Web agents fail at hard real-world tasks

“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: 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: 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: Mkdnsite – Markdown-native web server for humans (HTML) and agents (md) # What? Introducing mkdnsite ( markdown site ) - an open source Markdown-native web server that serves HTML to humans and raw Markdown to agents. No build step required. Runs on Bun/Node/Deno, as an OS-specific standalone executable, or as a Docker container. Possibly the easiest way to go from Markdown files to functional website in the new agentic era. Features: - Runtime-only, zero build - Content negot”

“Show HN: AI agents are bad at API integrations – we fixed it Hi, we're Sohaib and Hannan from APIMatic. We've been building tools to help Developers integrate with APIs for 5+ years at APIMatic. We're now trying to help AI agents do the same. This started from a conversation at PayPal DevDay 2025. The PayPal developer experience team were monitoring developers using AI agents to integrate PayPal APIs, and the agents kept reaching for outdated docs and deprecated SDK versions, ofte”

“Show HN: Recursive-Mode for Coding Agents recursive-mode is an installable skill package for coding agents. It gives your agent a file-backed workflow for requirements, planning, implementation, testing, review, closeout, and memory, instead of leaving the whole process scattered in context. Long-running agent work has a common failure mode: requirements, decisions, and plans live in the conversation. Once the session ends or the context window overflows, the agent loses track of what was decide”

“Show HN: OQP – A verification protocol for AI agents As AI agents autonomously write and deploy code, there's no standard for verifying that what they shipped actually satisfies business requirements. OQP is an attempt to define that standard. It's MCP-compatible and defines four core endpoints: - GET /capabilities — what can this agent verify? - GET /context/workflows — what are the business rules for this workflow? - POST /verification/execute — run a verific”

“Ask HN: What is the "Control Plane" for local AI agents? a href= https://ibb.co/v6QLjdBY img src= https://i.ibb.co/S4dV3mxr/Agents-Orchestration.png alt= Agents-Orchestration border= 0 /a I’ve been running an increasing number of local coding agents (Claude Code, Codex CLI, OpenCode, etc.) and I’ve hit a wall: orchestration and state visibility. When you have multiple agents working on different sub-tasks in a single repo, terminal logs become unmanageable”