Breadcrumb is a macOS app that continuously records and organizes everything that happens on your machine to give developer-focused AI assistants persistent, searchable context. It groups work into "scopes" (folders with enforced rules) so folder-specific policies apply automatically, captures screen content, meetings and session histories, and lets AIs pick up exactly where prior conversations left off without token-loss. Practical examples include diagnosing "disk full" issues by recalling prior advice and commands, extracting action items from standups, producing day timelines of app and web use, creating permanent rules like "Never push main," and turning repeated reports into one-word shortcuts (e.g., \fb-hours). It integrates with multiple AI backends (Claude, ChatGPT, Cursor, opencode) and can continue long threads as new chats while preserving full context.
Privacy and local control are central: history is encrypted at rest with a key in Keychain, recording can be paused instantly, apps/sites/phrases can be excluded, incognito is never recorded, and Breadcrumb says it does not build voiceprints or collect telemetry. Transcription and speaker identification can run on local models; sending context to cloud AIs is explicit and governed by each AI’s policy. Personal use is free with no account required; it requires Apple silicon (M1+), 16 GB RAM and macOS 15+, and a paid founding-seat option ($299, limited spots) plus future team products planned.
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.