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…
In plain words
Durable Swarm is an open-source framework that works as a replacement for OpenAI's Swarm, adding reliable execution to AI agent workflows. It allows multi-agent systems to automatically resume from their last completed steps if interrupted or restarted, making long-running agentic workflows resilient to failures. The framework is designed for developers building complex, interactive multi-agent systems that need to withstand transient interruptions without requiring extensive rearchitecting.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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 execution 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_...
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, October 2024
the whole month →
Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com