Alternatives
Products that do what Open-source SDK to generate UI-based CUA tools or RPA scripts on macOS does
My friend and I were building UI-based automation tools for small businesses and kept running into a few recurring problems: - Computer-use agents (CUAs) are powerful, but often unreliable and slow when controlling UIs directly. - Workflows vary — some can be handled deterministically by RPAs, while others need a bit more intelligence from CUAs (while they may share a lot of the same 'actions'). We wanted an easier way to record UI-based automation scripts that could: - Be run by humans, like a lightweight RPA, or - Be invoked by CUAs as tool calls — improving their reliability and speed. So…
- 1DA
Hi HN, Francesco from Cua here. I hacked this project together last weekend, inspired by the Codex Computer-Use release and lessons learned from deploying GUI-operating agents for our customers. The main problem: when a UI automation process controls a desktop app today, it usually takes over the human’s session. Your cursor moves, keyboard focus gets stolen, windows jump to the front, and you have to stop working until the agent is done. That is why we have historically avoided encouraging users to run these processes directly on their host machine, instead relying on VMs or GUI containers…
Apr 2026 · github.com
- 2AD
I've been building computer-use tools for a while, and I quietly launched this about a month ago (122 Stars on GH). I figured it was worth sharing here. Over the last few months, a lot of computer-use agents have come out: Codex, Claude Code, CUA, and others. Most of them seem to work roughly like this: 1. Take a screenshot 2. Have the model predict pixel coordinates 3. Click x,y 4. Take another screenshot 5. Repeat That works, but it's slow, expensive in tokens, and fragile. If the UI shifts a few pixels, things break. And the model still doesn't know what any element actually is. But the…
May 2026 · github.com
- 3
The power of Codex with local, self-hosted models and voice
Jul 2026 · opencodesuper.app
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13AA
Hey HN! We've just open-sourced Agent, our framework for running computer-use workflows across multiple apps in isolated macOS/Linux sandboxes. After launching Computer a few weeks ago, we realized many of you wanted to run complex workflows that span multiple applications. Agent builds on Computer to make this possible. It works with local Ollama models (if you're privacy-minded) or cloud providers like OpenAI, Anthropic, and others. Why we built this: We kept hitting the same problems when building multi-app AI agents - they'd break in unpredictable ways, work inconsistently across…
2025 · github.com
- 14
That's a bold claim. But I genuinely feel like I might have actually solved computer use (demo: https://x.com/mdlahfir/status/2088109763783700827?s=20) For context, I've been building agent-desktop (Inspired by agent-browser by Vercel Labs), an automation CLI for desktop apps. It's like Playwright but for desktops, not just native, but for Chromium apps as well. Trust me, yes, Chromium apps whose accessibility tree is dense. MacOS is GA; I'm almost close to launching for Windows and Linux! So, how did I solve it? Basically interoperability. The biggest issue with…
22d ago · github.com
- 15IB
Hi, I have been building small AI Agents for quite some time now using various frameworks and one thing that always bugged me was that iterating on small things like prompts, flows, tools etc always took a code change + deployment of the app. While the prompt part can be solved with Langfuse I haven't found a good way to keep the flow management remote (and open source). Lately I have been working with Genkit (https://github.com/firebase/genkit) and love how modular it is. So I thought why not build a UI builder on top of that that can handle simple flows, prompts and…
Sep 2025
- 16IB
My best friend and I developed a SaaS last month while working full-time: Chyrid (chyrid.com). It’s a tool for creating digital manuals without design or coding skills. Users build structured, polished documents with a drag-and-drop editor, and Chyrid handles the formatting—without using AI. We built it because most documentation tools are either too complex or too unstructured. A company is already using it for onboarding and process docs, but we’re still figuring out how to position it and who finds it most useful. Would love any thoughts on potential use cases or feedback on the concept.…
2025 · chyrid.com
- 17
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent. - CopilotKit/OpenBot
18d ago · github.com
- 18
- 19MA
Hi HN, I'm Cristina from CommandBar (YC S20). You've heard how lack of focus kills startups. We were afraid of this too. So for the past 3 years, we built “user assistance” tools for desktop and web apps only. (Stuff like an embedded Copilot trained on your product, cmd+k search, nudges, etc.) It took a lot of self-convincing but we’ve decided to finally launch all of this for mobile today too. In hindsight, we actually regret not doing it sooner. The more we dug into customer feedback, the more we realized how much more pronounced the problems we're solving on desktop are on mweb and native…
2023 · commandbar.com
- 20
- 21BA
This is a little side project I've been working on for the last few months. It's a service hosting Lua scripts behind static HTTP endpoints in a fully sandboxed environment. It's something I've built to scratch my own itch and now I'm launching a free public beta to see if it's something that anyone else also finds useful. My first professional job was for a company building an industrial IoT platform who's most unique feature was their Lua-based scripting platform. I ended up loving Lua so much that at my next job, at SmartThings, I ended up being the main instigator who made the Lua-based…
Nov 2025 · bodge.app
- 22AO
Hey HN, I built an AI-powered UI for macOS that automates tasks on both macOS and in browsers. I didn’t want to pay $200 for OpenAI’s operator, so I made my own using browser-use and macOS-use. It handles simple tasks like scraping data, filling out forms, and using macOS apps. It's not great at working with files yet, but I’m planning to improve that with custom tools for the LLM. The goal is to create a desktop “pet” that takes care of boring stuff—like drafting documents and filling out forms. Check it out and let me know what you think!
2025 · github.com
- 23
- 24AU
Hey HN! I built an open-source Python library that lets AI agents control mobile apps. Its heavily inspired by browser-use Here's a quick demo https://x.com/itsericktorres/status/1932996729458110482 From our experience testing mobile workflows or automate repetitive app tasks has always been a pain. You either write brittle UI automation scripts or do everything manually. And after testing out browser-use and seeing all the cool things people were building for web without the pains of normal automation I decided I wanted to build something like it but for mobile So I…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →