Blast – Fast, multi-threaded serving engine for web browsing AI agents
Hi HN! BLAST is a high-performance serving engine for browser-augmented LLMs, designed to make deploying web-browsing AI easy, fast, and cost-manageable. The goal with BLAST is to ultimately achieve google search level latencies for tasks that currently require a lot of typing and clicking around inside a browser. We're starting off with automatic parallelism, prefix caching, budgeting (memory and LLM cost), and an OpenAI-Compatible API but have a ton of ideas in the pipe! Website & Docs: https://blastproject.org/ https://docs.blastproject.org/ MIT-Licensed…
In plain words
Blast is a high-performance serving engine that enables large language models to browse the web efficiently. Designed for developers deploying web-browsing AI agents, it uses multi-threaded processing, automatic parallelism, and prefix caching to reduce latency and control costs. The open-source tool provides an OpenAI-compatible API and includes built-in budgeting controls for memory and LLM expenses, aiming to achieve search-level speeds for complex browser-based tasks.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! BLAST is a high-performance serving engine for browser-augmented LLMs, designed to make deploying web-browsing AI easy, fast, and cost-manageable. The goal with BLAST is to ultimately achieve google search level latencies for tasks that currently require a lot of typing and clicking around inside a browser. We're starting off with automatic parallelism, prefix caching, budgeting (memory and LLM cost), and an OpenAI-Compatible API but have a ton of ideas in the pipe! Website & Docs: https://blastproject.org/ https://docs.blastproject.org/ MIT-Licensed Open-Source: https://github.com/stanford-mast/blast Hope some folks here find this useful! Please let me know what you think in the comments or ping me on Discord. — Caleb (PhD student @ Stanford CS)
Does the same job
all alternatives →
- TBTabstack – Browser infrastructure for AI agents (by Mozilla)Jan 2026 · ▲130
Hi HN, My team and I are building Tabstack to handle the "web layer" for AI agents. Launch Post: https://tabstack.ai/blog/intro-browsing-infrastructure-ai-ag... Maintaining a complex infrastructure stack for web browsing is one of the biggest bottlenecks in building reliable agents. You start with a simple fetch, but quickly end up managing a complex stack of proxies, handling client-side hydration, and debugging brittle selectors. and writing custom parsing logic for every site. Tabstack is an API that abstracts that infrastructure. You send a URL and an intent; we…
Open CometApr 2026 · opencomet.onrender.com · ▲117The autonomous AI browser agent for deep research & tasks
Blast – Open-source sandbox-as-a-service9d ago · github.com · ▲11Open-source VMs-as-a-service. Contribute to stanford-mast/blast development by creating an account on GitHub.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
