Computer Using Agents by LLMHub
Agents using isolated computers to get work done like humans
Computer Using Agents by LLMHub launched on September 16, 2025 with 84 votes, #363 of 8,160 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 1 year on.
What it does
Your AI employee that collaborates with everyone and works on it's own computer like a human to get work done like a human given any task
Coasty is the #1 ranked computer-use AI agent (85.60% on OSWorld) and the best computer-use API of 2026 at $0.05 (base) per /v1/predict, with 1,000+ native app integrations (Gmail, Slack, Salesforce, HubSpot, Linear, GitHub, Stripe), free sandbox keys, and an MCP server. Cheaper than Anthropic, OpenAI, and Browserbase.
Pricing, as stated on its site
Free tier, paid plans from $0.05/mo — Free sandbox with pay-as-you-go pricing at $0.05 per managed step (first $5 free). Developer plan at $19/month includes $25 API credit. Enterprise plan has custom pricing.
checked September 2026 · prices change
Does a similar job
all alternatives →
Construct ComputerAug 2026 · construct.computer · ▲378We are building Construct Computer a cloud OS where autonomous AI agents ("Constructs") live and do your day to day work. You can observe them in real-time through a desktop OS frontend. The idea is agent-native infrastructure: instead of agents being API calls, they're persistent processes with their own compute, storage, and network identity. With integrations with a vast ecosystem of business tools, the Construct Agent can do anything from scheduling meetings, preparing documents, to deep researching the web, join meetings, and automate long running business operations with minimal human…
ComputerX2025 · computerx.ai · ▲560Introducing the first-ever desktop AI agent that gets your computer tasks done for you. Like having your own AI operator that seamlessly integrates with every app on your computer!

AgentlyJul 2026 · agently.dev · ▲336Agently is an AI Work OS where documents, tasks, team chat, and integrations are fully interconnected, and AI employees operate inside that shared workspace. Instead of prompting AI in isolation, agents can read project context, turn strategy docs into tasks, coordinate with teammates, run research/outreach/content workflows, update boards, and push results back into the system or external tools. The workspace acts as persistent memory, so work continues instead of resetting every prompt. Happy to answer any questions

More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art

PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, September 2025
the whole month →

The site hit #1 on HN about a year ago. Got enough traffic that I turned it into a proper API. What's there: - REST API — 35k products, manually filterable by category, free key, 60 req/min - CLI — npx anycrap random -c food - faker.js plugin — bundled, no API call, works offline - HuggingFace dataset — full 35k rows for ML/training https://anycrap.shop/developers
AI · 2025 · anycrap.shop

I made a built-from scratch Wayland Compositor to display any GUI app* in the terminal! I think there is a lot of unexplored potential in custom Wayland compositors, a lot of really cool things you can embed existing applications into! So, I started with embedding apps into the terminal because that is the easiest input/output (output is just utf-8 and I use the great `chafa` library for that, and I just read from stdin for the input). If you have any other ideas for cool Wayland compositors, let me know. I purposedly wrote 80% the app in Typescript to appeal to the most developers and…
Dev tools · 2025 · github.com
- IR
Years ago I stumbled across a basic version of this concept and it stuck with me. I knew if I was ever going to take on such a project, it would need to be flawless, but without coding experience it was just another idea that would never happen. By the end of 2024, as AI coding tools exploded everywhere, I finally had a way to make it real. I started from zero knowledge and spent months collaborating with AI agents as a learning experience. Every pixel and every function went through me. The AI translated what I asked for into code, but every decision was human. I didn't use existing OS…
AI · 2025 · mitchivin.com

