Live data from Hacker News

Viewing profile — mbroecheler

mbroecheler

HN member
Joined
Thu, Jun 14, 2012, 7:10 PM UTC
HN karma
17
Public activity
20 items

About mbroecheler

Working on DataSQRL.com - a compiler for your cloud data infrastructure.

Recent public activity

  1. story
    Show HN: Acorn.js – Turn GraphQL APIs into Tools for LLMs and Agents

    We built a lightweight Typescript library that turns GraphQL APIs into tool definitions for LLMs like GPT, Claude, and others. It also integrates directly with agentic frameworks l…

  2. comment
    Comment #43511072

    Exactly, any generic GraphQL server can be turned into a set of LLM tools with minimal overhead and complexity.

  3. comment
    Comment #43494637

    Second that. A lot of our use cases are "remote tooling", i.e. calling APIs. Implementing an MCP server to wrap APIs seems very complex - both in terms of implementation and infras…

  4. comment
    Comment #41144425

    I agree that being able to write one piece of code that solves your use case is a big benefit over having to cobble together a message queue, stream processor, database, query engi…

  5. story
    Show HN: Retrieval Augmented Generation for LLMs from APIs with Function Calling

    Dear HN, we'd love your feedback on a different approach to Retrieval Augmented Generation (RAG) for LLMs that uses function calling to retrieve the most relevant data from APIs. I…

  6. story
  7. comment
    Comment #36489022

    Totally agree with the motivation - it is too cumbersome to stitch all these cloud services together by hand. Another project that's similar in motivation but focused on cloud data…

  8. story
  9. comment
    Comment #35968536

    You are totally right. We did not want to create a new language and we are trying to keep it as close to SQL as possible. The problem is that SQL lacks streaming constructs you nee…

  10. comment
    Comment #35968150

    Exactly, there are so many amazing dataflow engines, stream processors, and databases out there. We are not competing with those. We are trying to "compile away" all of the data pl…

  11. comment
    Comment #35967676

    Yes, the idea to maintain materialized views based on standing queries to make the queries instantaneous is the same. In addition, DataSQRL handles the ingest (e.g. consuming event…

  12. comment
    Comment #35967452

    We'd love for you to join us in building a high-level data development language to simplify data-driven application development.

  13. story
  14. comment
    Comment #10205015

    I suppose our communication around Titan has caused some confusion after the acquisition by DataStax. As one of the Titan devs I can say that we have no plans to abandon Titan. Wha…

  15. comment
    Comment #10111524

    Take a look at Gremlin 3 - it now supports both declarative and imperative queries. In fact, you can even mix and match the two. You want to match a complex pattern? Use declarativ…

  16. comment
    Comment #8185270

    Yes, it works :-) Support for multiple storage backends gives Titan a lot of deployment flexibility and allows it to inherit some great features like multi DC support. Software com…

  17. comment
    Comment #5706241

    Approximately $63 per hour on Amazon EC2.

  18. comment
    Comment #4351067

    I think you are looking at a very different use case here. The systems that I think you are referring to analyze a static graph representation. The Graph500 benchmark in particular…

  19. comment
    Comment #4348963

    Absolutely, without NoSQL solutions like Cassandra Titan would not be possible. Regarding Zookeeper: We actually build a locking system into Titan that uses quorum reads/writes wit…

  20. comment
    Comment #4348954

    Hey, - the data we used was crawled by Kwak et. al in 2009. We wanted to use a real social network dataset for the experiment and that was the largest/most useful one we could find…