Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Gambit, an open-source agent harness for building reliable AI agents

github.com

Post reply on HN
Print view View original

11–20 of 33 posts

Re: Show HN: Gambit, an open-source agent harness for building reliable AI agents

#14

Post by randall »

Trufa wrote: post #12

Is this an alternative to https://mastra.ai/docs How would it compare?

So I look at something like Mastra (or LangChain) as agent orchestration, where you do computing tasks to line up things for an LLM to execute against.

I look at Gambit as more of an "agent harness", meaning you're building agents that can decide what to do more than you're orchestrating pipelines.

Basically, if we're successful, you should be able to chain agents together to accomplish things extremely simply (using markdown). Mastra, as far as I'm aware, is focused on helping people use programming languages (typescript) to build pipelines and workflows.

So yes it's an alternative, but more like an alternative approach rather than a direct competitor if that makes sense.

Re: Show HN: Gambit, an open-source agent harness for building reliable AI agents

#17

Post by brap »

Agent_Builder wrote: post #16

[dead]

This seems to be where it’s at right now, we can’t seem to make the models significantly more intelligent, so we “inject” our own intelligence into the system, in the form of good old fashioned code.

My philosophy is make the LLMs do as little work as possible. Only small, simple steps. Anything that can be reasonably done in code (orchestration, tool calls, etc) should be done in code. Basically any time you find yourself instructing an LLM to follow a certain recipe, just break it down to multiple agents and do what you can with code.

Re: Show HN: Gambit, an open-source agent harness for building reliable AI agents

#18

Post by randall »

brap wrote: post #17
Agent_Builder wrote: post #16

[dead]

This seems to be where it’s at right now, we can’t seem to make the models significantly more intelligent, so we “inject” our own intelligence into the system, in the form of good old fashioned code. My philosophy is make the LLMs do as little work as possible. Only small, simple steps. Anything that can be reasonably done in code (orchestration, tool calls, etc) should be done in code. Basically any time you find yo…

i have a slightly different but related take. the models actually are getting smarter, and now the challenge becomes successfully communicating intent with them instead of simply getting them to do anything remotely useful.

Gambit hopefully solves some of that, giving you a set of primitives and principles that make it simpler to communicate intent.

Post reply on HN