Agentspan is an open-source server and SDK for running AI agents as durable workflows. You can define agents programmatically, execute them server-side, and inspect each run and execution state in the UI. Agentspan adds crash recovery, human-in-the-loop approvals, guardrails, tool history, and observability around the agent frameworks and LLMs you already use. MIT licensed.
Hey Product Hunt,
We built Agentspan because production agent execution gets messy fast, and we're working to fix that. Common issues include state loss, human approvals needing resume logic, tool calls needing auditing, and retries causing repeated side effects.
Agentspan gives agents a durable execution layer. You define agents client-side, but execution state, tool history, approvals, and observability live on the server. The goal is to make agents easier to operate and debug without forcing teams to abandon the frameworks or models they already use.
The project is open source and MIT-licensed. Check out the repo at https://github.com/agentspan and the quickstart at https://agentspan.ai/docs/quicks....
The durability layer is the piece most agent frameworks skip. We're building AI workflows at RetainSure and the biggest headache isn't the LLM calls, it's what happens when a step fails partway through and the state is gone. Keeping execution state server side while defining agents client side is a clean separation. Does Agentspan support partial retries, or does a failure restart the whole run?
Crash recovery for agents is the thing nobody talks about until it breaks in production. We've had workflows silently fail partway through with no state to resume from. Human in the loop approvals are the other piece teams always bolt on last minute. Does Agentspan support branching approvals, where different steps route to different reviewers?
The durable runtime angle is the part I’d look at first. For agent teams, the hard bit is usually not starting a run, it’s resuming state, handling approvals, and seeing exactly what changed after a long task.
Durable AI agents that survive failures and interruptions is one of the harder infrastructure problems right now. Open-sourcing the runtime is a real commitment to the ecosystem. We've been building in the customer success for developer tool companies space at RetainSure, and Agentspan touches on something we think about a lot: how agent persistence changes what's possible in long-running business workflows. What's your approach to handling state when agents run for hours or days?
@nickorkes Congrats! Looks amazing, it's super cool for people who want to just focus on the code and don't spend too much time on the infra.
QQ, maybe trivial since I didn't check the codebase in detail, but by server, you mean it's still local, right? Not based on any specific cloud provider. It could be amazing to see adapter/connectors/versions on major cloud providers too, and have it super easy to deploy with few line of code (then no need to learn anything major from any provider side).
About Agentspan on Product Hunt
“Open-source runtime for durable AI agents”
Agentspan launched on Product Hunt on May 18th, 2026 and earned 92 upvotes and 13 comments, placing #19 on the daily leaderboard. Agentspan is an open-source server and SDK for running AI agents as durable workflows. You can define agents programmatically, execute them server-side, and inspect each run and execution state in the UI. Agentspan adds crash recovery, human-in-the-loop approvals, guardrails, tool history, and observability around the agent frameworks and LLMs you already use. MIT licensed.
Agentspan was featured in API (98.2k followers), Open Source (68.4k followers), Developer Tools (512.9k followers) and GitHub (41.2k followers) on Product Hunt. Together, these topics include over 113k products, making this a competitive space to launch in.
Who hunted Agentspan?
Agentspan was hunted by Nick . A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Agentspan stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Nick