Tracecast – open-source generative data apps built on top of Marimo
Hi HN, I'm Malachy, the founder of Tracecast. This project lets you generate interactive data apps on top of your data, using a Cursor-style AI chat. It stitches together Marimo, LangGraph agents, and data warehouse query tools. It has an Apache 2.0 license. The initial use case that spurred this project was business analytics, specifically generating product usage dashboards. This project's main inspiration is Marimo, an open source python notebook that can be "queried with SQL, run as a script, and deployed as an app" [1]. The recent release of Marimo Pair [2] demonstrated the power of…
What it does
In the maker’s words, at launch
Hi HN, I'm Malachy, the founder of Tracecast. This project lets you generate interactive data apps on top of your data, using a Cursor-style AI chat. It stitches together Marimo, LangGraph agents, and data warehouse query tools. It has an Apache 2.0 license. The initial use case that spurred this project was business analytics, specifically generating product usage dashboards. This project's main inspiration is Marimo, an open source python notebook that can be "queried with SQL, run as a script, and deployed as an app" [1]. The recent release of Marimo Pair [2] demonstrated the power of connecting AI agents like Claude Code to Marimo notebooks directly. This project seeks to build on that work by incorporating a LangGraph agent with two key abilities: (1) the ability to execute queries against a connected data warehouse (such as Snowflake); (2) the ability to write Marimo notebooks. When prompted, the LangGraph agent will run exploratory data analysis using database query tools. Then, it creates a polished Marimo notebook that's presented to the user in read-only mode. This project intentionally hides the Marimo edit mode. That means that the end user only ever sees a finished, read-only data app. Ease of use and trust in AI output were the main drivers behind this decision. 4 data sources are currently supported: Snowflake, BigQuery, Postgres, and Metabase. The code for the database query tools was derived from Google's open source MCP Toolbox for Databases. There is currently no support for MCP. Instead, data query tools are hardcoded. This decision was made to ensure high quality AI queries and limit tool bloat. This is an early stage project, and is configured to only run locally at this time. [1] https://github.com/marimo-team/marimo [2] https://news.ycombinator.com/item?id=47678844
Does the same job
all alternatives →- DAdstack – an open-source tool to build data applications easily2020 · ▲134
Dear HN, I am Riwaj, the cofounder of dstack.ai (https://github.com/dstackai). A few months ago, we built an online service that allows users to publish data visualizations from Python or R. The idea was to build a tool that did not require additional programming or front-end development for publishing data visualizations. Such a code can be invoked from either Jupyter notebook, RMarkdown, Python, or R scripts. Once the data is pushed, it can be accessed via a browser. Open-sourcing dstack: During our customer discovery phase, we realized that dstack.ai should integrate a lot…
- CECensus – Export for data warehouses2020 · ▲34
Hello Hacker News! We're a team of YC founders (Meldium W13, Draft S11, TapEngage S11) launching something new (https://www.getcensus.com). How many times has your business team asked you to generate yet another CSV file, write a ”quick report” in SQL, or send some custom data to a terrible API (looking at you Marketo)? We’ve built a product that connects directly to your data warehouse and syncs into apps like Salesforce, Customer.io and even Google Sheets. In fact, your business teams won’t even need to rely on engineering to manage all these pipelines. The tech stack for…
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 · 26d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com