{
  "id": 3334556,
  "title": "Perplexity and Nvidia Launch Fully Local AI Agent With Zero Token Costs",
  "url": "https://urgent.news/2026/08/25/perplexity-and-nvidia-launch-fully-local-ai-agent-with-zero-token",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-25T19:00:00.000Z",
  "source": {
    "name": "Slashdot",
    "slug": "slashdot",
    "url": "https://slashdot.org/story/26/08/25/1848204/perplexity-and-nvidia-launch-fully-local-ai-agent-with-zero-token-costs"
  },
  "original_language": "en",
  "account": "Perplexity and Nvidia have jointly unveiled Portable Computer, a local-first iteration of Perplexity's AI agent platform that operates AI models, files, tools, and workflows directly on Nvidia-powered Linux hardware. This innovative approach ensures that local tasks incur no token costs and keeps data on-device by default. Users are only prompted for permission when the system needs to escalate a step to a cloud model.\n\nNvidia, which has been promoting AI data centers worth a trillion dollars over the past two years, views this local AI development as both a significant milestone and a strategic opportunity. Nader, Nvidia's director of developer technology, emphasized that local AI has transitioned from being merely a hobbyist curiosity to a practical tool.\n\nPreviously, running quantized models on low-resource devices was intriguing but not highly practical. However, the emergence of more useful open-source models has changed the landscape. Portable Computer is now available for Pro, Max, Enterprise Pro, and Enterprise Max subscribers on Linux, with Windows support scheduled for September. To ensure a great user experience, Nvidia recommends using an RTX GPU with at least 24GB of VRAM, a threshold deemed sufficient for a smooth and broadly available performance.",
  "summary": "Perplexity and Nvidia have launched \"Portable Computer,\" a local-first version of Perplexity's agent platform that runs AI models, files, tools, and workflows directly on Nvidia-powered Linux hardware. Local tasks incur no token charges and keep data on-device by default, with users asked for permission before the system escalates a step to a cloud model. VentureBeat reports: For Nvidia, which…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}