Libretto PR agents – Automatically fix failing playwright scripts
Libretto PR agents is a free TypeScript library for maintaining Playwright browser automations. Add one line of code to your existing Playwright scripts and it lets an agent automatically open GitHub PRs fixing the script when it fails. A few months ago we released Libretto, a CLI + coding-agent skill for building deterministic browser automations. The idea was that for many browser workflows, especially repetitive business workflows, you don’t need an AI agent making decisions at runtime. You want deterministic Playwright scripts that are inspectable, faster to run, and much cheaper than…
In plain words
Libretto PR agents is a free TypeScript library that automatically fixes failing Playwright browser automation scripts. Users add one line of code to existing scripts, and the tool uses an agent to generate GitHub pull requests with corrections when scripts break due to website changes. It's designed for developers maintaining deterministic browser automations for repetitive business workflows who want inspectable, fast, and cost-effective alternatives to runtime AI agents.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Libretto PR agents is a free TypeScript library for maintaining Playwright browser automations. Add one line of code to your existing Playwright scripts and it lets an agent automatically open GitHub PRs fixing the script when it fails. A few months ago we released Libretto, a CLI + coding-agent skill for building deterministic browser automations. The idea was that for many browser workflows, especially repetitive business workflows, you don’t need an AI agent making decisions at runtime. You want deterministic Playwright scripts that are inspectable, faster to run, and much cheaper than repeatedly calling an AI browser agent. That helped us generate Playwright and network-request-based scripts, but websites can often change which breaks deterministic scripts. So maintaining a variety of scripts at scale is a headache. If you already have a bunch of functioning Playwright scripts, the last thing you want is to rewrite everything around a new runtime AI framework like browser-use or stagehand just to make maintenance easier. The Libretto PR Agent pulls your code from GitHub and connects via CDP to the browser session that just failed. It has an exec tool for injecting Playwright and javascript into the page, and once its inspected the failure, it opens a PR to your repo with a proposed code fix. You use it like this: try { await automationLogic(page); } catch (error) { await playwrightDebugger.debugFailure(error, page); throw error; } The agent is completely free and open source, lets you bring your own LLM provider API keys, and works with any browser provider (including self hosted). The source code is here: https://github.com/saffron-health/libretto/tree/main/package... We think this makes browser integrations much easier to maintain, especially for teams that already have Playwright browser automation scripts in production and don’t want a full migration to get AI-assisted debugging and repair. If you’re maintaining browser automations in production, would love to know what your debugging flow is currently and any feedback on this approach.
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 · 26d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
