Show HN: 20+ Claude Code agents coordinating on real work (open source)

austinbaggio

2 hours ago

19points

Single-agent LLMs suck at long-running complex tasks.

We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress.

How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents

We tested this on a Putnam-level math problem, but the pattern generalizes to things like refactors, app builds, and long research. It’s packaged as a Claude Code skill and designed to be small, readable, and modifiable.

Use it, break it, tell me about what workloads we should try and run next!

21 comments

Comments

yodon•41 minutes ago

The first screen of your signup flow asks for "organization" - is that used as a username or as an organization name or both (I can't tell what if anything will be on the next screen)

If your registration process is eventually going to ask me for a username, can the org name and user name be the same?

austinbaggio•32 minutes ago

We're working on improvements to make it easier to join orgs as a user so you can add friends/colleagues, but for now treat them as the same object

yodon•18 minutes ago

When you get a chance to work on your login flow, I recommend giving users an opportunity to request the key rather than automatically showing it once only on the first screen.

I created the account from my phone, and don't have access to the dev tools I'd want to paste the key into. I can deal with it, but I don't know if I'll be able to regenerate the key if I lose it, I'd rather not store it on my phone, and I don't trust my accuracy in manually typing it in on my laptop while looking at my phone, so all the options feel not great. Again, not an actual roadblock, but still something I'd encourage fixing.

Edit added: Good thing I copied the key to my phone before writing this message. Jumping over to this page seems to have forced a refresh/logout on the ensure page in the other tab, so my token would (I think? maybe?) be lost at this point if I'd done it in the other order.

austinbaggio•4 minutes ago

Ahh good call. You absolutely can generate a new key from the dashboard, so if you did lose the one generated during the quickstart, you'd be able to generate another when you log in next and go to the API keys tab.

Will make this more clear in the quickstart, thanks for the feedback

austinbaggio•33 minutes ago

username==orgname for now, so yes, just treat that as one in the same

miligauss•1 hour ago

It's a more of a black box with claude, at least with this you see the proof strategy and mistakes made by the model when it decomposes the problem. I think instead of Ralph looping you get something that is top-down. If models were smarter and context windows bigger i am sure complex tasks like this one would be simpler, but braking it down into sub agents and having a collective --"we already tried this strategy and it backtracked"-- intelligence is a nice way to scope a limited context window to an independent sub problem.

raphaelmolly8•1 hour ago

The Lean angle here is really interesting: most multi-agent demos dodge hard verification, but tying each agent’s output to makes the feedback loop objective. Curious how you’re handling goal-claim conflicts/duplication when two agents find competing tactic sequences for the same subgoal—do you keep both in memory with some ranking signal (time-to-verify, proof term size, etc.)?

clairekart•2 hours ago

What’s the failure mode you see with single-agent Claude Code on complex tasks? (looping, context drift, plan collapse, tool misuse?)

austinbaggio•1 hour ago

All of the above. The most frustrating one with the Putnam example with Claude was generating solutions that obviously didn't compile. This feels like plan collapse- not verifying its own work. I'm sure that if you just had a dumb two-model setup, it would eventually get to compiling code after n runs, but that was just for this one failure mode.

Atotalnoob•1 hour ago

You can use hooks to not allow it to stop without successful build

yodon•1 hour ago

Can you add a license.txt file so we know we have permission to run this (eg MIT and GPL V3 are very different)

austinbaggio•1 hour ago

Oversight - added MIT. How are you thinking of using it?

yodon•1 hour ago

For the moment, researching multi-agent orchestration. At first glance, your work looks among the best in class of published work I've seen. Particularly interested to understand the memory/communication/search model you're using, as it sounds like you've trying to think well past the GasTown/Beads/Claude-Code-Swarms concepts.

austinbaggio•7 minutes ago

Very kind of you to say. Our whole vision is that agents can produce way better results, compounding their intelligence, when they lean on shared memory.

I'm curious to see how it feels for you when you run it. I'm happy to help however I can.

christinetyip•1 hour ago

Cool, what’s a good first task to try this on where it’s likely to beat a single agent?

austinbaggio•1 hour ago

Math proofs are really easy to run with this specific harness. Our next experiments are going to be bigger, think full code base refactors. We're working on applying RLM to improve context window limits so we can keep more of the actual code in RAM,

Any workloads you want to see? The best are ones that have ways to measure the output being successful, thinking about recreating the C compiler example Anthropic did, but doing it for less than the $20k in tokens they used.

indra_varta•21 minutes ago

[dead]

miligauss•1 hour ago

we tried putnam a2

slopusila•1 hour ago

seems like it requires an API key to your proprietary Ensue memory system

austinbaggio•1 hour ago

Yeah we're using Ensue since it already handles the annoying infra pieces you’d otherwise have to build to make this work (shared task state + updates, event streams/subscriptions, embeddings + retrieval over intermediate artifacts). You can run the example with a free key from ensue-network.ai. This repo focuses on the orchestration harness.

zmanian•1 hour ago

“How does progress subscription work — are agents watching specific signals (test failures, TODO list, build status), or just a global feed?”

miligauss•1 hour ago

claude code doesn't support subscriptions out of the box, so we use the subscription feature to just alert the orchestrator to a single polling file. Not the most elegant thing but still a token save over reading a bunch of sub agent logs. It is as reactive as you can be given the current feature set of claude code.