Your agent cost $40 and took 34 seconds. But why? OpenObserve traces every agent session across models, tools, services, datastores, and user sessions so you can see exactly where time, money, and quality went. Detect loops, run online evals, and follow failures from the LLM call through your backend and database, alongside the logs, traces, and metrics from the rest of your production stack.
Hi Product Hunt, Ashish here, Head of Engineering at OpenObserve.
If your AI agent got stuck in a tool-call loop right now, would you know? Would you spot it before your customer did?
We didn't.
During a live demo, our own AI SRE Agent silently stalled. No errors. No timeouts. Nothing useful in the logs. We had to dump raw spans and debugged through them just to find the loop.
Reading raw spans isn't a debugging strategy—it’s an apology waiting to happen.
So we built AI Observability directly into OpenObserve. We wanted to see inside the black box.
Here is what it actually gives you:
Sessions map out every single turn. You see every LLM request, tool call, token count, cost, and exactly what prompt caching saved you.
Agent Graph plots your agents, tools, and models onto the exact same service map as the rest of your backend infrastructure.
Agent Behavior automatically flags the sessions that loop or fail—long before a user complains.
Online Evals let you score live sessions using any judge model (bring your own provider and key).
Annotation Queues let you turn those ugly, failed sessions into clean datasets so you can regression-test your fixes.
The best part? It's OpenTelemetry-native.
It normalizes OTel GenAI, OpenInference, OpenLLMetry, and Vercel AI SDK and many more out of the box. Nothing you’ve already wired up goes to waste, and you don’t have to ship a second copy of your data to another platform.
Our SRE Agent runs on this daily now, and it's still our harshest critic.
Point it at your own agent traces. I'd love to hear what you find.
congrats team! quick question - since traces capture full prompts and outputs, whats the story for sensitive data? users paste all kinds of stuff into prompts and that ends up in the trace. can we redact/mask fields before ingest or does everything get stored as-is?
Congrats on your launch!
One thing I'm curious about, since you're capturing full prompts and LLM responses, how do you handle PII that inevitably flows through agent traces? Is there a built-in redaction or masking layer before data hits storage, or is that left to the user's OTel pipeline to handle?
Does this integrate with products like Hermes? I tend to use this to as the main agent coordinator for my projects but it then also delegat3s to opencode. It would be amazing if this integrated with hermes so that it can monitor usage across all of my projects including the tasks that are delegated. I like the idea of b3ing able to better visualize and analyze usage directly, it is often the hidden layer that is missing and so telling when things are either not working or costing more than expected. Great work.
Hey PH - Eli from the GTM team at OpenObserve here! We've worked tons of different use cases and migrations, so if there are any questions feel free to drop them below!
We run OpenObserve self-hosted at Feature1, so congrats from a user. What I like about AI Observability: agent sessions land next to the logs, metrics and traces we already keep there, on OpenTelemetry, instead of in a separate LLM tracing tool with its own bill. Following a failure from the model call into the backend and the database is the part standalone tools cannot do. Looking forward to putting our own agent runs through it.
Some minor feedback, last I checked (~ month ago) it only allows integration via manual integration or custom harnesses, which is great of course for many cases.
However in case is with an existing harness, such as OpenClaw, Hermes, and LobeHub, I didn't see an easy way to easily integrate this feature.
Ideally would leverage corresponding model's API or webhooks to allow all uses of inference to be hooked up even in cases where the harness isn't cooperative.
Maybe this is all solved now, but Iast I checked was an issue as much work is done via existing or well known harnesses.
Please keep it up, really great improvements over the last year!!
I love OpenObserve because of its very friendly to use with great UI. I will like to know if there is test package that can be used as a proof of concept with my team?
How long does it take to go from a fresh install to seeing my first agent trace? What does the instrumentation actually look like?
@hengfei_yang for someone who wants to configure evaluation pipeline, how easy is it going to be? I am also looking to score the responses, say hallucination, risky and etc. With the agentic workflows we have lots of tool calls and that takes a while so how could we trace these tool calls and improve them?
Can I see what AI agents are doing when they interact with each other, and trace where things go wrong if one of them starts going off the rails?
Cool service! Can I break everything down by user and see statistics for each user? We have many agents working within a single user session, and that would be very useful for unit economics.
Is the trace approach applicable to multiple agents, or is it designed for single agent flows only? Btw, Congratulations @hengfei_yang & team @OpenObserve ✌️🎊.
Hi Product Hunt community, I'm Jake and one of the team members at OpenObserve. We're so excited to hear your feedback and questions today. Please drop your message here and let us know what you think.
Does ai observability share the same storage and query layer as the APM/Infra monitoring engine?
Hey Product Hunt, DevRel at OpenObserve here.
We've been building AI Observability into OpenObserve for the last few months, and it's finally live.
Everyone is shipping agents, but most tools only tell you the request went through, not whether the answer was any good. a hallucination still returns 200 OK. that's the gap we're closing.
how?
