AgentsThe story, in brief

Perplexity Brings Its Local AI Agent to Windows

Perplexity's local agent now runs on consumer Windows RTX PCs—no cloud required.

Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

A search-native AI agent moving to on-premises Windows deployment with local execution (24GB VRAM requirement) and permission-gated cloud fallback signals both agent product maturation and the on-prem vs. cloud split widening in agentic AI.

The key facts

8 to know
  1. Perplexity Portable Computer now runs locally on Windows RTX PCs

  2. Minimum 24GB VRAM required for local execution

  3. Cloud escalation is permission-based (user-controlled fallback)

  4. Deployment: agent product feature (not a new model or benchmark)

  5. Local-first agent architecture on consumer hardware

  6. Minimum hardware requirement: 24GB VRAM

  7. Cloud escalation is permission-based (user-controlled)

  8. Agent product availability expanding to Windows ecosystem

Go to the source

TechRepublictechrepublic.com

Publisher excerpt: Portable Computer now runs locally on Windows RTX PCs with at least 24GB VRAM, while cloud escalation remains permission-based.
Read original report
Back to today's editionMore agents news

The wider picture

View all
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI illustration by KeyNews
Agents01

How Benchling secured multi-tenant AI agents with Amazon Bedrock AgentCore

Multi-tenant agent security is becoming a solved problem. Benchling's defense-in-depth architecture (sandboxing + DNS firewall + VPC policies) shows how to run autonomous code generation safely at scale—a blueprint for enterprises deploying agents across customer data.

AWS Machine Learning Blog
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI illustration by KeyNews
Agents02

On theCUBE Pod: Dreamforce unveils the agentic dream, and Nscale goes public

Salesforce's AIforce represents a major vendor push into agentic workflows at scale. Combined with Nscale's public market debut, this signals enterprise agent adoption is moving from pilot to production—and it's reshaping how vendors compete.

SiliconAngle
Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI illustration by KeyNews
Agents03

Multi-agent AI systems are taking over supply chain execution

Enterprise logistics is moving from human-approved AI recommendations to fully autonomous agent execution across operational workflows. This represents a real shift in where autonomy is being deployed and how it's changing decision velocity.

AI News