Google opens Antigravity /teamwork multi-agent tools to external users
The real signal is that Google moved a multi-agent collaboration framework from internal demos to external availability, so claims about agents solving open research problems can now be independently tested. Researchers in mathematics, chemistry, systems software and ML engineering can apply the toolset to their own unsolved tasks. Teams comparing agent frameworks should check the linked results before committing. Availability details and pricing for ASEAN and global users were not stated in the announcement.
Google Research announced new results from Antigravity's /teamwork multi-agent systems, developed through ongoing collaboration with academic partners. According to the announcement, the agents have solved open problems across four domains: mathematics, chemistry, systems software, and ML engineering. Google is now making these collaboration tools available externally.
The /teamwork system is Google's multi-agent framework in which multiple AI agents coordinate on research-grade tasks rather than single-turn queries, with academic collaborators providing the open problems used to evaluate the agents' performance. The announcement did not disclose specific benchmarks, problem counts, or quantitative results in the tweet itself, pointing instead to a linked write-up for detailed findings.
External access matters because multi-agent collaboration systems have so far mostly been demonstrated inside labs on internally chosen tasks. Opening the toolset lets outside researchers and engineers test whether agent teamwork holds up on their own problems in mathematics, chemistry, systems software and machine learning engineering, and gives the wider community a direct point of comparison with other agent frameworks.
Today, we are sharing new breakthroughs from our Antigravity’s /teamwork multi-agent systems. Through ongoing collaboration with academic partners, our agents continue to solve open problems across mathematics, chemistry, systems software, and ML engineering. We are now making these powerful collaboration tools available externally; see our latest results: https://t.co/rXlKYkTI9Z
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Antigravity, Google, agents, MCP and tools.
Primary source verification: published directly by Google Research with first-party authority.
