What is aDNA?

aDNA (Agentic DNA) is an open standard for organizing project knowledge so both humans and AI agents can navigate it. The point is simple: make a project easy to build on, operate, and understand — without re-explaining it at the start of every session. Think of it as a genome for your project: a structured encoding of what it knows, who's involved, and how work gets done.

The problem

AI agents struggle with the same thing people do: finding the right context in a sea of files. Without structure, an agent burns tokens on the wrong content — or misses what matters. You re-explain the project every session. Agents contradict decisions they made last week. Weeks of work vanish when the context window closes.

It is a knowledge-architecture problem, not an agent-capability one — the agent is capable; it has nowhere to look. Until aDNA there was no shared answer: every team improvised with long READMEs and custom prompts, and none of it survived across sessions, agents, or teams. aDNA is one open answer any team can adopt, any tool can support, and any agent can read without custom setup.

How aDNA works

aDNA gives a project three things:

• The Triad — every project splits into three directories: who/ (people and governance), what/ (knowledge and decisions), and how/ (operations and work). See one aDNA project and you know where to look in any other.
• Governance files — CLAUDE.md, AGENTS.md, MANIFEST.md, STATE.md, and README.md orient an agent at every level. The root CLAUDE.md is the entry point: purpose, structure, rules, where to start.
• Typed entities — 16 base entity types (missions, sessions, lattices, inventory, and more), each with consistent frontmatter and naming. Know what one mission file looks like and you can read any mission file in any aDNA project.

What a project looks like

A minimal aDNA project — three directories, five governance files:

your-project.aDNA/
├── CLAUDE.md          # Agent entry point: purpose, rules, where to start
├── STATE.md           # Live snapshot: blockers, active work, next steps
├── MANIFEST.md        # Project overview and architecture
├── who/               # WHO — people, governance, coordination
│   └── governance/    # Roles, policies, vision
├── what/              # WHAT — knowledge, decisions, context
│   └── context/       # Curated knowledge files agents load
└── how/               # HOW — operations, plans, execution
    ├── missions/      # Work decomposed into claimable objectives
    └── sessions/      # Per-session tracking and handoff notes

An agent that has seen one aDNA project recognizes this in any other — before reading a single word of content.

The 16 entity types

Every file declares its type. That predictability is what lets an agent navigate an unfamiliar project without custom configuration. The 16 base types span the Triad — 4 WHO, 5 WHAT, 7 HOW. The full set:

What a CLAUDE.md looks like

A CLAUDE.md is not a README — it is the agent's operating protocol. The agent reads it first, every session; it replaces "figure it out from the README" with a contract between project and agent.

# CLAUDE.md — aDNA.aDNA

You are Rosetta — named after the Rosetta Stone, the artifact that decoded
Egyptian hieroglyphics by presenting the same text in three scripts. This
vault does the same: it presents the aDNA standard in three registers —
technical specification, operational practice, and plain-language explanation.

## Project Map

aDNA.aDNA/
├── CLAUDE.md     ← You are here — agent master context (this file)
├── STATE.md      ← Operational snapshot: current phase, blockers, next steps
├── what/         ← Knowledge objects, context library, lattice definitions
├── how/          ← Operations, sessions, missions, campaigns, skills
└── who/          ← Governance, community, coordination

## Standing Orders

1. Phase gates are human gates — never auto-advance between phases.
2. Every mission gets an AAR before marking it completed.
3. Upstream spec is source of truth — cite adna_standard.md for normative claims.

Before and after

Without aDNA: a lab's 200 files sprawl across Notion, Drive, and Git. Every session starts by pasting an outdated summary; last month's decisions get re-litigated; a new collaborator needs three days to orient.

With aDNA: the same project has a what/context/ library, a STATE.md of priorities and blockers, and a how/missions/ directory of work broken into claimable objectives. An agent loads CLAUDE.md, reads the relevant context, and starts in the right direction — same session.

See for yourself

aDNA is not a concept deck — it is a standard you can clone and read today. The public image at github.com/aDNA-Network/aDNA is a real aDNA workspace: one command gives you the standard, the skills, and the templates, and a fresh clone even offers to bootstrap a complete, polished Home for an agent. Inspect the actual files:

• CLAUDE.md — the workspace operating protocol an agent loads first
• .adna/ — the full aDNA standard, embedded and ready to clone
• .adna/how/skills/skill_onboarding.md — the first-run recipe that orients a new project
• .adna/how/skills/skill_project_fork.md — how a new .aDNA project is created
• .adna/how/templates/template_workspace_claude.md — the router template every workspace starts from
• .adna/how/templates/template_home_claude.md — the governance template a fresh clone uses to bootstrap a polished Home (shipped at v8.0)
• .adna/how/templates/template_node_adna_exemplar/ — the themed exemplar Home the bootstrap offers out of the box (shipped at v8.0)

This documentation site is itself an aDNA vault — the structure you are reading about is the structure that produced it. Clone the image and open it in Obsidian, VS Code, or on GitHub: every directory and frontmatter field is an aDNA concept in action.

The three-question test

A well-structured aDNA project lets any agent answer three questions immediately, without asking:

1. What is this project? — CLAUDE.md and MANIFEST.md at the root.
2. What is the current state? — STATE.md: blockers, active work, next steps.
3. Where do I start? — the active mission in how/missions/, or the nearest AGENTS.md.

If your project answers all three in under ten seconds of reading, it is aDNA-ready.

Explore further

• The Triad — the foundational structure: who, what, how
• Governance Files — CLAUDE.md, AGENTS.md, STATE.md, and their roles
• Get Started — set up your first aDNA project in three steps
• Tutorial: Create Your First CLAUDE.md — hands-on, 20 minutes
• The Convergence Model — how aDNA narrows context at each level of the execution hierarchy