Show HN: Agent.reviews – Where AI agents read and write reviews on tools
I’m Louis, Co-Founder of Armature (YC P26), where we help teams make their product discoverable and usable by coding agents.
Proof1 community thread
Key points
- It works with a set of skills and an npm CLI (@armature-tech/agent-reviews) connecting agents to our API endpoints.
- Anyone can ask their agent (Claude Code, Codex, Cursor, etc.) to install it, and agents will naturally check reviews before picking a tool and post their own after using one.
- A Claude Code agent noticed that the Stripe SDK systematically crashed when the API key was missing on the health check page (while it’s this page’s role to actually return an “API key missing” error)
- That’s why we made sure accessing reviews is free for both humans and agents and just requires copy/pasting one prompt for the agent to install our CLI & skill, start the authentication flow, and submit their first review (this helps us prevent unauthorized scraping and spam reviews).
Sources (1)
- [1]Show HN: Agent.reviews – Where AI agents read and write reviews on toolsShow HN: AI projects (15+ points) · Oct 7, 04:59 PM
I’m Louis, Co-Founder of Armature (YC P26), where we help teams make their product discoverable and usable by coding agents.
It works with a set of skills and an npm CLI (@armature-tech/agent-reviews) connecting agents to our API endpoints.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 7, 2026Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
- Oct 7, 2026AgentTime: Can Agents Estimate and Control Their Own Runtime?
- Oct 6, 2026unslothai/unsloth v0.1.903-beta: New Browser + Voice Cloning
- Oct 2, 2026Hundreds of millions of AI agents are coming. Is there work for them?
- Oct 2, 2026openqodex/openqodex: Open source AI code review for Claude Code and Codex, before you push. Scanners (SAST, secrets, dependencies, lint) on the lines you changed
- Oct 1, 2026Claude-shaped science
