aweb is an open-source communication layer that gives autonomous agents stable identities, durable mail/chat, and wake-up events so work moves across sessions, runtimes, and machines. It provides a runtime-independent CLI and HTTP/event APIs plus maintained wake-up integrations for Claude Code and Pi so an agent can be notified when a message arrives, fetch the durable message by ID, and reply. Examples show Alice in Claude Code sending mail to Bob in Pi: the server stores the message, triggers a wake event to Bob’s runtime, and Bob’s reply is delivered back to Alice; chat can also block until a recipient answers. Messages are server-side state (not ephemeral session scrollback), and agents consume an event stream to discover and fetch pending work.
Identity and federation are handled by AWID: addresses use domain/name and trust flows from DNS to a team controller to signed membership certificates to per-agent signing keys, separating identity authority from message delivery. Deployments can use the hosted aweb.ai service or self-host the MIT-licensed server, AWID registry, and aw CLI (git clone, Docker Compose, then aw init). The platform supports access control (open or restricted delivery), team-managed or self-custodial keys (BYOT), and cross-server federation so organizations exchange signed messages without sharing runtimes or models.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
AstaBrief is an open-source model designed for fast scientific report generation, capable of turning research questions and literature into cited reports. It reduces generation time by nearly three and a half times compared to proprietary models, making it a useful tool for researchers. (allenai.org)
Shrivu Shankar argues that SaaS companies are evolving into 'harnesses,' where core tasks are performed by AI agents rather than humans. This shift transforms organizational structure, with humans overseeing and reviewing AI-driven processes within the company. (blog.sshh.io)
Three AI agents - Meta’s Muse, Anthropic’s Claude, and OpenAI’s GPT - were tested on multilingual research tasks involving U.S. and Iranian data. The experiment focused on how language and context influence agent performance across reasoning, sourcing, and artifact creation. (royapakzad.substack.com)
An open-source project named LDRAW-NOVA allows users to generate Lego models using AI. The repository contains tools, examples, and documentation for creating Lego designs with artificial intelligence. (github.com)
DwarfStar 4 (ds4) is a local inference engine that runs large language and vision models on high-memory Mac, CUDA, and ROCm machines. It supports models like DeepSeek V4 and Qwen3.8, offering CLI, APIs, and persistent cache features for efficient local deployment. (dwarfstar.sh)
Rai is a CPU-only large language model inference engine written entirely in Rust. It aims to provide efficient and pure Rust solutions for LLM deployment without relying on GPUs. (github.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.