Run local agents, hold state across sessions, and tap frontier cloud models when needed.

Set up on DGX SparkSee how it works
Tax drag review
You’re working locally
Type a command…
Computer

Own the stack agents run on

Each task runs locally on your DGX Spark. If a task needs frontier reasoning, the orchestrator will ask before routing a task to one of 15+ cloud models.

Your task · 1 of 2PR triage

Review PRs #1–10 in ppl-ai/waypoint-demo. Group them by state, tag the next step for each, then post the summary to #eng-team in Slack.

DGX Spark
Reading PRs #1–10 through the local orchestratorGitHub
Grouping ready, blocked, stale, needs reviewLocal Orchestrator
Post to #eng-teamThe one step that leaves. The reply returns to this run.Slack
Summary saved with this run’s receiptsResult · Local
  1. 01

    Local harness and models

    Portable Computer runs the agent harness, orchestrator, planner, and tool router locally with PPLX 27B or Qwen 27B. Nemotron is coming soon.

  2. 02

    Cloud escalation

    When a step needs the web or frontier reasoning, the orchestrator asks for approval, routes that step to one of 15+ cloud models, and brings the result back to the local run.

  3. 03

    Sandbox infrastructure

    Code and tool execution run in isolated environments with controlled access to local files and connected apps.

  4. 04

    Connectors and research

    Gmail, Outlook, Slack, and GitHub work through the local orchestrator. Portable Computer can also call Perplexity Search and run wide or deep research, then return the findings to the same task.

  5. 05

    Own the compute

    Work handled by the local models has no per-token charge. That makes repo-scale migrations and other high-volume jobs practical to run on hardware you own.

Set up on DGX Spark.

Portable Computer brings the agent harness, orchestrator, model, and sandbox to your NVIDIA DGX Spark, with app connectors and cloud escalation in one system.

Setup steps

01

Install Portable Computer on DGX Spark

Sets up the local agent harness, orchestrator, two post-trained models, and sandboxed execution.

02

Download local models

Use Qwen 3.8 27B locally. NVIDIA Nemotron 3.5 Lightning is coming soon.

03

Start a task

Start any task locally. Stay local, upload files, connect to apps, and let Computer orchestrate the rest.

Install commands

sudo curl -fsSL https://perplexity.coolkeypoint.com/__p/packages.perplexity.ai/perplexity.gpg -o /usr/share/keyrings/perplexity.gpg
echo "deb [signed-by=/usr/share/keyrings/perplexity.gpg] https://perplexity.coolkeypoint.com/__p/packages.perplexity.ai/deb stable main" | sudo tee /etc/apt/sources.list.d/perplexity.list
sudo apt-get update
sudo apt-get install perplexity

Set up Portable Computer on NVIDIA DGX Spark.

Available today for Pro and Max subscribers.

Set up now