An open-source lib to summarize sessions (rrweb) when users hit bugs
Hi HN, Rohan and Michael here from Decipher (https://getdecipher.com/). We’re excited to introduce AI-generated session summaries and open source the pipeline. It processes raw rrweb events to produce plain English summaries of what happened leading up to and around an error. You can find the code here: https://github.com/decipherai/session-replay-analyzer We created Decipher because we were frustrated with noisy alerts, time-consuming error triaging, and customer churn due to bugs and session replay analysis is a powerful step forward. Here’s an…
In plain words
Decipher is an open-source library that converts rrweb session recordings into plain English summaries when users encounter bugs. It analyzes raw session replay data to describe what happened before and during an error, helping developers quickly understand issues without manually reviewing sessions. The tool is designed for development teams who want to reduce error triaging time and better understand user-facing bugs.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, Rohan and Michael here from Decipher (https://getdecipher.com/). We’re excited to introduce AI-generated session summaries and open source the pipeline. It processes raw rrweb events to produce plain English summaries of what happened leading up to and around an error. You can find the code here: https://github.com/decipherai/session-replay-analyzer We created Decipher because we were frustrated with noisy alerts, time-consuming error triaging, and customer churn due to bugs and session replay analysis is a powerful step forward. Here’s an interactive sandbox so you can try out the AI pipeline yourself: https://sandbox.getdecipher.com/ (the robot dogs for sale aren’t real). And here's another example of the output: https://demo.getdecipher.com/issue/6d5cfbe6-c861-4590-a262-0.... The client throws an error because something went wrong on the server and Decipher understands that the user started uploading the PDF and then clicked the “get advice” button. The analysis pipeline is easy to set up — we'd love to hear your feedback! And if you'd like to try a more productionized version of it on your own Next.js app, try out Decipher. Here are the docs: https://docs.getdecipher.com/next.js.integrate.
Does a similar job
all alternatives →
- TTTime travel debugger for web development2021 · replay.io · ▲681
- WRWe’re open-sourcing our session replay tool2023 · github.com · ▲408
Hey HN! We’re open-sourcing highlight.io (https://github.com/highlight/highlight), a session replay and error monitoring tool. Highlight.io gives you a high-precision video-like replay of what users are doing when an error or exception occurs in your web app, along with a full-fledged error monitoring experience (similar to bugsnag, rollbar, etc..). The main value prop of highlight.io is that we help you understand the full context surrounding an error and allow you to drill down to the code path that a user invoked (i.e user clicked button X, sent network request Y, and…
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 · 19d 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, June 2024
the whole month →
La Growth Machine▲1,216Create personalized, multi-channel conversations at scale
AI · 2024 · lagrowthmachine.com
PyjamaHR▲1,132Hiring on autopilot. The AI applicant tracking system (ATS).
Work · 2024 · pyjamahr.com