HNHacker News
TopNewBestAskShowJobs

tarasyarema

143 karma · joined November 29, 2018

https://github.com/tarasyarema
submissionscomments
tarasyarema··on Show HN: Agent Swarm – Multi-agent self-learning teams (OSS)
hope it does not go rogue...
tarasyarema··on Show HN: Agent Swarm – Multi-agent self-learning teams (OSS)
Hello there HN!

We've been building agent-swarm since November last year, and we wanted to share an update on its capabilities, specially focused on the self-learning part.

After all the hype with OpenClaw, I thought that the existing architecture needed a rewrite to make it compounding. Hence, last week we implemented a self-learning core to the swarm so that it can compound.

It follows really similar ideas to the OpenClaw where there's a SOUL.md and IDENTITY.md. As it's docker based, it has some personal and shared volumes that persist, so those are used to track re-usable scripts and notes. We also added SQLite based memory that agents can write to and query. The interesting part about it is that there's personal and shared memory, which allows the lead to propagate learnings across the swarm!

We've been using it non-stop for the last week, and I already see the compounding effects. E.g. we have a morning scheduled task that makes the lead assess the previous day work, and figure out ways to improve it's processes, and it got better!

To end, note that it's fully OSS and it's as easy as deploying a docker compose to a VPS, or even locally. It's core is based on an MCP that the lead and all workers share, which allows you to impersonate the lead locally to control the swarm from your coding agent too!

We implemented a super simple UI at app.agent-swarm.dev that runs in the browser only so you can put your API url and key to see it in action.

P.S.: It uses the claude CLI only now, so there should be no issue with the Anthropic terms, and it's really thought to be self-hostable.

P.S.2: Obviously, all the agent swarm code has been written at 95% by agent swarm via Slack :D

If you have doubts or questions about the architecture, or what we are planning to build next, happy to chat in the comments section!

tarasyarema··on Ask HN: What are you working on? (February 2026)
Working on multiple things focused mainly on how to push the limit of validating changes in an automated way in the world of AI:

- https://github.com/desplega-ai/qa-use CLI to control browsers and tests locally, coding agent friendly - https://github.com/desplega-ai/agent-swarm OSS agent swarm that can be deployed with docker compose using Claude - https://desplega.ai platform that supports qa-use backend

Cheers!

tarasyarema··on Show HN: Ghidra MCP Server – 110 tools for AI-assisted reverse engineering
Simple question: why not a cli instead? As seems that lately LLM and agentic tools seems to be better at using clis rather than bloated MCPs?
tarasyarema··on Are We Doomed Yet?
So after all the OpenClaw and moltbook hype and drama, I decided it's time to have a place to gauge how doomed we feel (as techies).

No auth, just vote and it will store that. Note that you might vote more than once.

Code at https://github.com/desplega-ai/ai-toolbox/tree/main/arewedoo...

tarasyarema··on Choose Boring Technology (2015)
In the age of AI, choosing boring tech seems like a way to improve your outcomes. That's why all examples from big labs are in either TS or Python. Same applies to infra, dbs, and other stuff.

Conjecture: Embrace boring tech, to build new tech.

tarasyarema··on Agent-swarm: How to burn your Claude Code Max sub
Hi there HN!

We built an MCP server that coordinates multiple Claude Code instances running in Docker containers. It follows a lead/workers pattern, and the MCP glues the agents together.

They get a full ubuntu with sudo (YOLO) and a way to spawn services with PM2 (so they are persisted and restarted on container restarts).

Also, they have persistent workspaces, both for personal and shared across the whole swarm, so the lead can micromanage the workers more easily :D

It's super easy to setup and deploy. You can run it locally, really the only thing required is running `claude setup-token` and good to go.

WIP:

- Only tested with Claude Code, though architecture should support other CLI agents (Gemini CLI, Codex, Opencode). - Horizontal scaling works but coordination gets chatty with many workers (needs prompting)

Open to feedback on the architecture, or similar projects!

tarasyarema··on Show HN: WillItFront.Page – Test your HN post before submitting
Well the timing is one thing that it outputs, but it also analyzes the content for things like:

1. Relevance to HN (e.g. OSS, relevant tech articles, etc.) 2. Similar posts matching (e.g. if it's repeated, or low-impact ones) 3. Provides recommendations on title, description

To be fair, it's pretty "dumb" now, as it does a mix of deterministic queries to the database + LLM analysis to build the report.

