Show - HN Paper

Show HN: All the LM solutions on SWE-bench are bloated compared to humans

Show HN: Skill Eval – A framework for testing the quality of AI agent skills

Show HN: Engram update – 92% DMR, hosted API, lessons shipping agent memory

Show HN: SLOK – SLO composition with traffic-weighted service chains in K8s

Show HN: I packaged decade of video infra battle scars into tools for AI agents

Show HN: Let your website visitors ask ChatGPT/Claude/Gemini about your product

Show HN: Recite – I built an Skill and MCP so my AI agent does my bookkeeping

Show HN: Ekumene – In a distracted era, I built a system to see your time whole

Show HN: EZorro – Describe your trading strategy, and turn it into an algo

Show HN: Teaching Tokens: Implementing Private, Lightweight AI in the Classroom

Show HN: BrowseBrawl – What if browser agents battled to generate training data?

Show HN: We built a News Synthesis Engine to fight media bias

Show HN: Kodama – A self-hosted autonomous daemon for Claude Code and Codex

Show HN: React multi-step form library with dynamically generated steps

Show HN: Claude Code Spinner Verbs Extractor

Show HN: What I learned running a crypto data pipeline at 120M messages/day

Show HN: EZorro – Describe your trading strategy, and turn it into an algo

Show HN: O4DB – Intent-based M2M protocol without centralized APIs

Show HN: AI Code Review CLI

Show HN: I reverse-engineered car lease math against three real dealer documents

238 239 240 241 242 243 244 245 246 247