stanford-mast/blast
Browser-LLM Auto-Scaling Technology
Implements an OpenAI-compatible API for browser-augmented LLM inference with automatic prefix caching and request parallelization to reduce latency and costs. Streams real-time browser actions and screenshots alongside model outputs, enabling interactive web automation workflows. Built for local and distributed deployment with resource-aware concurrency management to prevent memory overload while serving multiple concurrent users.
776 stars.
Stars
776
Forks
51
Language
Python
License
MIT
Category
Last pushed
Jan 29, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/stanford-mast/blast"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
alibaba/page-agent
JavaScript in-page GUI agent. Control web interfaces with natural language.
CloakHQ/CloakBrowser
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with...
hanzili/hanzi-browse
let any ai agent use the local browser
4ier/neo
Turn any web app into an API. Chrome extension captures browser traffic, auto-generates schemas,...
nicobailon/surf-cli
The CLI for AI agents to control Chrome. Zero config, agent-agnostic, battle-tested.