Chidori – Fast web-to-Markdown fetching for AI agents
HTML-to-Markdown for AI agents when JinaAI and Firecrawl already dominate.
Agentic AI-friendly CLI for X.com (Twitter) API - designed with machine-readable output, non-interactive operations, and idempotent commands
Rust X.com client with agentic CLI, but tweepy, nodejs twitter-api, and official clients dominate.
Rust developers building X.com integrations; AI agents needing structured API output.
tweepy · twitter-api-v2
Design principles: - Zero unnecessary abstraction - Strong typing over dynamic JSON - Clear separation between transport and domain logic - Composable request builders
Looking for feedback on: - Error handling patterns - Versioning strategy - Public API surface design
Happy to answer questions.
HTML-to-Markdown for AI agents when JinaAI and Firecrawl already dominate.
Agent-first CLI contract with proper stdout/stderr separation for workflow capture.
Blog post analysis showing LangGraph didn't change architecture from custom async Python implementation.
Open-source CFR poker agent when PioSolver and GTO+ cost hundreds.
This is someone treating a CV as structured data rather than a PDF: resume.json, evidence.json, availability.json, agent-card.json and a curated llms.txt are all exposed plus schema.org JSON-LD. Nice touches include GitHub Actions that validate links and push an IndexNow update on every commit — practical engineering to get content noticed by crawlers and agents. It’s a focused, well-implemented experiment, but its usefulness depends on broader adoption or tooling that consumes these bespoke conventions.
Searchable directory for llms.txt files when general search engines could index these.