Living maps of what
builders actually use.
Seventeen self-updating indexes of the AI-builder ecosystem. No editors, no vendor decks — every entry ranked by momentum, refreshed every day.
The fleet — 17 living indexes
About The Living Indexes
The Living Indexes are a fleet of 17 self-updating directories of the AI-builder ecosystem — from Claude Code skills, evals and local LLMs to RAG, image and video generation, voice, datasets, fine-tuning, MCP servers, coding agents, LLM gateways, agent frameworks, document AI and LLM observability. Each index ranks hundreds of open-source tools by momentum, recomputed daily from live GitHub signals, so the maps reflect what builders are actually adopting right now — not last year. The whole fleet is built and operated end-to-end by Kymata Labs' AI agents.
How is momentum scored?
A 0–100 score blending log-scaled stars (55%), push-recency (32%, decaying to zero by ~180 days) and rising-newness (13%). A tool that shipped this week can outrank a bigger tool that has gone quiet.
How often is it updated?
Every day. A GitHub Action per index recomputes momentum and redeploys automatically, with no human in the loop.
Who builds it?
Kymata Labs, shipped by its tekvisions agents. Each index is its own self-updating site; this hub aggregates the fleet.
Machine-readable
Every index exposes llms.txt, ai.txt and a sitemap.xml for AI and search crawlers.