- trace every agent, tool call and model request
- score quality on live traffic, and run experiments before you ship
- send weak traces to a human, then turn them into eval datasets
More importantly it's one unified platform. LLM traces sit next to your logs and infra, OpenTelemetry native, self host or cloud, priced per GB not per span.
It's in beta and we'd love practitioner feedback. if you're running agents in prod, what's painful for you today?
thanks for taking a look.
If an agent uses many models in one session, can I see how much costs for each model, and total cost for the session?
Hi Product Hunt, Simran here from the OpenObserve team.
One thing we kept running into while working with AI workloads: an LLM call can succeed while the agent still fails.
That’s the gap we wanted to solve with AI Observability.
Instead of looking at LLM calls in isolation, we wanted to see the entire session: LLM calls, tool calls, tokens, cost, latency, evaluations, and the infrastructure underneath it.
And because it’s built into OpenObserve, those AI traces live alongside your existing logs, metrics, and application traces. No second observability stack just for your AI workloads.
It’s also fully OpenTelemetry-native, so you can bring telemetry from the frameworks and instrumentation you’re already using.
If you’re already running AI workloads in production, I’d be curious to hear what you’re actually using today to debug them.
Hi guys, Hengfei here, I designed this module, so let me add the part the launch page doesn't cover — what we deliberately chose not to build.
Sessions, not calls. Most LLM tracing anchors on a single request. But agents don't fail at a call — they fail across a path: right answer, wrong tool, fourteen times. So the session is the first-class object, and cost, tokens and scores roll up to it. Spans are the substrate, not the unit of analysis.
One data layer. We could have shipped a separate AI observability product. We didn't — because half of what kills an agent isn't the model. It's a vector DB timing out, a 429 from a downstream service, a retry storm in your own API. If agent spans live in a different system than your infra traces, you get to debug the same incident twice.
Scores are append-only. An evaluation is data, not a label. Change your judge prompt and the old scores don't get overwritten — they get a new version. Otherwise "quality improved" is unfalsifiable.
Bring your own judge. The judge model is yours, self-hosted open weights included. Evaluating production traffic shouldn't require shipping production traffic to someone else.
One thing that genuinely surprised me while building this: the OTel GenAI semconv renamed core attributes twice in two years (gen_ai.system → provider.name, events → input/output.messages). Betting on a fixed schema would have been the real mistake. The mapping layer turned out to be the feature.
What's the worst agent failure you've had to debug straight from raw spans? Collecting these — seriously.
About AI Observability by OpenObserve on Product Hunt
“OpenTelemetry-native observability for agents and LLMs”
AI Observability by OpenObserve launched on Product Hunt on September 10th, 2026 and earned 288 upvotes and 109 comments, earning #2 Product of the Day. Your agent cost $40 and took 34 seconds. But why? OpenObserve traces every agent session across models, tools, services, datastores, and user sessions so you can see exactly where time, money, and quality went. Detect loops, run online evals, and follow failures from the LLM call through your backend and database, alongside the logs, traces, and metrics from the rest of your production stack.
AI Observability by OpenObserve was featured in Developer Tools (519.1k followers), Artificial Intelligence (478.2k followers) and Tech (632k followers) on Product Hunt. Together, these topics include over 371.2k products, making this a competitive space to launch in.
Who hunted AI Observability by OpenObserve?
AI Observability by OpenObserve was hunted by fmerian. 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.
Reviews
AI Observability by OpenObserve has received 6 reviews on Product Hunt with an average rating of 5.00/5. Read all reviews on Product Hunt.
Want to see how AI Observability by OpenObserve stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
fmerian
Hi Product Hunt, Ashish here, Head of Engineering at OpenObserve.
If your AI agent got stuck in a tool-call loop right now, would you know? Would you spot it before your customer did?
We didn't.
During a live demo, our own AI SRE Agent silently stalled. No errors. No timeouts. Nothing useful in the logs.
We had to dump raw spans and debugged through them just to find the loop.
Reading raw spans isn't a debugging strategy—it’s an apology waiting to happen.
So we built AI Observability directly into OpenObserve. We wanted to see inside the black box.
Here is what it actually gives you:
Sessions map out every single turn. You see every LLM request, tool call, token count, cost, and exactly what prompt caching saved you.
Agent Graph plots your agents, tools, and models onto the exact same service map as the rest of your backend infrastructure.
Agent Behavior automatically flags the sessions that loop or fail—long before a user complains.
Online Evals let you score live sessions using any judge model (bring your own provider and key).
Annotation Queues let you turn those ugly, failed sessions into clean datasets so you can regression-test your fixes.
The best part? It's OpenTelemetry-native.
It normalizes OTel GenAI, OpenInference, OpenLLMetry, and Vercel AI SDK and many more out of the box. Nothing you’ve already wired up goes to waste, and you don’t have to ship a second copy of your data to another platform.
Our SRE Agent runs on this daily now, and it's still our harshest critic.
Point it at your own agent traces. I'd love to hear what you find.