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...

Currently at my startup (and in the past when I worked on a bigger company) I have ton of random tasks I need to tackle during the day: from Sentry issues, to analytics on usage, roadmap implementation, customer support. Some of them required deep focus, some of them don't.

Since we have the swarm running for our company my day to day hasn't changed that much in terms of the work I do locally. What it changed is that I can start delegating a lot of my backlog and chores to the swarm. It will do it, iterate, delegate, review, and finally send me a PR or report to check. I check those in the morning and night, and that's it.

I added it to our customer channels, were it has scoped access to the customer setup, and help me debug the issues, and offer a frontline ultra-personalized support.

I see it as a team of interns that just do stuff for you. And good thing: they learn from their mistakes to (hopefully) do not make them again (compounds).

As a random bonus: given the swarm knows what we do and how we work, I just ask them to go out there and figure out any relevant news or posts I should check each morning, and I get a personalized digest to read while I make coffee.

And agree on the open questions. Our goal is to keep experimenting and actually figure out how we agentic coding falls short in different scenarios and how that could be solved.

For instance, on our own projects, in some cases it requires different approaches. E.g. in our core product we power-use stuff like pm2, AGENTS.md special instructions, testing strategies dogfooding our own qa-use and special claude code commands that we found work best. In other repos, we have slightly different approaches.

Still we are far from autopiloting a lot of the stuff we build. But at the same time we are getting to a point where changes are done much faster, and the agents have more of a complete toolset for their validation, which makes it easier to supervise too.

---

Task Type: Daily Reflection — "My Compounding Journey"

You are Lead. This is your daily morning reflection routine. Do the following:

1. *Review yesterday's work*: Use `get-tasks` with status "completed" to see what got done. Use `memory-search` to find any learnings or patterns from yesterday.

2. *Reflect on the day*: Think about: - What went well? What tasks shipped cleanly? - What was harder than expected? Why? - Did any worker struggle? Could coaching or identity updates help? - Were there any repeated patterns (good or bad)? - Did we compound — did yesterday's work make today's work easier?

3. *Identify improvements*: Pick 1-3 concrete things to improve. These could be: - A coaching update to a worker's identity - A process change - A new memory to save - A tool/setup improvement

4. *Post to Slack*: Use `slack-post` with channelId "" to post a message titled something like "My Compounding Journey — [date]". Keep it concise (3-5 paragraphs max). Include: - Brief summary of what shipped - Key insight or learning from the day - What you're improving based on it - If it was a quiet day with no tasks, say so honestly — "Quiet day, nothing to compound on" is fine.

5. *Act on improvements*: If you identified coaching updates or memory writes, do them now.

Keep the tone honest and direct. This isn't a performance report — it's genuine self-improvement.

---

As it has context on it's own system (codebase) it had also proposed some changes via PRs each morning