I built a new software primitive. It replaces AI screenshot agents
I built a Rust binary (~700KB, two dependencies) that snaps onto any Windows application, continuously reads its UI Automation accessibility tree into a SQLite database, and lets external processes control the app via SQL INSERT. The core insight: every GUI application already describes itself as structured text through the accessibility layer (built for screen readers since 1997). Every major AI lab is taking screenshots of this and running vision models on it. DirectShell just reads the text directly. What it does: - Reads every button, field, menu item into a queryable SQLite DB…
I built a new software primitive. It replaces AI screenshot agents launched on February 17, 2026 with 5 votes, #1,882 of 16,627 launches that month and more than 75% of that year's launches.
What it does
Every AI lab on Earth teaches agents to use computers by screenshotting and guessing. We taught AI to read instead. DirectShell reads the Windows Accessibility Tree — every button, field, and menu in any application — as structured text. No vision model. No pixel guessing. 120x cheaper. 10x faster. Works with any LLM, any app, offline. 700KB. Open source. The door was open for 29 years. We walked through it.
Because i could not Ressist. Contribute to IamLumae/DirectShell development by creating an account on GitHub.
In the maker’s words, at launch
I built a Rust binary (~700KB, two dependencies) that snaps onto any Windows application, continuously reads its UI Automation accessibility tree into a SQLite database, and lets external processes control the app via SQL INSERT. The core insight: every GUI application already describes itself as structured text…
Does a similar job
all alternatives →
Agent-desktop – Native desktop automation CLI for AI agentsMay 2026 · github.com · ▲99I'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…
Libretto – Making AI browser automations deterministicApr 2026 · github.com · ▲134Libretto (https://libretto.sh) is a Skill+CLI that makes it easy for your coding agent to generate deterministic browser automations and debug existing ones. Key shift is going from “give an agent a prompt at runtime and hope it figures things out” to: “Use coding agents to generate real scripts you can inspect, run, and debug”. Here’s a demo: https://www.youtube.com/watch?v=0cDpIntmHAM. Docs start at https://libretto.sh/docs/get-started/introduction. We spent a year building and maintaining browser automations for EHR and payer portal…
We made our own inference engine for Apple Silicon2025 · github.com · ▲186We wrote our inference engine on Rust, it is faster than llama cpp in all of the use cases. Your feedback is very welcomed. Written from scratch with idea that you can add support of any kernel and platform.
RawInputViewer – Examine how games receive inputs from Windows2022 · github.com · ▲49This is my third ever GUI programming project -- I've only ever done any sort of programming in AutoIt as I'm entirely self-taught via their docs/tutorials. I've only just started learning about control flow and structuring of GUI apps really recently, so you might find that the data access patterns in my source code to be a mess as I wrote them before learning about those concepts.
- IBI built an OS that is pure AIMar 2026 · pneuma.computer · ▲34
I've been building Pneuma, a desktop computing environment where software doesn't need to exist before you need it. There are no pre-installed applications. You boot to a blank screen with a prompt. You describe what you want: a CPU monitor, a game, a notes app, a data visualizer and a working program materializes in seconds. Once generated, agents persist. You can reuse them, they can communicate with each other through IPC, and you can share them through a community agent store. The idea isn't that everything is disposable. It's that creation is instant and the barrier to having exactly…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, February 2026
the whole month →
Lovon AI Therapy▲801Feel closer and have more fun with your partner every day!
AI · Feb 2026 · lovon.app
Hello my name is Ben Ward for the past 3 years I have been remastering the financial game Wall Street Raider created by Michael Jenkins originally on DOS in 1986. It has been a rough journey but I finally see the light at the end of the tunnel. I just recently redid the website and thought maybe the full story of how this project came to be would interest you all. Thank you for reading.
Work · Feb 2026 · wallstreetraider.com