Web agents fail at hard real-world tasks

“Show HN: Agent-desktop – Native desktop automation CLI for AI agents 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 w”

“Show HN: Git for AI Agents hi guys. been working on something i think is fundamentally missing in today's workflow with ai agents. vcs. i find myself struggling with questions that agents can't answer like why did you do it? , when did u delete this folder? why? , etc. or trying to /rewind (after a /compact...) or basically `bisect` to find when and why something was done by the agent in the current / previous session. just like git did for code, i think we are the same ”

“Launch HN: TesterArmy (YC P26) – Agents that test web and mobile apps Hey HN - we’re Oskar, Szymon, and Piotr, and we’re building TesterArmy ( https://tester.army ). TesterArmy is an agentic testing platform that runs end-to-end checks before deployment and in production. Instead of wasting hours on manual testing or maintaining static scripts, we let you specify your tests in natural language and handle everything in between. We've built the platform fully around agents. Our agen”

“Show HN: Kontext CLI – Credential broker for AI coding agents in Go We built the Kontext CLI because AI coding agents need access to GitHub, Stripe, databases, and dozens of other services — and right now most teams handle this by copy-pasting long-lived API keys into .env files, or the actual chat interface, whilst hoping for the best. The problem isn't just secret sprawl. It's that there's no lineage of access. You don't know which developer launched which agent, what it ac”

“Show HN: Reverse-engineering web apps into agent tools Hey HN! We built a browser-based agent that runs inside an authenticated web app, watches how the app calls its own APIs, and automatically turns those into agent tools. You can think of it as an auto-generated MCP server that self-updates as the host app changes. The result is a skilled AI assistant that actually integrates deeply with any product (not just chat and RAG) with minimal effort. Check out these short demos below that show the a”

“Show HN: TinyFish Web Agent (82% on hard tasks vs. Operator's 43%) Enterprises need ~90% accuracy to deploy web agents. Until now, no agent has come close on real-world tasks. TinyFish is the first production-ready web agent. Here's the evidence. Results of hard task scores on Online-Mind2Web (300 tasks, 136 live websites, human-correlated judge): - TinyFish: 81.9% - OpenAI Operator: 43.2% - Claude Computer Use: 32.4% - Browser Use: 8.1% Why not WebVoyager like everyone else? Because it&#x2”

“Show HN: Broccoli, one shot coding agent on the cloud Hi HN — we built Broccoli, an open-source harness for taking coding tasks from Linear, running them in isolated cloud sandboxes, and opening PRs for a human to review. We’re a small team, and our main company supplies voice data. But we kept running into the same problem with coding agents. We’d have a feature request, a refactor, a bug, and some internal tooling work all happening at once, and managing that through local agent sessions meant”

“Show HN: rmBug – audited database access for humans and agents We've been building things together for a long time. LEGO first, then software. Across every company and project since, one thing kept showing up: database access security was broken. Not always dramatically. Sometimes it was the budget. Sometimes months of convincing. Sometimes just a quiet burden nobody talked about. Support staff with access to every customer's financial data. Engineers who left but somehow still had cre”

“Show HN: The agent that builds and operates its own SaaS tools For context, we started working on our general AI agent CraftBot before OpenClaw came out. It works similarly to OpenClaw and Hermes agent: control your PC to do task + memory + proactivity. However, here is the catch: it can create and operate its own SaaS tools with the concept of Living UI Living UI is a system where an AI agent can scaffold and launch real, working web apps on demand. Each living UI can be a dashboard/softwa”

“Ask HN: What coding agents are you using? My main coding agents are CodeX-CLI and OpenCode (Harness seems to have some problems). I also use CodeWhale, Antigravity-CLI and OpenClaude as supplements (because of network issues, I don't really dare to use Claude Code). In some special cases, bashagt. What coding agents are everyone using, or do you have any recommendations? New tools are coming out like waves now.”