NetFabric – next-gen network monitoring solution
Hi HN! We’re Tobias and Beni, co-founders of NetFabric. NetFabric is a next-gen network monitoring solution that’s here to tackle the chaos of network downtime with a fresh approach using mathematical models and machine learning: We integrate all your network data sources into a single, easy-to-use platform, giving you clear answers to any network question in real time. # Why Network Monitoring Needs a Revolution Network downtime is a massive headache for companies everywhere. Just an hour of downtime can cost millions—Amazon lost $34 million in just one hour in 2021! But the pain doesn’t…
What it does
In the maker’s words, at launch
Hi HN! We’re Tobias and Beni, co-founders of NetFabric. NetFabric is a next-gen network monitoring solution that’s here to tackle the chaos of network downtime with a fresh approach using mathematical models and machine learning: We integrate all your network data sources into a single, easy-to-use platform, giving you clear answers to any network question in real time. # Why Network Monitoring Needs a Revolution Network downtime is a massive headache for companies everywhere. Just an hour of downtime can cost millions—Amazon lost $34 million in just one hour in 2021! But the pain doesn’t stop at the financial hit. Downtime disrupts operations, ties up engineers in endless troubleshooting, and damages customer trust. The issue with current network monitoring tools is that they offer only basic insights into the complex world of networks. They rely on fragmented data, leading to false positives and incomplete problem resolution. This often means engineers spend excessive time deciphering alerts and dealing with misleading signals, which only prolongs downtime and worsens operational inefficiencies. # Our Innovative Approach Leveraging Years of Research At NetFabric, we aim to revolutionize the network monitoring world with a bold new approach. Unlike traditional solutions, NetFabric seamlessly merges observations coming from a wide range of network sources (such as routing information, forwarding tables, device configurations, and logs) into one coherent knowledge base. As a result, it delivers actionable intelligence, offering a comprehensive and accurate understanding of network issues while effectively managing the flood of alerts from conventional tools. NetFabric achieves this by addressing two fundamental challenges: 1. Network Diversity: First, real-world networks vary widely in terms of deployed devices, protocols, and architecture; this network diversity causes variations in the representations of monitoring data (such as configurations, metrics, or logs), preventing one-size-fits-all monitoring solutions. NetFabric addresses this by integrating large language models (LLMs) to handle non-standard data sources and user queries effectively. 2. Protocol Complexity: Second, at their core, networks are driven by intricate protocols. With a rigorous understanding of protocol logic, network monitoring can generate valuable insights from the available data, e.g., by explaining why a given network problem was observed, and how the problem can be resolved. Since such a systematic understanding of protocols is beyond LLMs, NetFabric complements LLMs with advanced mathematical models informed by a decade of academic research. By merging these technologies, NetFabric delivers a unified and complete view of complex networks and provides actionable insights while cutting down on false positives. This dual approach not only optimizes resource allocation but also helps organizations minimize downtime and keep their operations running smoothly. # Some Of The Use Cases That We Enable: - Faster issue resolution: We naturally guide operators towards the problem across data sources and layers, enabling real-time root cause analysis. - Actionable alerts & reports: We make alerts actionable by adding the missing context to correlate, aggregate and filter them before they reach your inbox. - What-if & resilience analysis: We improve availability and proactively prevent incidents by leveraging our models to evaluate what-if scenarios. - Meaningful AIOps: We unlock large language models (LLMs) for network data, and combine them with our mathematical models where their reasoning abilities fall short. - Many other use cases: Furthermore, our approach applies to network security, application & multi-cloud monitoring, planning, cost management, self-healing networks, auto-documentation, and more. We’d love to hear your thoughts on network monitoring, share your experiences, and get your feedback!
Does the same job
all alternatives →
- KWKnow when your network is down2016 · ▲7
Panos here - cofounder of NetBeez. We started NetBeez because we were not able to detect who and where are the users experiencing network problems. When the Raspberry Pi came out we immediately saw the perfect platform to use for our monitoring agent. And we decided to build the tool that would capture the end-user experience on wide area networks. The low cost of the Raspberry Pi enabled us to build a tool that can scale to dozens and hundreds of locations without costing an arm and a leg. NetBeez does both wired and wireless monitoring. You can try it for free here:…
- AFAPI for network testing from 20k+ real devices worldwide2024 · developer.bitping.com · ▲9
Hi HN! I'm Nick, one of the cofounders of Bitping, and we'd like to share a tool that we've been working on for the past couple of years that lets you test network connectivity from real user devices around the world. We originally were part of a hackathon focused on building a product that is powered by micropayments and we settled on a network that could ping other network devices and users could be paid in fractions of a cent for performing said work. After winning the hackathon, we built an uptime monitoring service and discovered some discrepancies between our data and traditional…
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 · 27d ago · cactuscompute.com
Launched alongside, July 2024
the whole month →
- IC
Many years ago, I made VJ softwares (to mix live visuals in clubs) for unexpected platforms like the Game Boy Advance, the Playstation 2 and the Raspberry Pi. This year, I’m back with a new web-app: Pikimov. Inspired by Photopea (a free Photoshop clone), I created this web-based motion design & video editor as an alternative to After Effects, to fill empty void. It's free, without signup, without cloud uploads (your files stay on your machine), and your projects are not used for AI models training.
AI · 2024 · pikimov.com
