Apache Burr: Build reliable AI agents and applications
burr.apache.org
Apache Burr: Build reliable AI agents and applications
1–10 of 125 posts
Re: Apache Burr: Build reliable AI agents and applications
#2I couldn't find an explicit reference for the naming, but for anyone wondering there is a Hamilton example: https://github.com/apache/burr/tree/main/examples/multi-agen...
Re: Apache Burr: Build reliable AI agents and applications
#3I just create a MVP chatbot for a client that has a Django app. I took the route to no frameworks. Claude/codex wrote the agent loop, the tools, the streaming..it’s working well for the MVP, we’ll see
Re: Apache Burr: Build reliable AI agents and applications
#4First time I hear about Burr, curious why it was incubated in Apache.
Re: Apache Burr: Build reliable AI agents and applications
#5How does this compare to https://strandsagents.com/ ? I'm interested in tools in this space, right now I'm not attached to one, but Bedrock + Serverless on Agent Core feels like the "easy guided path" though I don't like the platform lock-in
Re: Apache Burr: Build reliable AI agents and applications
#6I'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 memory, async tool calls, etc, but not THAT complicated from a traditional software engineering perspective.
Everyone seems to want to build their agent framework. But if you're tasked with building an agent, I've found it much easier and more maintainable to just build 1:1 code for THAT agent: most of the abstractions you get from an agent framework purely get in the way and obfuscate core agent logic.
You end up being forced to use the abstractions chosen by the agent framework, which sometimes are a mismatch for what you're actually trying to do.
Re: Apache Burr: Build reliable AI agents and applications
#7Claude Opus really loves this template when building websites. It's very funny how many times I've seen it for recent launches.
Re: Apache Burr: Build reliable AI agents and applications
#8First time I hear about Burr, curious why it was incubated in Apache.
Why wouldn't it? The ASF has a long history of incubating new FOSS projects. Some graduate and become household names. Others fail and end up in the attic. The ASF can provide organisational support and generally fosters good communities.
Re: Apache Burr: Build reliable AI agents and applications
#9Claude Opus really loves this template when building websites. It's very funny how many times I've seen it for recent launches.
And it lags my desktop every-time, I hate it. It's the default bootstrap theme all over again but instead with SVG's.
Re: Apache Burr: Build reliable AI agents and applications
#10I'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…
Couldn't agree more - tried to convince a business that doubling down on OpenClaw wasn't going to solve problems except for some 0-1 stuff, and that almost immediately they'd run into roadblocks because most of the product wouldn't serve their use case.
4 months of mostly spinning their wheels later they launched a really lackluster OC product that's effectively DOA.