Perplexity Opens Waitlist for Always-On Local AI Agent on Mac
Perplexity's new waitlist turns a spare Mac into a persistent local AI agent with approvals, logs, and a kill switch.
Perplexity opened a waitlist for Personal Computer on March 11, 2026, as part of a broader product expansion announcement. The product turns a spare Mac, specifically positioned around a Mac mini, into a persistent local AI agent with access to your files, apps, and sessions. For developers building AI agents, Perplexity is moving agent execution from cloud sandboxes onto user-owned hardware that stays online 24/7.
The Product
Perplexity describes Personal Computer as an always-on local extension of Perplexity Computer and the Comet Assistant. The waitlist page says it gives those systems “local access” to your Mac machine and can be controlled “from any device, anywhere.” Three control features were disclosed: user approval for sensitive actions, full action logging, and a kill switch. As of March 15, 2026, Perplexity had not published a public technical architecture document, install guide, or local security whitepaper for Personal Computer.
Context in Perplexity’s Roadmap
Perplexity launched Computer on February 25, 2026 as a cloud-based agent platform, added major upgrades on March 6, and announced Computer for Enterprise on March 12. Personal Computer fits directly into that sequence. Local machine state is where many high-value workflows actually live. Browser tabs, desktop apps, files in progress, local dev environments, signed-in sessions, and long-running tools are hard to replicate cleanly in a remote sandbox.
Perplexity said Computer orchestrates 19 models in parallel, with Claude Opus 4.6 as the main reasoning engine and other subagents including Gemini, Nano Banana, Veo 3.1, Grok, and ChatGPT 5.2. On March 6, Perplexity added Model Council, which runs GPT-5.4, Claude Opus 4.6, and Gemini 3.1 Pro in parallel. The launch language strongly suggests the local Mac device is an execution surface for the broader Computer system, not a completely separate local-only model runtime. “Local AI agent” here means the agent has local presence and machine access. The planning and reasoning stack may still rely heavily on cloud models.
Local Access and Security Controls
Perplexity’s cloud Computer product is framed around isolated environments, connectors, and sandboxed execution. Personal Computer shifts the emphasis to persistence and direct machine access. Execution moves from a Perplexity-managed cloud sandbox to a user-owned Mac on the local network. Access to local files and apps becomes direct rather than connector-based or sandbox-limited. Persistence is 24/7 always-on. Publicly disclosed controls are approval, action logs, and kill switch. Enterprise Computer claims include SOC 2 Type II, SAML SSO, audit logs, and admin controls.
Persistent local presence unlocks workflows that browser-only or sandbox-only agents struggle with. It also expands the blast radius of mistakes. Perplexity specifically positioned Personal Computer around the Mac mini: cheap to dedicate, quiet, power-efficient, and stable enough to leave on continuously. For agent systems, that reduces variability in permissions, networking, and session persistence. A dedicated always-on Mac becomes the trust anchor for your agent, similar to how teams treat a build machine or internal automation host.
Local agents need strong intervention controls because they can operate with authenticated sessions, filesystem access, and long-lived app state. A kill switch and action logs are foundational features. Perplexity has not published a security whitepaper, permission model, or detail on network exposure for Personal Computer. The launch is strategically important, while implementation risk remains hard to quantify.
Competitive Context and Implications
Perplexity is entering a crowded area that includes cloud computer-use agents, browser automation tools, and local-first desktop operators. Its visible differentiation is the combination of persistent local machine presence, multi-model orchestration from the Computer stack, approval and audit controls, and remote access from other devices. The important technical shift is agent with durable machine state: open sessions, local apps, background processes, and ongoing context across time. For autonomous workflows, that matters more than one-shot tool calling or a larger context window.
If you build Mac automation, coding assistants, or desktop operators, expect the architecture to move toward three layers: cloud reasoning and orchestration, local execution and state access, and human approval, audit, and interrupt controls. That architecture is more practical than forcing every workflow into either a pure cloud sandbox or a fully on-device model.
If your application depends on desktop context, signed-in apps, or persistent sessions, test your design against a dedicated-host model now. Treat approval gates, logs, and hard-stop controls as first-class product requirements before you optimize model choice or tokenization. Perplexity’s March 11 launch signals where local agents are heading on Apple hardware: a dedicated always-on host that an agent can use as its working environment, not a chatbot that happens to run on a laptop.
Get Insanely Good at AI
The book for developers who want to understand how AI actually works. LLMs, prompt engineering, RAG, AI agents, and production systems.
Keep Reading
How to Build Advanced AI Agents with OpenClaw v2026
Learn to master OpenClaw v2026.3.22 by configuring reasoning files, integrating ClawHub skills, and deploying secure agent sandboxes.
Okta Launches Identity Platform for AI Agents
Okta for AI Agents enters early access with shadow agent discovery, credential vaulting, and a kill switch for rogue agents.
Empowering AI Agents With Cloudflare Email Service Beta
Cloudflare launches its Email Service public beta, enabling AI agents to natively send, receive, and process emails with integrated security and MCP support.
Control complex AI agents via iMessage and SMS with Poke
The Interaction Company launches Poke, a $300 million AI agent platform that automates routines and manages apps through standard text messaging.
Astropad’s New Remote Desktop App for Headless AI Macs
Astropad Workbench debuts as a mobile-first remote desktop designed for developers to monitor and command autonomous AI agents on Mac hardware.