Comments URL: https://news.ycombinator.com/item?id=48447084

Points: 2

# Comments: 1

Still trying to figure out if there will be ways to "bot check" from Anthropic side for this workarounds.

Comments URL: https://news.ycombinator.com/item?id=48403472

Points: 2

# Comments: 1

For a while we've seen companies focused solely on the coding agent part, and specially building harnesses. We thought it would be interesting to go in another direction: building on top of them.

Building on top of them allowed us to create a system that can be plugged where you work (e.g. Slack, Linear, Github, Gitlab, email, etc) and work as a peer. It really feels like a new teammate that works with you.

Some of the core components of it are:

1. Plug in any harness: codex, Claude Code, Claude managed agents, Devin, pi, etc.; 2. Memory layer. It's an abstraction, hence you may build your own implementing an interface; 3. Communication layer where you work; 4. Multi agent architecture with single lead (we started with any agent as the entrypoint and we saw lead only was better).

We are building it in public, and today we just hit 400 stars (wow). Also we have some companies that are trying to integrate it into their teams (+50 people) with promising results.

I'm really curious what you think about it, and how do you see this pattern emerging and being used by companies that want to go truely agent-native.

Any feedback or suggestions are more than appreciated!

Cheers,

Comments URL: https://news.ycombinator.com/item?id=48020415

Points: 1

# Comments: 1

I loved the chat sdk for node, but I wanted to use it in Python, so I let my agent-swarm run in the night to port it (it only costed $500 in claude usage xD).

Performing some E2E tests now, and will be releasing to pypi as `chat-py` with the adapters as separate packages (as the chat sdk).

My goal is to keep it in sync on a daily basis.

Cheers!

Comments URL: https://news.ycombinator.com/item?id=47862668

Points: 1

# Comments: 1

If you saw my last post, we've been building agent-swarm (https://github.com/desplega-ai/agent-swarm) for a while, and one of the problems that we started encountering and getting more annoying each time was: how do we share / check stuff bi-directionaly with the agents (they run remotely).

Use case ---

The use case is simple: agents create a document somewhere and I want to be able to check it, leave comments, etc. But also for the other agents (in other machines / dockers) to be able to check it.

Until now the solution was simple: docker volumes. We mounted a /workspace/personal (personal volume) for each agent, and a /workspace/shared (shared volume in lead and workers). This allowed easy collab in the swarm, but not easy for me. I had to either SSH or have the swarm build an app and serve it locally via proxy :D.

Problem ---

On the other hand last week I decided to figure out other places to deploy this, and I tried fly.io, which I liked the DevEx a lot. The problem with it was that each machine allowed a single volume. I then tried Archil (which worked, but it was a ownership and setup mess).

Solution ---

So... ended up creating agent-fs, which is an s3 backed suuuper simple API (comes with MCP and CLI) that let you have an interface like the one from GDrive, but thought for agents.

When I published the npm I asked the swarm to register, and in less than 5 minutes I was already seeing the shared drive and docs they created in the live UI.

Why not use gws cli? Because I want each agent to be able to auto-register with an email (we use agentmail for them), get an API key and get going. It should be headless. Invites should be easy and each register comes with an initial personal drive.

Also this allows something nice (and silly). If you register as a human and have a shared drive w the swarm. Using the MCP insta allows to have that in any place with MCP support (e.g. Claude web, ChatGPT) which is a fast way to have a knowledge base across systems.

Thoughts on this?

Comments URL: https://news.ycombinator.com/item?id=47424556

Points: 2

# Comments: 0

funny you found that XD

1. Agents update those files themselves, but currently with my oversight and guidelines (from the UI you can even see it's contents)

2. Measuring this is extremely hard, if not impossible. One of the goals of the swarm is to help me on random tasks that can span a lot of different pieces, not just implementing a feature.

Before last week, we did not have the memory and identity files. And, from an empirical pov, I can say that the general feel improved a lot. I see that in similar situations it does not perform the same mistakes. Also, what is stored in those files generally is something that the agent CAN NOT find using it's tools (like the paper suggest to avoid) which actually helps.

In any case, the swarm created a research on this topic a few days ago https://github.com/desplega-ai/agent-swarm/pull/86 maybe I'll iterate on it and see what we can get :D

I think you focused on the bonus point, rather than the first part (which is the relevant one).

https://github.com/desplega-ai/agent-swarm/pulls?q=is%3Apr+i...