HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
desplega-ai
agent-swarm
TypeScript2025–2026
desplega-ai / agent-swarm

agent-swarm

Your Company Agentic Operating System

AI & Machine LearningSystems & InfrastructureLanguages & CompilersDevOps & CloudCommunication & SocialAutomation & WorkflowsLibraries & SDKs
Explore on GitHubRead Hacker News discussions
3Distinct people
18Mentions
0Explicit recommenders
1.1KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Your Company Agentic Operating System

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by month18 dated mentions

Observed mentions: 2025-12-23 17:14:31 UTC to 2026-10-30 12:01:32 UTC.

0123452025-12-01 00:00:00 UTC to 2026-01-01 00:00:00 UTC (exclusive): 2 mentions; 2 submissions, 0 commentsDec 20252026-01-01 00:00:00 UTC to 2026-02-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-01 00:00:00 UTC to 2026-03-01 00:00:00 UTC (exclusive): 5 mentions; 1 submissions, 4 comments2026-03-01 00:00:00 UTC to 2026-04-01 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2026-04-01 00:00:00 UTC to 2026-05-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-05-01 00:00:00 UTC to 2026-06-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsMay 20262026-06-01 00:00:00 UTC to 2026-07-01 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2026-07-01 00:00:00 UTC to 2026-08-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2026-08-01 00:00:00 UTC to 2026-09-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-09-01 00:00:00 UTC to 2026-10-01 00:00:00 UTC (exclusive): 2 mentions; 1 submissions, 1 comments2026-10-01 00:00:00 UTC to 2026-11-01 00:00:00 UTC (exclusive): 4 mentions; 2 submissions, 2 commentsOct 2026

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Dec 20252025-12-01 00:00:00 UTC2026-01-01 00:00:00 UTC220
Jan 20262026-01-01 00:00:00 UTC2026-02-01 00:00:00 UTC000
Feb 20262026-02-01 00:00:00 UTC2026-03-01 00:00:00 UTC514
Mar 20262026-03-01 00:00:00 UTC2026-04-01 00:00:00 UTC110
Apr 20262026-04-01 00:00:00 UTC2026-05-01 00:00:00 UTC101
May 20262026-05-01 00:00:00 UTC2026-06-01 00:00:00 UTC000
Jun 20262026-06-01 00:00:00 UTC2026-07-01 00:00:00 UTC110
Jul 20262026-07-01 00:00:00 UTC2026-08-01 00:00:00 UTC202
Aug 20262026-08-01 00:00:00 UTC2026-09-01 00:00:00 UTC000
Sep 20262026-09-01 00:00:00 UTC2026-10-01 00:00:00 UTC211
Oct 20262026-10-01 00:00:00 UTC2026-11-01 00:00:00 UTC422

What Hacker News says

18 sources
harlequinetcie·Oct 20, 2026Submission

Ask HN: How do you decide to cut scope when AI makes it so easy to add?

