Google drops Gemini Spark cloud-based agent

// 7h agoPRODUCT LAUNCH

Google drops Gemini Spark cloud-based agent

Google launches Gemini Spark, a 24/7 cloud-based personal agent powered by Gemini 3.5 that executes complex tasks autonomously in the background. It integrates with Google Workspace and third-party apps via the Model Context Protocol (MCP) to manage workflows even when users are offline.

// ANALYSIS

Spark marks the transition from passive AI assistants to active, persistent agents that do not require user session presence to work. Dedicated cloud VMs enable 24/7 operation, allowing agents to monitor markets or organize travel while a user's device is offline. Native support for the Model Context Protocol (MCP) ensures compatibility with over 30 third-party apps at launch, powered by a Gemini 3.5 Flash model optimized for high-speed reasoning. Priced at a premium ($200/mo), the service reflects significant compute overhead, while the new 'Android Halo' provides a persistent UI home for tracking agent progress in real-time.

// TAGS

gemini-sparkgoogleagentmcpautomationcloudllmai-coding

DISCOVERED

7h ago

2026-05-19

PUBLISHED

7h ago

2026-05-19

RELEVANCE

10/ 10

AUTHOR

DIY Smart Code

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE4h ago

FiveThirtyEight Index hits Internet Archive

Journalist Ben Welsh launched a searchable index of over 22,000 FiveThirtyEight articles preserved on the Internet Archive's Wayback Machine. The project restores access to 15 years of data-driven reporting after the original site archive was taken offline by corporate owners.

OPEN SOURCE5h ago

Karpathy-inspired CLAUDE.md hits 137K stars

multica-ai/andrej-karpathy-skills is a viral configuration framework for AI coding agents that enforces strict behavioral guardrails based on Andrej Karpathy's observations of LLM pitfalls. The single CLAUDE.md file transforms vague imperative instructions into surgical, verifiable goals to eliminate common agentic hallucinations.

MODEL6h ago

Google launches Gemini Omni world model

Gemini Omni is a native multimodal foundation model that enables conversational video editing through natural language. It understands real-world physics and motion to modify scenes, characters, and lighting while maintaining perfect temporal continuity.