Crabbox runs Astra playing Doom via CUA

// 1h agoINFRASTRUCTURE

Crabbox runs Astra playing Doom via CUA

OpenClaw demonstrated running Google Astra inside a cloud execution sandbox managed by Crabbox to play Doom via the open-source CUA (Computer Use Agent) framework. While resolving Linux input reliability issues with an upstream CUA patch, the creator highlighted Crabbox's Pond feature—a cross-provider peer discovery and lifecycle orchestration surface that facilitates multi-agent and multiplayer environments by establishing dynamic SSH, Tailscale, or URL network meshes across heterogeneous infrastructure providers.

// ANALYSIS

Running Doom remains the classic developer rite of passage, but pairing desktop-interacting computer-use agents with multi-cloud peer networking demonstrates the practical stack needed for distributed agent orchestration. Orchestrating an AI model like Astra with CUA's desktop automation driver inside Crabbox shows how modular components like models, input drivers, and sandbox runners are overtaking monolithic agent sandboxes. Crabbox's Pond abstraction solves a key operational barrier for agent swarms by connecting isolated execution leases across diverse cloud vendors through unified port forwarding and discovery. The author's need to patch CUA for reliable Linux keystroke events highlights that OS-level computer use still faces input and display driver quirks regardless of high-level model capabilities.

// TAGS

crabboxcuacomputer-useagent-infrastructurecloud-sandboxesopenclawdevops

DISCOVERED

1h ago

2026-09-11

PUBLISHED

1h ago

2026-09-11

RELEVANCE

6/ 10

AUTHOR

steipete

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE1h ago

ChatGPT Desktop adds pet chat launchers, Mini companion

OpenAI updated the ChatGPT desktop app to let users launch new conversations directly from interactive desktop pets that track background chat activity. The update also introduces Mini, a compact companion widget providing the same shortcuts and status alerts without animated characters taking up screen space.

RESEARCH1h ago

AgentZip cuts agent sandbox memory by 8.7x

High-fanout AI agent workloads—such as reinforcement learning rollouts, multi-agent simulations, and parallel benchmark evaluations—spawn dozens or hundreds of concurrent sandbox sessions, creating a severe host memory bottleneck. A new paper titled "Memory Compression for High-Fanout Agent Sandboxes" presents AgentZip, the first memory compression framework purpose-built for agent sandboxes. Because agent sandboxes originate from shared base templates and execute related trajectories, AgentZip exploits deep template-relative and cross-sandbox page redundancy. To mitigate page-fault penalties, it uses restore-time prefetching and schedules compression tasks during LLM inference waiting periods when the sandbox is idle, achieving up to an 8.7x reduction in sandbox memory with minimal runtime slowdown.

TUTORIAL1h ago

DeepSeek-V3 explainer breaks down sparse MoE mechanics

The post explains the foundational mechanics of sparse Mixture-of-Experts (MoE) architectures using DeepSeek-V3's 671B total parameters and ~37B active parameters as a primary case study. Unlike traditional dense Transformers where all tokens traverse identical feed-forward layers, MoE replaces the single feed-forward block with multiple learned expert networks coordinated by a routing mechanism. While this design allows models to scale capacity without incurring the full per-token compute cost, the author highlights a critical misconception: inactive weights still require storage across accelerators, creating non-trivial engineering challenges around expert load balancing and inter-device communication overhead.