You can see the plan for the idea tester here https://github.com/desplega-ai/ai-toolbox/blob/main/willitfr...

tarasyarema··on We hacked Lovable to Vibe QA your apps
another
tarasyarema··on We hacked Lovable to Vibe QA your apps
this is an example reply
tarasyarema··on Tunnl.gg
Is this any different from localtunnel? Nice thing about that one is that its oss, actually we forked it in my company to do some more custom stuff.

Any plan to make it oss?

https://github.com/desplega-ai/localtunnel-server

tarasyarema··on We hacked Lovable to Vibe QA your apps
Hacked the Lovable.dev site to be able to inject an iframe in there, and allow users to vibe QA their app inside the native experience.

It was pretty straight forward to do, specially thanks that all vibe coding apps have iframes with the dev sites, so it's easy to get the url. Also, funny enough, they are generally served with a token param, that is perfect to use externally as in our case: to vibe e2e test the app.

But... obviously it might get flaky if they change something, probably need to vibe Qa the vibe QA :D

Repo for the extension here https://github.com/desplega-ai/vibe-qa-extension

tarasyarema··on Ask HN: What Are You Working On? (Nov 2025)
We are building https://desplega.ai which is a QA agent that help teams ship fast without compromising quality.

We focus on making it as fast as possible, integrated into CI, MCP for local dev, and support both an autonomous (we call it discovery) and guided test creation approach.

We believe that in the era of vibe-coding, quality is key, as we are lazer focus on building a solution that scales with your product, and removes the burden of QA from your team.

Technically, we built an in-house engine that is in charge of generating the tests, that speeds up and gets better the more you use it.

tarasyarema··on Ask HN: What Are You Working On? (Nov 2025)
That's a great idea, and I live the UI! I wish I have some time now to learn Japanese now...
tarasyarema··on Benchmark for Agent Context Engineering (2025)
This last days I wrote about agent context engineering, based on the learning from building agents this last year.

tldr: Context control is key for complex flows, if you are not doing that you are just guessing.

What do you think?

tarasyarema··on Launch HN: Propolis (YC X25) – Browser agents that QA your web app autonomously
Looks interesting! How it would work in terms of latencies? Also, would you be able to run on CI, or even with ephemeral envs? From my experience it is key to be able to run it on each change.
tarasyarema··on QA-use-MCP: MCP for E2E testing
We use PW for the interaction with the browser, but really how we represent what to do is in a custom format (could be executed in other frameworks too). So the PW we could generate would be a subset, where the more interesting parts (custom functions) are not really implemented in PW.

Also part of our format is specially finding deterministic way of running steps, with automatic healing when failed. And we also build the whole system in a way that is self-hostable, so in the cases you mention you could be able to have control over what is run and where.

tarasyarema··on QA-use-MCP: MCP for E2E testing
Totally! Actually self hosting the localtunnel was key to improve latency, and it was easy enough to do.

Also about the CLI thing you mention, we had cases where people did not use MCP clients, so I actually wanted to expose a way to interact with the tools directly without the need of the server running!

tarasyarema··on QA-use-MCP: MCP for E2E testing
As I mentioned above, a playwright won’t make the cut for many of the serious test cases we’ve seen, you need a whole system that ensures your tests are run and improved immediately. We created this project in a way that supports on-premise deployments, but you’ll need to run the whole engine and eventually use some SLMs/LLMs at different stages.
tarasyarema··on QA-use-MCP: MCP for E2E testing
One of the things we used is this algorithm with retries from meta: https://engineering.fb.com/2020/12/10/developer-tools/probab...

If your challenge is flakiness, this should help initially. Unfortunately, there’s a lot of work in our engine, and a custom system to handle operations that goes beyond vanilla Playwright so running it locally would be quite challenging.

tarasyarema··on QA-use-MCP: MCP for E2E testing
Hey there, been building an MCP to help discover, automate and run E2Es automatically connected to you Cursor / Claude / Codex / etc.

Funny enough, one of the most challenging things while building it was to be able to remotely control the browser that runs locally (been using https://localtunnel.me/ for it), while making sure that it does not impact the user too much.

Also, I wondered if there's someone that is shipping CLIs with an "mcp" command, as seems that having a normal CLI for the funcionatilitie sof the MCP would make a lot of sense + with the option of running it as an MCP if the user wants to.

Have you seen this pattern?

Also, as there's a lot of buzzwording around MCPs, any of you that been using an MCP as a daily driver? For me it was the github one, specially for code search and stuff like that.

tarasyarema··on Resend to RSS, or when a friend wants RSS instead of an email
Here's today funny story:

I'm building a company and as we are early stage, we have a newsletter for people that might be interested in our progress, and one of them is a good friend of mine. Nevertheless, he asked to be removed from our newsletter, and instead of just unsubscribing like a normal person, he said "just give me an RSS feed"... So I built this while having lunch today...