I've been having this conversation with my co-founder for months. It's so easy to add incremental features nowadays, and most seem useful. There's nothing obviously wrong with them. On top of that, people are using the software, and they appreciate how complete it is. The UX is cluttered, but 99% of interactions don't use it, so who cares. How do you decide to cut scope when in the current setup there's nothing to lose? Am I simply to old school? For context, this is the project: https://github.com/desplega-ai/agent-swarm
2 points · Open discussion
tarasyarema·Oct 16, 2026
Hi there, Disclaimer: the blog should be glanced high-level as human, read the below instead. You can point your agents to it tho. We've been working on agent-swarm (https://github.com/desplega-ai/agent-swarm) as an oss MIT project for a while. One of the core principles on why we believe in is that when you adopt AI internally in your company, you should be free and not tied to a single provider (e.g. Devin). Yesterday Devin introduced the Devin Oncall, and we wanted to replicate the feature in the swarm, but with one thing in mind: what if Devin is down? As the swarm is built on top of a set of building blocks (not only agents), we created a set of workflow, deterministic scripts, and ui so that when a Pagerduty (or any other) comes it will handle it with automatic provider failover. It's a simple thing really. In the blog post our swar
Read the rest
m created explaining how to set it up you can see the high-level wf, and sub-wf. If for some reason you have a swarm running point it to it. If you have some other system, do it too, as it might give you the high-level arch. to replicate it. Cheers,
In Open Oncall: Open-Source Alternative to Devin Oncall
tarasyarema·Sep 29, 2026
Hi there! A few weeks ago, Boris posted how formal verification helped fix issues in their codebase (https://x.com/bcherny/status/2102543349102338309) and I definitely wanted to try it out in the swarm codebase. The idea was simple: 1. Go over the codebase and fine most critical parts that could be modelled 2. Pick the first few and try to model them based on main code 3. Find counterexamples 4. Generate failing tests for them (single tests file diff pr) 5. Go over each of them and fix them + add the counterexamples in the repo for reference I think this pattern is super nice tbh, and it helps a lot on reasoning around the code and implementation, specially when AI was involved. The main issue: we had to add a daily wf to check for any updates to the spec, so that we keep it in sync (price you pay when the language can not be expressive e
Read the rest
nough, e.g. js). Another win was that for the heartbeat system, which I wanted to refactor for a while, it managed to propose a simplification from 1.3M states to only ~4k (lol). I believe it can be used for complex systems refactoring, while keeping the same functionalities. Blog post about it (beware AI generated, but it contains some of the prompts we used during the session, just point your agent to the link and let it cook) -> https://www.agent-swarm.dev/blog/tla-plus-races-agent-swarm I've been wanting to use tla+ for years, but always struggled w the syntax when working on something non-trivial. AI generating the specs and explaining the reasoning behind them helped a lot! If you curious about the specs -> https://github.com/desplega-ai/agent-swarm/blob/main/specs/t... Cheers,
In TLA+ helped us fix and10 issues in our OSS project
tarasyarema·Jul 23, 2026
Hi, the blog post was written assisted with our own swarm, based on the experiment. Indeed we had the concept of workflows from the start (like n8n), but the point of the scripts is type safe executions that the agents can write, with access to APIs, MCPs, etc. E.g. this PR from ~10 days ago https://github.com/desplega-ai/agent-swarm/pull/934 was going in this direction, offering a way to defined type safe connections to able to use more the scripts instead of adding MCPs or tools. e.g. offering a way to do `ctx.api.gmail.searchEmail` coming from an OpenAPI spec. The whole point of this blog is the "dumb" realisation of the following: If you have an agent (say Claude Tag, or some other fancy Slack bot) that you keep asking the same things (e.g. check DataDog error and correlate PRs on a timeframe) and the agent does that process agentical
Read the rest
ly, you are wasting tokens. Now, if you give a way for the agents to write these scripts (code mode) the next time a task like that happens then essentially you just run that and you get easily 90% cost reduction in THAT process. Not globally, obviously.
In Code mode yields a 99.2% cost reduction in our systems
tarasyarema·Jul 23, 2026
Hi there! We've been building https://github.com/desplega-ai/agent-swarm in the open for a while, and one of the things we wanted to do since the start is find how powerful it can be to push for a code mode like env for the swarm. We tried it and we managed to reduce up +90% of token costs by using swarm scripts (the code mode variant we implemented) for some of our schedules. This is game changer, as we are able to 1. Run those schedules faster 2. Cheaper 3. More reliably Been thinking a lot now on how we should prompt and change the default templates to force the agents to build on top of this. If it can be re-used or it's a recurring thing -> scripts. Thoughts? Have you seen this type of improvements in your setups? Cheers,
In Code mode yields a 99.2% cost reduction in our systems
tarasyarema·Jun 29, 2026Submission

Show HN: The open-source alternative to Claude Tag

Hi there HN! Been working on agent-swarm since Nov last year, and talking with a lot of companies on the exact same narrative that Claude Tag and Karpathy are pushing as "breaking change" and "the new UX era of AI". We believe that as you move to an AI-native approach in your company you should be in control of the models, harnesses, context, and memory. It should not be a blackbox as Claude is doing. Hence the swarm is trying to solve this problem: and open project that let you define a team of agents that meet you where you work. Just @agent-swarm in any channel and you good to go. Want to continue the convo in email? You can. It is FOSS and we aim to always be. AI models might be closed, but how you integrate it should be open. https://github.com/desplega-ai/agent-swarm Cheers,
3 points · Open discussion
harlequinetcie·Apr 8, 2026
We ended up adding workflows with deterministic paths, that can use RAW API calls, CLIs, and agents. I think that was a big differential. We also added pi-mono, and started using more and more other models for different tasks (Gemini, K2.5, GLM-5, you name it). I think the problem is that most are building solutions that rely in one provider, instead of focusing self learning capabilities on improving the cost-quality-speed ratio. For reference: https://github.com/desplega-ai/agent-swarm
In Google open-sources experimental agent orchestration testbed Scion
tarasyarema·Mar 18, 2026Submission

Show HN: Agent-fs – The missing filesystem for agents (and humans)

Hello there HN, coming back with more agentic suff :) 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 an
Read the rest
d 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?
2 points · Open discussion
tarasyarema·Feb 26, 2026
Yeah, saw that paper. And I have the following notes on it: 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/desp
Read the rest
lega-ai/agent-swarm/pull/86 maybe I'll iterate on it and see what we can get :D
In Show HN: Agent Swarm – Multi-agent self-learning teams (OSS)

Showing the 15 most recent of 18 sources. Enable JavaScript to search and browse every indexed mention.

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.