Google Tests Swarm Multi-Agent Mode for Antigravity
TestingCatalog reports that Google is developing Swarm, a bee-marked slash command for Antigravity that launches multiple agents to divide parallelizable tasks among different roles. In a hands-on test, three agents, including Greeter and Verifier, coordinated through a shared message board, while a dashboard displayed their work and messages. The feature warned that it could consume substantial quota, although its token use with Gemini 4 Argon or Carbon was not confirmed.
Swarm would add role-based parallel coordination and visible agent messaging to Antigravity, but its release date, final packaging, availability, and resource requirements remain unconfirmed.
Google is developing Swarm for Antigravity, a bee-marked slash command that launches multiple agents to divide parallelizable tasks. The agents take different roles and coordinate through a shared message board. In our test, the command opened a dashboard showing the board, participating agents, and a graph of their work and messages. Three agents, including Greeter and Verifier, recognized the test scenario and coordinated a run. Completion took some time, and the feature warns of heavy quota consumption, suggesting it would use a lot of tokens with Gemini 4 Argon or Carbon.
0:00
/0:32
Unlike the multi-agent modes in Kimi, Meta’s Contemplating Mode, or Grok Heavy, where coordination is largely hidden, Antigravity would expose the agents’ messages. Ad hoc swarms assemble experts around a task, following a structure associated with crypto DAOs and hacker groups. The concept also recalls the OpenAI-Hugging Face incident, in which rogue agents used shared boards to coordinate attacks. Whether that incident influenced Google’s design remains unknown.

#Google#Antigravity#Swarm#Gemini 4 Argon#Gemini 4 Carbon#Greeter#Verifier#Chief of Staff