kvaranasi_
kvaranasi_ on Hacker News
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.
Posted by
kvaranasi_ on Wednesday June 17, 2026 @07:14PM
from the show-hn dept.
https://github.com/Rocketgraph/rocketgraph
Hi HN, I'm Kaushik, and I built Rocketgraph. I believe that while other spaces have caught up to the AI wave, the observability space is still lagging behind, using the same tools and dashboards that we use to analyse logs from human-written code. But now the code is written and debugged by AI, so we need to rethink how we do observability where the observer itself is an AI.The problem that I...
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.
I would love to hear your thoughts on this.
Posted by
kvaranasi_ on Sunday May 24, 2026 @05:46PM
from the show-hn dept.
Posted by
kvaranasi_ on Friday April 03, 2026 @04:10AM
from the github.com dept.
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.
Posted by
kvaranasi_ on Friday March 13, 2026 @03:31PM
from the ask-hn dept.
Hey, I'm just curious. I know that there is a feature in Datadog that shows new log patterns formed and disappeared. So when something goes wrong, what is it that developers look for beyond this? It should be pretty straightforward to find an error in the haystack. By looking at novel error patterns, right?When was the last time you had to spend hours debugging to find the root cause?
Posted by
kvaranasi_ on Friday March 13, 2026 @09:03AM
from the github.com dept.
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?"
Posted by
kvaranasi_ on Sunday March 08, 2026 @11:34PM
from the show-hn dept.
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.
Posted by
kvaranasi_ on Saturday February 21, 2026 @06:31PM
from the show-hn dept.
https://deploydiff.rocketgraph.app
I built this tool that connects to your Kubernetes and Datadog via read access. Collects logs before(60 minutes) and after(15 minutes). And compares them to catch regressions early on. This eliminates the need to jump across 5-6 dashboards to know if the deployment is working as expected, just by looking at the telemetry data. It's a thin intelligence layer for deployments. Usually, you get...
Posted by
kvaranasi_ on Tuesday February 17, 2026 @04:50PM
from the show-hn dept.
https://dashboard.rocketgraph.app
Hi HN, I've been building RocketLogs, an intelligence observability layer that sits on top of Loki, Tempo, and Prometheus.The problem I kept running into: you get paged at 3 AM, open Grafana, flip between six dashboards, grep through logs, try to figure out which deploy went out, and an hour later you maybe have a root cause. You still need to dig through code and find the culprit. The data is...
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.
APM, logs, metrics and alerting all on a single pane of glass.
Posted by
kvaranasi_ on Sunday January 11, 2026 @06:07PM
from the ask-hn dept.
Is it just me or do you guys think Datadog pricing is crazy? I mean even to SEE APM you have to pay like $50/mo minimum. What if my app has just 10 requests per month, can I get for free? No, pay us. What if it's just me building? No, still pay us.But hey we'll give you this metrics page for free which just basically tells you your RAM usage.And the worst part is, there is no proper alternative...
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.
Posted by
kvaranasi_ on Sunday January 11, 2026 @03:19PM
from the ask-hn dept.
Hey guys,I've come all the way to SF to build a startup. But honestly doesn't feel like much has changed. Is there anything I need to do in order to leverage SF better? Or does being in SF doesn't really matter that much?
Posted by
kvaranasi_ on Tuesday September 30, 2025 @01:26AM
from the github.com dept.
can you please email me at kaushik [at] rocketgraph.io
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.
Posted by
kvaranasi_ on Monday September 08, 2025 @09:26PM
from the ask-hn dept.
I don't understand why people pay thousands of dollars to DataDog when you can do the same with Grafana. I would like to understand what's so good about it.
What could be one such business domain?
Posted by
kvaranasi_ on Sunday January 05, 2025 @09:23AM
from the ask-hn dept.
I'm looking for tools that integrate well with AWS Cloudwatch, Datadog and other telemetry logging systems and can predict errors in the infrastructure before they even happen. Possibly even integrate with Github to get PR data and asses if a deployment might have a high chance of failure. Basically create a time-series like representation of all actions in the infrastructure(Infrastructure As...
Yeah. Needs to be more concrete.
Correct they come into CSV -> analytics. They don't care if we use Postgres or Mongo.
I think this is probably by using a COPY command. Assuming the file is on the same server as Postgres. But from a windows/linux machine, if a user wants to upload the CSV file, I don't see any options in the market.