THE GAIA ECOSYSTEM

One system.
Three names.

Gaia is an open capability control system for AI agents. It is built as three named parts, and this page has exactly one job: tell you what each name is and how they relate. Every part keeps its own documentation — this page links to it and never repeats it.

Gaia is Three Names: Gaia Research, Gaia Skill Tree, and Gaia Skill Heaven

What is Gaia?

Agents can now do far more than any one person can verify. Gaia’s answer is to stop treating that as a single problem and split it into four questions that are usually mashed together:

  1. What capabilities exist, and why should I trust them?
  2. What do they actually cost, and do they work?
  3. What should enter this session, right now?
  4. How far can that be pushed before it stops being safe?

Each question has a home. Keeping them apart is the whole design: one is the permanent public record (the Skill Tree), one is the open laboratory (Research), and one is the runtime umbrella that houses your session (Skill Heaven).

THE THREE NAMES

Who does what.

The registry records it, research proves it, the runtime houses it. Each room keeps its own colour.

ROOM 01 · THE RECORD / REGISTRYACT ACTIVE

Gaia Skill Tree

The permanent public record and registry of what agent capabilities exist (Yggdrasil), who demonstrated each one first, and what evidence stands behind it. A skill is not an entry in a list — it is a record with a trail: its origin contributor, its evidence, its stars, and a timeline of how it earned them.

You want this if you are looking for a capability, checking whether one is trustworthy, or putting your own work on the record.

Browse the Skill Tree
ROOM 02 · THE LABORATORYACT ACTIVE

Gaia Research

The open laboratory that measures what capabilities really cost and whether they help — what a skill costs while merely listed, what it costs when invoked, and how different harnesses behave — then publishes the method along with the findings that went the other way. The HH Index is currently in the works. You are reading it right now.

You want this if you want the numbers behind a claim, or the method to reproduce it yourself.

ROOM 03 · THE RUNTIME UMBRELLAWIP PROTOTYPE

Gaia Skill Heaven

The runtime umbrella that decides what enters an agent’s session and how much of it. Where the Tree answers what exists and why trust it, Skill Heaven answers what should be in this context, right now — housing Skill Zero (the subtractive launcher) and Skill Hell (the exploratory summon). Heaven is the converge summon direction; Ultra is the auto-switch:

  • Skill Zero: The subtractive launcher that starts your harness with zero ambient skill debt.
  • Skill Heaven: The converge summon direction for focused, curated session capabilities.
  • Skill Hell: The exploratory summon direction for wide capability search across the evidenced world.
  • Skill Ultra: The governor auto-switching entropy per gap at the crown of the line.

You want this if you want on-demand skill summoning, a clean slate, or session-only capabilities without permanent installation bloat.

HOW THEY RELATE

It is a loop, not a stack.

  1. Research measures cost, quality, failure, and harness behaviour.
  2. The Skill Tree records which capabilities are trusted, on what evidence, and by whom.
  3. Skill Heaven uses that record to decide what enters a session, and at what dose.
  4. The run itself produces new evidence — what it cost, what it fixed, what it broke — which goes back to Research.

Each rotation leaves the next one better informed. That is why the names stay separate: measuring, remembering, and admitting are different jobs. Fuse them and the thing making runtime decisions ends up grading its own homework.

START HERE

Which one do I want right now?

Reader intent mapped to a Gaia surface, its true state, and one concrete action
If you want to…Go toStateDo this
Find a capability, or check if one is trustworthySkill TreeACT ACTIVEBrowse the Skill Tree ↗
Put your own skill on the public recordSkill TreeACT ACTIVERead the contributor path ↗
See the numbers behind a claim, or reproduce oneResearchACT ACTIVEOpen the research ledger →
Launch with zero ambient skill debt (clean slate)Skill Zero (under Skill Heaven)WIP PROTOTYPEUse Skill Zero ↗
Summon skills on demand into session or explore/convergeGaia Skill HeavenWIP PROTOTYPEVisit Skill Heaven ↗
See the benchmark method behind the HH IndexResearchACT ACTIVERead the benchmark method →

WHAT CHANGED

If you learned Gaia earlier.

REVISION 1 · 2026-07-29

Some of what Gaia shipped this year replaces things people already learned. This is a standing surface, not an announcement: when something makes prior knowledge wrong, it gets a dated entry here.

The three names 2026-08-11

Gaia is told publicly as three names — Gaia Skill Tree (the record / registry), Gaia Research (the laboratory), and Gaia Skill Heaven (the runtime umbrella). Following the Skill Zero rename (RFC gaia-skill-tree#1509), the ecosystem shifted from four names to three: Skill Zero (the subtractive launcher) and Skill Hell (the exploratory summon) now live under the Skill Heaven runtime umbrella rather than standing as separate top-level ecosystem names. Within the umbrella, Heaven represents the converge summon direction and Ultra is the auto-switch.

The four names 2026-07-28

Gaia was previously told publicly as four names — the Skill Tree, Research, Skill Heaven, and Skill Hell. That framing was retired when runtime surfaces consolidated under the Skill Heaven umbrella.

Yggdrasil II 2026-07-07

The Skill Tree’s structure changed. If you learned it before this date, three things you know are now wrong: skill types collapsed from four to two, the progression branch is derived at read time and is never written down, and the rank words above three stars were renamed. Trust Magnitude became the single gate for ranking up.

Every claim has a trail.

This page owns the relationships and nothing else. Each part of Gaia keeps its own thesis, its own docs, and its own receipts — and this is the page that tells you which one you are standing in.