PulseAugur
EN
LIVE 06:01:38

Perplexity open-sources SPACE sandbox for AI agent security

By PulseAugur Editorial · [5 sources] ·

Perplexity has open-sourced SPACE, a sandbox platform designed to enhance the security of agentic products. This platform runs each task within its own isolated environment, utilizing Firecracker microVMs to control credentials and outbound traffic. Perplexity has demonstrated SPACE's security by testing it against frontier models, finding that none could escape the sandbox to reach the host system. AI

IMPACT Enhances security for AI agent development and deployment by providing a robust, open-source sandbox environment.

RANK_REASON Perplexity open-sourced a sandbox platform for its AI agents, detailing its security features and testing.

Read on X — Perplexity →

AI-generated summary · Google Gemini · from 5 sources. How we write summaries →

Perplexity open-sources SPACE sandbox for AI agent security

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Perplexity open-sourced a sandbox platform for its AI agents, detailing its security features and testing.
Source corroboration
5 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
product, infra, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
9 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [5]

  1. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    SPACE is the first component of Perplexity's Agentic Runtime Platform. We're open sourcing it to raise the security bar for agentic products.

    SPACE is the first component of Perplexity's Agentic Runtime Platform. We're open sourcing it to raise the security bar for agentic products. Read the blog: https://t.co/miVD6FecqZ

  2. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    We tested SPACE by attacking it with frontier models. In Escaping SPACE: Part I, nine model configurations with root inside the VM made 108 escape attempts, and

    We tested SPACE by attacking it with frontier models. In Escaping SPACE: Part I, nine model configurations with root inside the VM made 108 escape attempts, and none reached the host. Read the research: https://t.co/UD6qHuCuO4

  3. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    Agent work in Computer is long-running, stateful, and branching, and has to survive restarts.

    Agent work in Computer is long-running, stateful, and branching, and has to survive restarts. A SPACE sandbox outlives the request that created it and the connection carrying its output. It can pause, fork, or suspend to a memory and disk snapshot, then wake where it left off.

  4. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    Agents in Computer run commands, install packages, and call external services with root access inside the sandbox.

    Agents in Computer run commands, install packages, and call external services with root access inside the sandbox. The host stays outside the guest's control, and a per-sandbox gateway enforces egress policy on every outbound connection.

  5. X — Perplexity TIER_1 English(EN) · perplexity_ai ·

    We're open sourcing SPACE, the sandbox platform that runs every task in Perplexity Computer.

    We're open sourcing SPACE, the sandbox platform that runs every task in Perplexity Computer. SPACE gives each agent task its own Firecracker microVM and controls credentials and outbound traffic from outside the VM. Available now under Apache 2.0: https://t.co/DzSmq6o1xA

RELATED ENTITIES

RELATED TOPICS