No, that was a completely different project - build websites in minutes, not weeks. But yes, the AI wave did kill that because you can literally make websites in minutes with Claude code today. But it has the same name - Rocketgraph, and I built it.
Monitoring tools were built with the premise that humans have written the code and humans are reading the logs, querying dashboards. But today, it's far from the truth. The machine writes code and the machine debugs it. But the logging tools have not evolved beyond complex LogQL queries that take weeks to understand the documentation. And not to mention, the ever-evolving logging patterns within the same company.
It is impossible to detect anomalies in log patterns using deterministic methods alone. That is why companies like Datadog, etc have stopped at anomaly detection at the metrics layer. Because they are numbers you can predict. And you can't feed your entire firehose to LLMs because they blow up in compute.
I developed Rocketgraph that generates "snapshots" from billions of logs so that your agents can query and root cause without hallucinating and burning your engineering budget. First, we fingerprint the logs by masking away all the PII stuff, then use fuzzy matching to group together similar logs using TF-IDF. Then we apply IsolationForest to rank the logs with an anomaly score. By now, we have condensed them to 100-1000 log patterns we call a "snapshot". Here is the interesting part: we just make an LLM call with the service graph dependency map to root cause over the log patterns, and the result is something like what is shown. They are highly accurate.
It can be used to detect anomalous retry loops, weird call patterns, unseen formats, etc.
Basically, I'm building Datadog - but the user is an AI agent. A monitoring tool whose output is queryable and consumable by an AI agent.
Hey, I thought this might be helpful to some of you who are working in the observability space. It's a large dataset of real-world logs. You can use it to benchmark your tools. Or test the ones you are building. I am not the author.
I really like this library. It basically masks the PII data and creates log templates from logs. So you can ask questions like "How many times has the database connection timed out?" Or "How many times have users logged out of the app?"
Consider you have logs at ~100k/hour. And you are looking for a log that you have never seen before or one that is rare to find in this pool of 1000s of look-alike errors and warnings.
I built a tool that flags out anomalies. The rarest of the rarest logs by clustering them. This is how it works:
1. connects to existing Loki/New Relic/Datadog, etc - pulls logs from there every few minutes
2. Applies Drain3(https://github.com/logpai/Drain3) - A template miner to retract PIIs. Also, "user 1234 crashed" and "user 5678 crashed" are the same log pattern but different logs.
3. Applies IsolationForest(https://scikit-learn.org/stable/modules/generated/sklearn.en...) - to detect anomalies. It extracts features like when it happened, how many of the logs are errors/warn. What is the log volume and error rate. Then it splits them into trees(forests). The earlier the split, the farther the anomaly. And scores these anomalies.
4. Generate a snapshot of the log clusters formed. Red dots describe the most anomalous log patterns. Clicking on it gives a few samples from that cluster.
Use cases: You can answer questions like "Have we seen this log before?". We stream a compact snapshot of the clusters formed to an endpoint of your choice. Your developer can write a cheap LLM pass to check if it needs to wake a developer at 3 a.m for this? Or just store them in Slack.
Grafana sucks imo. Their UI is bad, it takes time to setup. It's very difficult to maintain it all together. There should be a free alternative. I'm surprised there is literally no free alternative to Datadog.
Got it. Yeah I'm building a monitoring tool for web applications. I guess I should start going to some conferences or something. Still figuring it out.
ok wow. I will check them out and start reaching out. Also any industries I should target with the current idea? Company size/position you have in mind?
Okay, I reached out to a few who are cursing DataDog, but also are not fully committed to buying what I'm building. How do I reach out to more people? I mean, it's like I KNOW there is some way here. Because they are not like "I'm happy with DataDog", but it's also not like "We're ready to abandon it for yours".
I talked to ones paying like $40k/mo and $80k/mo(DHH).
Makes a lot of sense. So I am thinking of building an AI-powered Datadog alternative. Why now? is because with AI I can rapidly build integrations to Ruby, Python and other languages.
But I'm really low-confidence on this one, because how do I make it reach a lot of people? Is there a need for this? Because I can make it really cheap.