Comments URL: https://news.ycombinator.com/item?id=47936814

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936801

Points: 1

# Comments: 0

As a data scientist, you spend the majority of your time wrangling data. Even though you might have a set of techniques and tricks you like to use, how exactly you treat a particular source of data tends to be fairly bespoke, so you end up writing custom logic each time.

Ragnerock was born from the observation that modern LLMs can be used to automate a lot of the grunt work involved in this process, while still allowing for fully customizable pipelines. What’s more, by leveraging techniques like constrained decoding, it’s possible to provide a unified query interface regardless of the data source - bridging raw data sources like text and images with your existing structured data living in your databases.

Ragnerock has four main components:

- A workflow designer that lets you build LLM-driven data processing and analysis pipelines - A job orchestration layer that runs those workflows - A query interface which lets you inspect the results of those workflows with plain SQL - A notebook system which is 100% API-compatible with Jupyter and runs on your existing kernels, so you can easily pull data into your existing environments and analyses

Ragnerock also supports bring-your-own AI (OpenAI, Anthropic, and Google APIs), databases, and blob storage, so you can join with your existing datasets and have all outputs flow to your data lake. We’re particularly excited about our web crawling feature, which allows you to scrape websites and trigger workflows on updates: for example, you might point Ragnerock at your favorite blog and run a workflow to assess posts for topics and sentiment.

You can try it out at https://www.ragnerock.com ; no credit card needed and the first 20 hours of compute are free. It’s an early-stage product so we’re especially interested in feedback.

Happy to answer any questions - John and I will be around in the comments today.

Comments URL: https://news.ycombinator.com/item?id=47936757

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936726

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936689

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936677

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936529

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=47936503

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936371

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936347

Points: 25

# Comments: 4

Comments URL: https://news.ycombinator.com/item?id=47936317

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936209

Points: 24

# Comments: 4

Comments URL: https://news.ycombinator.com/item?id=47936190

Points: 3

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=47936156

Points: 65

# Comments: 28

Comments URL: https://news.ycombinator.com/item?id=47936144

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47936076

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=47935987

Points: 2

# Comments: 0

Then it kept growing. Wouldn't it be cool if i could talk to a coding agent directly, like the Star Trek computer? Oh, maybe like Iron Man (says everyone..).

Why am i spinning up another terminal to run research on this? Hey Iris, can you run the research and throw it in the Vault? Let me know when you're done. Send a Slack message, check my emails, red team that PR request.

Super Voice Mode is now the thing I use for work — coding, research, thinking out loud, orchestrating agents. It sits above every tool on your Mac and gives you one consistent voice layer across all of them. Claude Code, Codex, Gemini, local models, whatever's running. Transcription is local, no audio saved no internet needed.

The whole thing was built spec-driven with AI coding agents — Claude Code, Codex, the lot. Engineering background, but the agents did the building. Which feels appropriate given what the product is.

The whole thing was built spec-driven (a little vibing) with AI coding agents — Claude Code, Codex, the lot. Engineering background, but the agents did the building. Website design everything Experiment continues.

This is early. There's more coming.

Free tier, no email required. Download and it works.

Happy to get into how the local transcription works, the model integrations, or the agent-driven build process.

Comments URL: https://news.ycombinator.com/item?id=47935973

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47935773

Points: 7

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=47935751

Points: 4

# Comments: 0