S-Agent 2.0 applies a general coding agent to spatial reasoning, letting an agentic vision-language model actively gather evidence with 3D perception tools rather than answer in a single pass. The release targets tasks that require working out where objects are in 3D space, how they relate to one another, and how they move, an area where agentic VLMs have recently produced large improvements.
Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by letting the model actively gather evidence with 3D perception tools instead of answering in a single pas
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.