10 repositories · 1 under 3,000 stars
Coding assistants, agents, command-line helpers and plugins for the day's programming work.
A plugin that makes a coding assistant look for the existing answer before writing a new one.
Reads a project and draws a clickable map of how its parts connect.
One local address in front of the free tiers of many AI providers.
LiteLLM meters what the AI costs. This one tells you whether it was any good.
Audits whether ChatGPT, Perplexity and Google AI Overviews can find and cite your site — CLI, Python library, MCP server and Astro integration.
GitHub's spec-driven development toolkit — intent, then specification, then plan, then the agent implements.
Command-line pipe to any model, with every prompt and response logged to a queryable SQLite file.
Pydantic-validated structured output from any LLM, with automatic retry on malformed responses — so the subtopic map cannot fail to parse.
One interface over 100+ model providers, with per-key budgets, spend tracking, caching and fallbacks — the meter on the AI bill.
A marketplace of ready-made Claude Code plugins, subagents and skills — a free capability upgrade to how he builds everything else.
No repository in this area carries every tag you picked.
A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.
No tracking pixels. One click to leave. The archive stays free either way.
We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.