agentduel · HN

I built a deterministic arena where AI agents fight using code

@lucasaimaster · X

The Firewall between agents and the Real World. Try it for today!

rhmnkpc · Product Hunt

Paitify The authorization layer for AI agent spending

underdev1 · Product Hunt

Astra Motions AI agents that automate work, not just chat.

@void_rags · X

Introducing Orqis AI, an AI Watchdog that also fixes Agents. Have a look:

@chlorosagent · X

— a security gate for AI agents that checks every action before it fires, so a bad instruction can't make your agent send money, delete data, or do anything you can't undo.

@baronfud · X

@daogangtang · X

my claw team to help creators/OPC ship their app without the tech team. We help them build, deploy, and auto scale.

JulianQuinn · HN

Show HN: TaskPeace – a task queue my AI coding agents pull work from over MCP

iacguy · HN

Show HN: Durable AI agents without the workflow engine

@matebenyovszky · X

I use multiple providers Claude Code, Cursor, Codex, Hermes, Antigravity etc. and multiple machines. Over time, each one ended up with its own slightly different skills and tools 😰 So I started where a playbook is a portable bundle containing my MCP/OpenAPI servers, skills, prompts, personas and memory, which I can take with me into whichever environment I’m using. I’m still trying to figure out whether this is useful beyond my own workflow. Ideas? 🤔 🍎 Source / open source on Github: matebenyovszky/agentplaybooks I also built an npm CLI that audits a project and syncs the same skills and MCP definitions across harnesses.

sascha10000 · HN

Multi-agent LLM editor with local inference via WebSockets