oh god, the vibecoded homepage, I instantly closed that. sorry
Apache Burr: Build reliable AI agents and applications
101–110 of 125 posts
Re: Apache Burr: Build reliable AI agents and applications
#102Was this built using https://vorpus.github.io/performativeUI/ ? It hits every AI generated landing page trope possible. Or was it done ironically?
amazing set of components. just noticed my "ai-native" company has almost all of them.
Re: Apache Burr: Build reliable AI agents and applications
#103Earlier quoted context omitted.
For me the heart of an agentic system is NOT using agents (except when you really have to). Components of a working system include: - Pipelines/recipes to describe multi-step flows (deterministic, agentic and HiTL steps), loops, conditionals, exit-on's for max loop iteractions, etc - The logistics to actually run the model and HiTL steps reliably across multiple agent worker pools - Management and delivery (and secur…
Can you comment more on > Context management so the right agents have the right context for the right sessions at the right time I'm going to do a show HN tomorrow that explains how you can give your agents years of experience. The basic idea is, you would commit in your repo or download manifests (JSON files) that can be converted to "Brains" (SQLite databases). Each brain can have its own properties. For example, I…
I do file summaries as well. Basically a knowledge base commit hook + agent that creates/updates a file containing a summary and list of its dependencies, followed by updating an index to include it. Super useful for creating system migration scopes and just managing context in general.
Re: Apache Burr: Build reliable AI agents and applications
#104Was this built using https://vorpus.github.io/performativeUI/ ? It hits every AI generated landing page trope possible. Or was it done ironically?
I was just wondering the same thing!
I do suspect it was built with some form of AI though because the handful of links I've tried to dig into have all linked to the wrong place/are invalid :/
Re: Apache Burr: Build reliable AI agents and applications
#105I have to say, after the recent Performative UI post here on HN, I was not expecting an apache foundation project to have gradient words on the landing page.
Re: Apache Burr: Build reliable AI agents and applications
#106There's no such thing as "reliable" AI.
Re: Apache Burr: Build reliable AI agents and applications
#107the observability layer is almost always what DIY agent setups skip, and it's the first thing you miss in production. (built clawmetry for agent runtimes like openclaw, claude code, hermes etc specifically because of this)
Re: Apache Burr: Build reliable AI agents and applications
#108So many software homepages use that tailwind template, or a variety of it. As soon as I see it, it suggests to me a poor quality/rushed product.
Re: Apache Burr: Build reliable AI agents and applications
#109One of the co-creators/maintainers here! Will try to answer Qs over the day.
Do you ever abbreviate the project name as A. Burr and how many Hamilton jokes[1] result from this? [1] https://en.wikipedia.org/wiki/Burr%E2%80%93Hamilton_duel
wait till you see our other project github.com/apache/hamilton ;)
Re: Apache Burr: Build reliable AI agents and applications
#110I'm still on the fence about agent frameworks, they have their place, and it depends on the nature of the agent: e.g. "Low latency, return a good enough response in 3 seconds, vs. working for 3 hours on a problem." BUT, if you boil it down, an agent really is context building, making an LLM call, executing requested tool calls, parsing the final model output, returning it to some frontend. There's extensions like mem…
Arguably, if your agent needs a lot of custom logic to drive the agent loop it isn't an "agent" at all. At best it is an agentic workflow, or rather a workflow with some LLMs calls in between.
I think that's why agent SDKs feel like the wrong abstraction. If you are writing a workflow, use a workflow engine (Airflow, Temporal, etc), and call some LLMs with a small LLM library. If you need a "real" agent, use a full-featured agent harness, like Codex or CC or Pi or whatever, then load it up with all the tools, skills, mcps that it needs, and let it rip.
Incidentally I've been building a full featured agent harness that runs inside durable workflow engines [0], but it is designed _not_ as an SDK but rather as a standalone, full-featured harness with an API.