HMhmaxdml·Nov 5, 2024
Would be nice if there was a serverless library that lets you do in-process orchestration so you don't need abominations like Step Functions ;)
e.g., https://github.com/dbos-inc/durable-swarm
In Get me out of data helldbos-inc
durable-swarm
Python2024–2024
dbos-inc / durable-swarm
durable-swarm
Augment Swarm with durable execution to help you build reliable and scalable multi-agent systems.
2Distinct people
3Mentions
0Explicit recommenders
118GitHub stars
What to know before exploring
What it is
Augment Swarm with durable execution to help you build reliable and scalable multi-agent systems.
GitHub
Where it is used
No documented product use has been verified yet.
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
- dbos-inc/dbos-transact-py · linked in 2 of the same discussions
Mentioned in the same Hacker News threads. That is not proof they are substitutes.
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 day3 dated mentions
Observed mentions: 2024-10-17 16:00:26 UTC to 2024-11-05 00:21:20 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Oct 17 | 2024-10-17 00:00:00 UTC | 2024-10-18 00:00:00 UTC | 1 | 1 | 0 |
| Oct 18 | 2024-10-18 00:00:00 UTC | 2024-10-19 00:00:00 UTC | 0 | 0 | 0 |
| Oct 19 | 2024-10-19 00:00:00 UTC | 2024-10-20 00:00:00 UTC | 0 | 0 | 0 |
| Oct 20 | 2024-10-20 00:00:00 UTC | 2024-10-21 00:00:00 UTC | 0 | 0 | 0 |
| Oct 21 | 2024-10-21 00:00:00 UTC | 2024-10-22 00:00:00 UTC | 0 | 0 | 0 |
| Oct 22 | 2024-10-22 00:00:00 UTC | 2024-10-23 00:00:00 UTC | 0 | 0 | 0 |
| Oct 23 | 2024-10-23 00:00:00 UTC | 2024-10-24 00:00:00 UTC | 0 | 0 | 0 |
| Oct 24 | 2024-10-24 00:00:00 UTC | 2024-10-25 00:00:00 UTC | 0 | 0 | 0 |
| Oct 25 | 2024-10-25 00:00:00 UTC | 2024-10-26 00:00:00 UTC | 0 | 0 | 0 |
| Oct 26 | 2024-10-26 00:00:00 UTC | 2024-10-27 00:00:00 UTC | 0 | 0 | 0 |
| Oct 27 | 2024-10-27 00:00:00 UTC | 2024-10-28 00:00:00 UTC | 0 | 0 | 0 |
| Oct 28 | 2024-10-28 00:00:00 UTC | 2024-10-29 00:00:00 UTC | 0 | 0 | 0 |
| Oct 29 | 2024-10-29 00:00:00 UTC | 2024-10-30 00:00:00 UTC | 1 | 1 | 0 |
| Oct 30 | 2024-10-30 00:00:00 UTC | 2024-10-31 00:00:00 UTC | 0 | 0 | 0 |
| Oct 31 | 2024-10-31 00:00:00 UTC | 2024-11-01 00:00:00 UTC | 0 | 0 | 0 |
| Nov 1 | 2024-11-01 00:00:00 UTC | 2024-11-02 00:00:00 UTC | 0 | 0 | 0 |
| Nov 2 | 2024-11-02 00:00:00 UTC | 2024-11-03 00:00:00 UTC | 0 | 0 | 0 |
| Nov 3 | 2024-11-03 00:00:00 UTC | 2024-11-04 00:00:00 UTC | 0 | 0 | 0 |
| Nov 4 | 2024-11-04 00:00:00 UTC | 2024-11-05 00:00:00 UTC | 0 | 0 | 0 |
| Nov 5 | 2024-11-05 00:00:00 UTC | 2024-11-06 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
3 sourcesShow HN: Durable Swarm – A Framework for Building Reliable AI Agents
Hi HN!
Today me and qianli_cs want to share a new open-source project we've been working on called Durable Swarm. It's a drop-in replacement for OpenAI’s Swarm that augments it with durable execution to make your agentic workflows resilient to failures, so that if they are interrupted or restarted, they automatically resume from their last completed steps.
https://github.com/dbos-inc/durable-swarm
We believe that as multi-agent workflows become more common, longer-running, and more interactive, it's important to make them reliable. If an agent spends hours waiting for user inputs or processing complex workflows, it needs to be resilient to transient failures, such as a server restart. However, reliable multi-agent orchestration isn't easy—it requires complex rearchitecting like routing agent communication through SQS or Kafka.
Durable exe
Read the rest
cution helps you write reliable agents while preserving the ease of use of a framework like Swarm. The idea is to automatically persist the execution state of your Swarm workflow in a Postgres database. That way, if your program is interrupted, it can automatically resume your agentic workflows from the last completed step.
Here’s an example application–a durable refund agent that automatically recovers from interruptions when processing refunds:
https://github.com/dbos-inc/durable-swarm/tree/main/examples...
We also converted all of OpenAI’s example applications to Durable Swarm:
https://github.com/dbos-inc/durable-swarm/tree/main/examples
Under the hood, we implemented Durable Swarm using DBOS (https://github.com/dbos-inc/dbos-transact-py), an open-source lightweight durable execution library that we developed. The entire implementation of Durable Swarm is 24 lines of code, declaring the main loop of Swarm to be a durable workflow and each chat completion or tool call to be a step in that workflow. Check it out here:
https://github.com/dbos-inc/durable-swarm/blob/main/durable_...
Show HN: Durable Swarm – Reliable Multi-Agent Orchestration with OpenAI's Swarm
Hi HN!
Today we want to share Durable Swarm, a drop-in replacement for OpenAI’s Swarm that augments it with durable execution to help you build reliable and scalable multi-agent systems. Durable Swarm makes your agentic workflows resilient to failures, so that if they are interrupted or restarted, they automatically resume from their last completed steps.
https://github.com/dbos-inc/durable-swarm
We believe that as multi-agent workflows become more common, longer-running, and more interactive, it's important to make them reliable. If an agent spends hours waiting for user inputs or processing complex workflows, it needs to be resilient to transient failures, such as a server restart. However, reliable multi-agent orchestration isn't easy—it requires complex rearchitecting like routing agent communication through SQS or Kafka.
Durable exec
Read the rest
ution helps you write reliable agents while preserving the ease of use of a framework like Swarm. The idea is to automatically persist the execution state of your Swarm workflow in a Postgres database. That way, if your program is interrupted, it can automatically resume your agentic workflows from the last completed step.
Here’s an example application–a durable refund agent that automatically recovers from interruptions when processing refunds:
https://github.com/dbos-inc/durable-swarm/tree/main/examples...
We also converted all of OpenAI’s example applications to Durable Swarm:
https://github.com/dbos-inc/durable-swarm/tree/main/examples
Under the hood, we implemented Durable Swarm using DBOS (https://github.com/dbos-inc/dbos-transact-py), an open-source lightweight durable execution library that (full disclosure) we developed. The entire implementation of Durable Swarm is 24 lines of code, declaring the main loop of swarm to be a durable workflow and each chat completion or tool call to be a step in that workflow. Check it out here:
https://github.com/dbos-inc/durable-swarm/blob/main/durable_...
Me and qianli_cs are here to answer any questions!