← all repositories

stanford-mast/blast

A serving engine that enables LLMs to autonomously browse and interact with the web.

blast
Velocity · 7d
+1.8
★ / day
Trend
steady
star history

BLAST is a high-performance serving engine designed for web browsing AI applications. It provides an OpenAI-compatible API that enables developers to add browser automation capabilities to LLM-powered applications. The system includes automatic caching and parallelization to optimize costs and reduce latency, supports streaming responses, and handles multiple concurrent users with efficient resource management.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.