URI: 
        _______               __                   _______
       |   |   |.---.-..----.|  |--..-----..----. |    |  |.-----..--.--.--..-----.
       |       ||  _  ||  __||    < |  -__||   _| |       ||  -__||  |  |  ||__ --|
       |___|___||___._||____||__|__||_____||__|   |__|____||_____||________||_____|
                                                             on Gopher (inofficial)
  HTML Visit Hacker News on the Web
       
       
       COMMENT PAGE FOR:
  HTML   Agent-o-rama: build, trace, evaluate, and monitor LLM agents in Java or Clojure
       
       
        kamma4434 wrote 11 hours 10 min ago:
        I understand this is meant as a demo of what Rama can do. As a
        potential user I am not keen on running a distributed system that is a
        black box and contains all of its data – how do I access it? How do I
        back it up?
       
          nathanmarz wrote 6 hours 59 min ago:
          It's not meant as just a demo of what Rama can do. It's a fully
          featured tool that supports the end-to-end workflow of building and
          maintaining robust LLM agents. It has an easy-to-learn API and you
          don't need to learn how to program Rama itself.
          
          Rama isn't open source, but it's far from a black box. All data
          structures and computation are fully visible in the UI. You can
          inspect depots, topologies, and PStates, and see exactly what's
          stored and how it changes over time. Everything is also accessible
          through the Rama client API for direct querying. The PState schemas
          used by Agent-o-rama are defined here: [1] Backups are easy: you
          configure a “backup provider” (we provide one for S3) and a
          schedule for incremental backups. The free version can also be backed
          up with a short maintenance window. Full details are here:
          
  HTML    [1]: https://github.com/redplanetlabs/agent-o-rama/blob/master/sr...
  HTML    [2]: https://redplanetlabs.com/docs/~/backups.html
       
        nathanmarz wrote 1 day ago:
        Hey, project lead here. I'm happy to answer any questions you have
        about Agent-o-rama or its technical internals.
       
          esafak wrote 1 day ago:
          Can you compare it with JetBrains' Koog, if you are familiar with it?
          [1] I see you're still using Clojure since writing Apache Storm!
          
  HTML    [1]: https://www.jetbrains.com/koog/
       
            nathanmarz wrote 23 hours 27 min ago:
            I'm only somewhat familiar with Koog, but these these are major
            differences according to my understanding:
            
            - Execution model: Koog is a library for defining agents that run
            within a single process. AOR agents execute across a distributed
            cluster, whether one node or thousands.
            
            - Deployment and scaling: Koog provides no deployment or scaling
            mechanisms. That's something you need to figure out on your own.
            AOR includes built-in deployment, updating, and scaling.
            
            - Integration complexity: Koog must be combined with other tools
            (monitoring tool, databases, deployment tools, etc.) to approximate
            a complete agent platform. AOR is fully integrated, including
            built-in high-performance, durable storage for any data model.
            
            - Experimentation and evaluation: Koog has no features for
            experimentation or online evaluation. AOR includes extensive
            support for both.
            
            - Scalability: AOR scales horizontally for both computation and
            storage. With Koog, you'd need to design and operate that
            infrastructure yourself.
            
            - Observability: Koog's observability is limited to traces and
            basic telemetry exposed via OpenTelemetry. AOR provides a much
            broader set of telemetry, including "time to first token" and
            online evaluation charts. You can also split all time-series charts
            automatically by any metadata you attach to your runs (e.g. see how
            agent latency differs by the choice of model used). Plus, it's all
            built-in and automatic.
            
            Please correct me if I'm wrong on any aspect of Koog.
       
       
   DIR <- back to front page