- SignalDesk1小时前
Original Summary
My friend and I have worked at a number of BI companies and thought: Can’t a coding agent do most of this now?<p>Almost. They just need a context/semantic layer to ensure query correctness and some kind of artifact for publishing findings and visualizations.<p>We built an open source project called Graphene that provides these tools:<p>- Semantic layer that’s more token-efficient than YAML, more deterministic than Markdown (eg, composable, callable metric macros), with a query API that’s well in-distribution (SQL). - MDX-like files for dashboards (Markdown with inlined SQL + HTML components for viz with support for CSS and Javascript) - Connects to popular data warehouses or local DuckDB<p>Your coding agent will build really in-depth reports and can ofc leverage any other skills or context that you've made available to it. We dogfood it inside a monorepo with our website, app source code, planning docs, etc so the agent has access to a ton of context. It’s also nice that the agent can add instrumentation, adjust pipelines and transformations, and add dashboards all in one PR.<p>If you want to try it out, just point your coding agent at <a href="https://github.com/graphene-data/graphene/blob/main/docs/setup.md" rel="nofollow">https://github.com/graphene-data/graphene/blob/main/docs/set...</a> and ask it to set up Graphene.<p>If you don’t have data to play with, you can clone our example project:<p>1.
git clone <<a href="https://github.com/graphene-data/example-flights.git" rel="nofollow">https://github.com/graphene-data/example-flights.git</a>> 2.cd example-flights && npm install`<p>Would love any/all feedback!中文概览
中文标题： Show HN：Graphene——为编程智能体打造的数据分析工具包
作者开源了 Graphene，为编程智能体提供语义层（比 YAML 更省 token、比 Markdown 更确定，含可组合指标宏与 SQL 查询 API）、类 MDX 仪表盘文件，并可连接主流数据仓库或本地 DuckDB。
- 情报分类：开源项目与落地
- 分类依据：作者明确说明为开源项目，归为开源项目与落地。
- 信息来源：Hacker News 新项目
- 发布时间：2026/10/2 05:29:52
- 暂无回复