_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
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 â 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 âbackup providerâ (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