70 stories
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content What I Built Meet ErrataGuard, an AI-powered board game companion and rules agent designed to solve a problem every complex tabletop gamer faces: conflicting rulebooks, errata sheets, and developer…
Watch an engineer use a coding agent against an unfamiliar API and you see the same ritual every session. They paste the docs URL, then the auth section, then an example response, then a correction: "pagination is cursor, not page", "money is integer cents", "the list wrapper is data.items".
1. Deadbugz -- the server that waits for call #3 (August 2026) Pillar Security documented an active campaign pushing a malicious MCP server (it calls itself "productivity-suite") through 23 GitHub pull requests opened within 74 minutes (Aug 10).
Building the Payment Layer for AI: x402 Protocol Infrastructure for Autonomous Agents AI agents will need to pay for compute, data, and API calls — and the infrastructure to let them do that autonomously exists today.
Every team evaluating Model Context Protocol (MCP) servers reaches the same question: do we hand-maintain a second description of our API for agents, or do we generate it from the contract we already have? If you keep an OpenAPI document, the second answer is the sane one.
La consolidación de motores de respuesta como ChatGPT Search, Google Gemini (AI Overviews), Perplexity Pro y Claude ha transformado de forma irreversible el proceso de búsqueda y compra B2B en España.
Parece cena de ficção científica: uma cancela de pedágio aos pés da pirâmide da Tyrell Corp cobrando uma taxa por cada bit do seu código. Daria pra chamar de "imposto de token" essa tentativa de criar um lock-in onde três ou quatro fornecedores de IA precificam cada linha de código que o seu time…
I've been working on coding projects in my terminal and my IDE for years, (shoutout to CodeBlocks for my C++ fans!) but as agents continue to make the case for streamlined task management in our development cycles, one thing that I found frustrating was the moment I had to step away, close the…
Most MCP servers get tested the same way: connect one client, call a few tools by hand, ship it. Then real agents show up. Dozens of sessions at once, three tool calls in parallel, sessions that never get closed. The failures that follow don't look like crashes.
Quick version: LMCP is a Mac app that turns the apps you already use into tools your AI can call. Install it once and Claude Desktop, Claude Code, Cursor, Codex and other MCP clients can work with Mail, Calendar, Teams, Slack, WhatsApp, iMessage, Outlook, OneDrive, Google Drive, Zoom, Office files,…
Android UI Renderer MCP is a local MCP server that lets a coding agent render Android UI without an emulator or a device: it gets back a PNG plus a component tree it can query for bounds, text, and state.
As web scraping becomes more complex, the tools we use to navigate that complexity need to become smarter. I recently took some time to explore how Claude skills can be integrated into a web scraping workflow.
This is a submission for Path One: Agents in the Sanity Challenge. AI disclosure: this project and post were produced by an autonomous AI coding agent under the CedarProof work identity. No human authorship or independent human review is claimed.
Agent Plugins 1.0 is a real, published, vendor-neutral standard for bundling Agent Skills and MCP server configuration in one directory. But commands, hooks, permissions, credentials, distribution, and governance are not suddenly universal.
Control leaves the process NVIDIA presented the Open Agent Safety Platform on September 28, and the design decision is the news. The runtime is called OpenShell, it is open source, and it already supports Codex, Claude Code, Pi and Hermes.
Your agent triaged the alerts, wrote the patch, opened the pull request, updated the docs, and merged. The bug is in production. The migration ran against the wrong table. The customer got the email with the wrong number. All of it is irreversible. And a human owns every bit of it.
Pi 1.0 sat at #1 on Hacker News today with 1,200+ points. Pi Durable, its sibling release, is also in the top 10. The part that got people typing: the agent that spent over a year dunking on MCP now supports MCP. Here's what actually shipped, and why I think the design matters more than the drama.
Agent Boundary | Defining the Reach of Enterprise AI Authority | R.A.H.S.I. Framework™ An agent cannot edit a customer record directly. It can, however, invoke a workflow that can. The workflow’s permission does not become the agent’s permission—but the agent may still cause the edit.
Showing 54 of 70 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news from Dev.to AI
Join 15,000+ AI enthusiasts
