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

Show HN: Agent-harness-kit scaffolding for multi-agent workflows

ahk.cardor.dev

Post reply on HN
Print view View original

21–30 of 33 posts

Re: Show HN: Agent-harness-kit scaffolding for multi-agent workflows

#24

Post by hungryhobbit »

It took me awhile to figure out what this even does, and that was only because our team had just discussed agent coordination the day prior.

There are AI people who live and breathe AI every day, and people who don't know AI at all. In-between are lots of people in the middle of "leveling up" with AI ... but ATM the tool's docs are only for the very first group.

FWIW, I really think a paragraph or so of plain English describing the problem (agents can't communicate by default) and the solution (this tool lets them coordinate) would help everyone else (and would take like two seconds to add).

Re: Show HN: Agent-harness-kit scaffolding for multi-agent workflows

#25

Post by enmanuelmag »

elysianfields wrote: post #13

This looks really cool. Did you think about including automatic worktree creation + sandboxing? I've built sth similar (more focus on the project setup and being able to work on multiple things at once with a single agent), that uses git worktrees to create a separate space (symlinks .env files) and bubblewrap to isolate the worktree for the agent.

Thanks! That a very good idea. I will add it on my roadmap and start planning. Thanks, if you have more ideas or proposal add it on the repo too

Re: Show HN: Agent-harness-kit scaffolding for multi-agent workflows

#27

Post by enmanuelmag »

lynellf wrote: post #9

Looks cool, but is it really provider agnostic? I only see Claude Code and OpenCode as advertised examples. How does this differ from RooCode and similar agent orchestration tools?

I will ad emote provider option on the future, to expose all internal logic as the MCP and new guest urge available from any provider

Re: Show HN: Agent-harness-kit scaffolding for multi-agent workflows

#28

Post by enmanuelmag »

koolba wrote: post #5
enmanuelmag wrote: post #2

[dead]

If you replace sqlite with a remote DB like Postgres, can you federate the agents and have multiple pointing at the same central knowledge store?

Yes that a goal on my roadmap. Thanks, if you have more ideas or proposal add it on the repo too

Re: Show HN: Agent-harness-kit scaffolding for multi-agent workflows

#29

Post by enmanuelmag »

dubovskiyIM wrote: post #19

Two questions on the design: "lead-agent reads sub-agent output" makes the lead an LLM judge. Are there post-conditions checked, or is LLM-judge approval the final gate? Related: does the system reason over typed state or over raw output?

[flagged]

Re: Show HN: Agent-harness-kit scaffolding for multi-agent workflows

#30

Post by eugeniecregan »

mettamage wrote: post #20
eugeniecregan wrote: post #17

Earlier quoted context omitted.

How are you finding the communication between your agents? Ours is really interesting - they are developing personalities. Sometimes being quite passive aggressive with each other

Hmm... they remain similar-ish. But I think that's also because I have a lot in my claude.md file that they have to follow empiricism as a philosophy. Things need to be verified, researched, backed by data, etc. That's also how I live my life, so when it starts to develop a personality, usually I'd ask what the benefit of that is. If it doesn't have a good answer, then I have yet another rule in my CLAUDE.md about wh…

That's really interesting - so they develop personalities if we allow them to?! Is it part of social conditioning? Would humans have a personality if they lived in isolation?
Post reply on HN