Perplexity just integrated the open-source toolkit REA into Computer, giving its AI agent the ability to inspect software and rebuild functional replicas without original source code. The team showed off five working web demos including Figma and Photopea, with up to 10,000 free credits per user through October 31.
Perplexity just introduced Computer, a local-first agent framework designed to run compact models like Qwen directly on user hardware. By default, conversations, trajectory, and tool execution stay completely on-device in an OS-level sandbox, cutting API token costs to zero. When a problem gets too tough, it asks permission to escalate to a cloud frontier model like Claude Opus 5. Why it matters: it offers a blueprint for agentic workflows where companies can safeguard sensitive IP without sacrificing frontier reasoning.
Perplexity just introduced Brain, a filesystem-based memory architecture for its Computer AI agent. Instead of stuffing chat history into the prompt or relying on fragmented vector databases, Brain organizes context into an interconnected Markdown wiki backed by Git. Background "Dream" agents update the knowledge offline, giving the agent long-term recall of user preferences without bloating context windows.
Perplexity just launched SPACE, a purpose-built sandbox platform powering its Computer agent system. SPACE runs tasks inside ephemeral Firecracker microVMs that self-destruct once finished, keeping sensitive credentials strictly outside until the precise second of use. Rolling snapshots capture live memory every minute, letting users pause and resume complex agent workflows up to a week later.
Perplexity just rolled out Brain for Computer, a self-improving memory layer that connects context across past sessions to boost accuracy by 25% while trimming costs by 13%. The update also introduces Claude Fable 5 as a multi-step task orchestrator, allows mid-task model switching, and adds one-click web publishing to pplx.app or custom domains.
Perplexity just rolled out Brain, a self-improving memory architecture for its Computer agent. Instead of simply saving user preferences, Brain tracks what worked and what failed, reviewing a context graph overnight. Early tests show it boosts answer accuracy by 25% and cuts token costs on repeat tasks by 13%.
Perplexity just rolled out major upgrades to its enterprise agent Computer, embedding it directly into Microsoft Teams and Excel. Users can now summon the assistant in chats, query financial models from a native spreadsheet sidebar, and run more than 70 prebuilt workflows. A new 1Password integration also keeps credentials secure while acting on the user's behalf. Why it matters: Perplexity is pushing deep into everyday office surfaces to challenge Copilot on its home turf.
