The aDNA Network
Language and DNA were co-created by everyone before us. The context that powers AI should be too — built, shared, and governed in the open, for the good of all. The open standard and network where that happens, on the Lattice Protocol.
What a context democracy is
A self-governed network where people and their agents build, share, and govern context graphs in the open — each project its own graph, all of them federating into a shared commons.
Real aDNA vaults — forges, frameworks, platforms, and public-good archives — federating on the Lattice Protocol.
The living registry
Every vault is a real, governed context graph — its own persona, its own history, its own place in the network. Here's a slice across 40 of them.
aDNA
tended by Rosetta
Self-referential aDNA documentation — teaches the standard by using the standard (Operation Rosetta)
III
tended by Argus
Inspect/Introspect/Improve quality framework…
CanvasForge
tended by Hermes
Canvas-substrate forge: deck + comic applications…
TaskForge
tended by Berthier
Canonical task ontology + claim-lease federation surface…
LA Venture Graph
tended by Cartographer
LA venture ecosystem knowledge graph (UCLA Anderson + Nerdstage/Demo Day LA)…
Home
tended by Hestia
This vault — per-node operational governance for Mac/stanley; the operator's daily-driver…
wga
World Genome Academy — buildpack + symphony + site
RareArchive
tended by Mnemosyne
Rare Archive OSS rare-disease AI project…
How it Works
Three steps from scattered files to a project your agents can navigate — and keep navigating.
Structure
Every agent session starts from scratch — agents relearn your project by rummaging through files. aDNA ends that. Three directories (what you know, how you work, who's involved) give any agent instant orientation.
my-project/
├── CLAUDE.md ← agent master context
├── what/ ← what the project knows
│ └── context/ typed context files
├── how/ ← how it operates
│ └── missions/ decomposed work plans
└── who/ ← who's involved
└── governance/ roles & rules
Orient
Without a map, agents blast through irrelevant files or ask you to re-explain the project. Agents read your CLAUDE.md and AGENTS.md first, then pull typed context at exactly the depth they need — not your entire repo, not a blank slate.
# CLAUDE.md — climate-pipeline You are working on climate-pipeline. A data pipeline for surface temperature records (1990–present). ## Priority Rules 1. Never overwrite raw sensor data 2. All outputs need uncertainty ranges 3. Ingestion changes need peer review
Execute
Context windows close and wipe progress — the next agent starts over. aDNA decomposes work into sessions, missions, and campaigns — context-sized chunks that fit a single agent window. What one agent learns, the next inherits.
plan_id: mission_schema_v2 status: active ## Objective 1 — Migrate schema - Status: ✓ complete - Files: data/schema.py ## Objective 2 — Backfill validation - Status: in_progress - Depends on: [1]
The Standard
aDNA is an open specification — MIT licensed, community-driven, designed for extension.