Graphene is an everything-as-code data analytics framework built to let coding agents perform SQL-based exploration, visualization, and reporting. It provides a semantic layer called Graphene SQL that combines full SQL capability (CTEs, subqueries, window functions, set operators, and 170+ functions) with modeled metrics and joins so agents can generate accurate, governed queries without learning bespoke APIs. Projects are organized as .gsql semantic models and .md “pages” for dashboards; a CLI (installable via npm/pnpm/yarn) compiles queries, renders pages, runs syntax checks, and serves a dev UI. Pages support rich visuals, inputs, HTML/CSS/JS/ECharts, and two layout modes for monitoring versus narrative use. Supported backends include Snowflake, BigQuery, ClickHouse, Postgres, MotherDuck, and local DuckDB.
Design goals prioritize token efficiency, agent ergonomics, and high ceilings so agents can iterate quickly and produce consistent, polished outputs. Everything-as-code enables version control, CI, deterministic metric definitions, and safer bulk refactors compared with ad hoc notebooks or React dashboards. Licensing permits free internal use under the Elastic License 2.0; a hosted Graphene Cloud and managed services (MCP server, Slack bot) are offered for turnkey deployments. The stack targets teams that want agent-driven analytics, reproducible metrics, and freedom from proprietary dashboard lock-in.
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)
GPT-2, released in 2018, required an estimated 10²¹ FLOPs to train, making it a significant milestone in AI development. The article discusses why similar models or advancements did not occur earlier, such as in 2005, due to technological and resource limitations. (dynomight.net)
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)
Today's best Hacker News stories, summarized and screenshotted, one email a day.