The interesting technical bit: Resend's broadcast API doesn't return email content (it's documented but still surprising). So you can't just fetch broadcasts and serve them as RSS...

The workaround is to:

1. Fetch broadcast metadata (subject, from address) 2. Fetch all sent emails separately 3. Match them by comparing subject + from fields 4. Cache everything in Vercel blob storage

The cron job respects Resend's 2 req/sec rate limit, so first sync takes ~4 minutes for 370 emails. But subsequent runs are incremental - only 9 seconds when there's nothing new.

Built with Next.js API routes + Vercel Blob + Vercel Cron. Works surprisingly well for such a hacky approach. The matching-by-subject thing feels fragile but hasn't failed yet jeje

---

PS: Are you still using RSS?

PS2: I initially thought of using Google Groups for this, but seems it's not supported. Sad :/

PS3: Thanks Claude Code 2 <3

tarasyarema··on Redis is fast – I'll cache in Postgres
I completely agree with your view! I use postgres for all, as the cost of switching to the (scalable) solution for this kind of problems is low, and in the ens let’s be realistic about how “viral” your app can get…

When I worked in a bigger company in the past we used postgres to store raw blobs for data transformation pipelines (+1T table), and queries to it were instant due to good index usage. Others might have gone to BigQuery or something else making more complex and def more expensive.

PS: I love tools like Temporal, Hatchet or Oban that rely on Postgres and can scale a ton too.

tarasyarema··on Launch HN: Ghostship (YC S25) – AI agents that find bugs in your web app
If you register, you can see it's $5 per run (voyage)
tarasyarema··on Launch HN: Ghostship (YC S25) – AI agents that find bugs in your web app
Completely agree with some of the comments, actually the hardest part is to execute these tests in a fast an reliable manner paralelizing the most of it, for your regression tests.

As we all know, in large orgs the form issue has been solved by using trusted components with unit tests. What worries me is how somebody were actually to provide valuable bugs, those that keep you up at night trying to fix them.

I worked with exploratory testing companies that would report hundreds of bug that nobody ever cared about. Does YC really care about the bug that they found, or have a business impact?

(Actually coming from building a company in this area now https://desplega.ai, you can try it out for free too)

tarasyarema··on Show HN: I built a text to JSON local tool in GitHub Spark
Hi there!

I just received the email from Github that they enabled Spark for my account, and I wanted to give it a try. I asked the same prompt to Spark and v0 and Spark did pretty good, and actually it let change the theme (in an opinionated) way that is pretty easy if you want to try some presets.

It's a simple text to JSON tool using a few common models, using an API key that is stored in the browser, you can see it in the repo here: https://github.com/spark/tarasyarema/text-to-json-schema. Surprisingly I always end up doing a lot of this type of operations, and wanted to give it a try, maybe I end up using it :D

What do you think about Github moving into this realm of generative apps? Will they win the lovables' and v0s?

Only bad thing is

1. You can not make the link public... you need to be signed in into Github... 2. Tried to deploy with Vercel and seems the spark module is private...

Also in the first try it used a function spark.llm which was not even exported which felt weird, and actually required no API key... I could not find any docs around it, anyone has some insights on it?

Cheers!

tarasyarema··on How I found my way to contribute to OSS
Hi there!

I always wanted to contribute to OSS. I tried direct ways to do it, like Hacktoberfest, finding good-first-issues, reading contribution guides. Nevertheless, after a while I found that the best way to do it (for me) was to actually build something I was passionate about first, which naturally led to contributions.

tl;dr: Stop trying to force contributions. Start by solving your own problems, and the contributions will follow.

Curious about how did you started to contribute? Any fun stories around that?

tarasyarema··on Ask HN: Is it worth investing on gamifying your app early on?
Interesting thought, this reminds me of the universal paperclips game, but applied to a start-up. I believe gamifying onboardings could be an interesting experiment, but haven't seen any company lately trying this.
tarasyarema··on Show HN: Kan.bn – An open-source alterative to Trello
Nice one, more of a random question: are you planning on having paid only features for the project, or have it fully self-hosted version be the same in terms of features as the hosted one?
tarasyarema··on Show HN: Time Travel with Your SQL
I also understood that, but seems unreasonable to be able to achieve it without somehow storing the state via scd or some sort of audit + multi engine support
← PreviousPage 3 of 4Next →