Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Tasker

An open-source desktop agent for browser and OS automation

Details

External ID
46457912
Source
HN
Company
—
Product
Tasker
Website domain
automatewithtasker.com
Launched
Jan. 1, 2026
Cohort
—
Upvotes
33
Upvotes percentile
0.7292490118577075
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

Hi HNI recently got married, promptly had a bit of a meltdown, and decided to lock myself in a room and build for a while.At the same time, I was trying to outbound sell for my startup and kept running into the same problem: I wanted an automation tool that could actually use my computer like a person. Click through UIs, copy/paste between apps, handle messy workflows — not just APIs and webhooks.I couldn’t find anything that felt: - consumer-friendly (non-technical) - local-first - flexible enough for real-world, UI-driven tasksSo I challenged myself to see how far I could get building an open-source, desktop automation app powered by AI. That’s Tasker.I’ve been using it daily for ~2–3 weeks for sales workflows, and my father has been using it to help generate estimates for his HVAC business. It’s still early (still needs to expand to general OS), but it’s already replaced a lot of manual work for us in browser.One thing that’s become very clear: a cloud/deployable version that can run on cron or be triggered via HTTP would unlock a lot of use cases. I’m not totally sure where this goes next, but I wanted to share it early and get feedback.Would love thoughts on: - What workflows you’d actually trust something like this with - Desktop vs cloud tradeoffs - Where this breaks down in practice - Whether this feels useful or just scaryRepo and docs are linked on the site.

Enrichment

Theme
AI agent frameworks and developer tools
Vertical
Horizontal
Function
Agent / copilot
Audience
Developer
AI stance
AI feature
Project type
Hobby / open-source project
Normalized one-liner
browser and os automation agent
Manually corrected
False

Could you build this?

Partial A basic UI with browser automation (Playwright/Puppeteer) is vibe-codeable, but reliable cross-platform desktop OS automation using vision and computer-use agents is notoriously brittle and complex.

What it would actually take: Typically an Electron or Tauri desktop shell coordinating Playwright for browser tasks and OS-level accessibility APIs / screen capture / mouse-keyboard hooks (e.g., RobotJS or PyAutoGUI). The hard part is reliable multimodal computer-use agent execution: interpreting screen state across arbitrary monitor resolutions/OS window states and recovering from failures, requiring AI agent evaluation harnesses and native desktop system integrations.

Discussion

20 comments analyzed.

Competitors mentioned: Tasker (Android automation app)

Concerns raised: Doesn't record specific actions like website visits, text clicks, copying, Privacy concerns when running locally, Confusion with existing Tasker app on Android, Gap between planned workflows and actual execution behavior, Potential filesystem/OS API errors with irreversible effects

Feature requests: Run automation in separate session/screen so user can continue working, Self-hosted/own server deployment option, Configuration-based sandboxing and allowlisting without code changes, Improve task recording accuracy for specific web interactions

Competitors

Other products that read as similar to this one — 182 launches clear the similarity bar, closest 8 shown.

Attention rank: #63 of 183 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 51 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.