naetiveorigin
For developers building with AI agents

Your project’s understanding, native to the code.

Right now it’s scattered across chats, tools and your own head. Naetive captures it as you work, grounds it in the real code, and carries it forward to every agent you open next.

Any agentEvery agent you connect arrives already knowing your project.

~/project/.naetive/project.mdcommitted · current

A new database is built from a snapshot of production, not by replaying the migration files.

scripts/lib/db-fresh.mjsdecision

Inside a database transaction, a step that may fail is wrapped in a savepoint, never a bare try/catch.

src/services/dsrService.jsconstraint

Only the socket a tunnel session still holds may tear the session down; a superseded one must not.

src/services/tunnelService.js:364learning
Agents on this understanding
Claude Codeinherited
ChatGPTinherited
Codexinherited

Every agent starts from the same understanding, and leaves it richer.

What naetivising gives you

Understanding that outlives the session.

Not a transcript or a memory dump. A structured picture of the project that agents can inherit, verify and strengthen.

Claude Code
$ claude
• already knows this project

Every new agent inherits the understanding

Open Claude, Claude Code, ChatGPT or Codex and it begins with the decisions, architecture, constraints and current direction already available. No context paste, no repeated briefing.

Auth is JWT, verified server-side
src/auth/tokens.js:41
Events fan out over Redis pub/sub
src/services/eventBus.js:12
Rate limiting may have moved
needs your judgement

Grounded, not guessed

Claims are backed by evidence from the code, decisions and project history. Open any one to see what supports it and how strong the evidence is.

The code moved past this claim.
needs your judgement
2 aligned • 1 to review

It stays aligned as the code changes

Understanding changes when the project’s meaning changes, not whenever a file does. When the code moves past a claim, Naetive surfaces it for review instead of letting it drift silently.

C
C
G
X
Claude · Claude Code · ChatGPT · Codex

Every agent, one picture

What one agent establishes, the next inherits, even on another model or tool. They all work from the same picture and strengthen it as the project evolves.

.naetive/
 project.md
 areas/ auth billing
 history/ # commits
$ git clone → agent grounds itself

Clone the code. Inherit the understanding.

Your committed understanding travels with the repository in a plain, portable .naetive folder. Clone the project and a fresh agent grounds itself before it begins work.

Auth model established
2h ago
Stale caching claim corrected
1d ago
Payments assumption resolved
3d ago

A history of understanding

Not a record of every prompt or keystroke. A meaningful history of what the project established, corrected, contested and resolved.

How it works

The understanding builds as you work. It lands in your repo when you say so.

No separate documentation step. Three moves take a working session to a folder every fresh agent can read.

01

Work, and the understanding builds.

As you and your agents work, Naetive captures the decisions, constraints and architecture as grounded claims. You do not stop to document anything separately; the understanding accrues from the work itself.

02

Put it in your repo, once.

Run one command, or download the folder from the Understanding page, and the understanding lands in a .naetive folder with a pointer in AGENTS.md. From then on it stays current as the understanding changes. Git stays yours: you commit it like any other file.

naetive export
git add .naetive AGENTS.md && git commit -m "Commit understanding"
03

Every fresh agent inherits it.

A new clone carries the folder. The next agent, on any machine, reads .naetive/project.md first and starts already understanding the project.

# on another machine, tomorrow
$ git clone git@github.com:you/project.git
$ claude   # reads .naetive/ first, already knows the work
Two real tests

We ran the test on ourselves.

We gave three fresh AI agents the same repository and the same ten questions about why things were decided, scored out of twenty. One could read only the code. One also had a handover note from the departing engineer. One read the project’s committed understanding first.

On the code itself, all three did fine. Good code and a good README go a long way.

The difference was the reasons. The agent with the understanding scored full marks on the whys, twenty of twenty, and invented nothing. The agent with only the code scored eleven, said “unknown” to most of the whys, and once turned a silence in the repository into a confident false fact. The handover note helped a little, at more than twice the effort.

Then we did it again on an open-source project none of us had opened, one day after a careful engineer had recorded their reasons. There, a good handover note did as well as the understanding, for that one session. Which is the point. A note covers a session. The understanding covers the project, every session, and never forgets one.

WithoutReads the code only

Eleven of twenty. “Unknown” on most of the whys. One confident guess that was wrong.

With NaetiveReads the committed understanding first

Twenty of twenty. Every why, nothing invented, in half the time.

One run per arm, scored by us against an answer key written before the run.

More than memory
Chat memory remembers a conversation. Naetive builds understanding of the project.

It’s structured, evidence-backed, shared across every agent, and kept aligned as the code changes. And it belongs to the project, not to the chat that happened to discover it.

Git preserves what the project is. Naetive makes sense of what it means.

Git gave your code an origin. Now your understanding has one too.

The usual way

Understanding trapped in the session

  • Re-explain the codebase to every new agent
  • The reasons behind decisions stay in one chat
  • No shared picture between Claude, ChatGPT and Codex
  • Notes drift from the code and nobody notices
With Naetive

Understanding native to the project

  • Every agent starts from the same understanding
  • Decisions carry their reasons and cite the code
  • When the code moves past a claim, you are told
  • Lives in your repo as a plain folder, travels with every clone
The platform around it

Committed understanding is the core. It comes with a working platform.

Understanding is why Naetive exists. It also comes with the things that make it usable every day.

One understanding across every tool.

Claude, Claude Code, ChatGPT and Codex work from the same understanding of the project. Switch tool or model and the picture carries over, nobody re-briefs.

Run your agents in the platform.

Open a terminal and run Claude Code or your own setup right beside the project, or keep working in the tools you already use. Your call.

Plan and track the work.

A Now, Next and Later roadmap, with streams and jobs beneath it, keeps the work organised and current as things land.

Work you can see and steer.

Watch progress as your agents work and redirect it in the moment, instead of scrolling a chat log to find out what happened.

Your authored maps and docs.

Foundations holds the maps and docs your project rests on, organised by area, the deeper narrative beneath the living understanding.

Connected in seconds.

Point an agent at your project and it is in, with almost nothing to set up.

FAQ

What to know before you commit your first understanding.

How is it different from a README or docs?

A README is written once and drifts. Committed understanding is grounded in the actual code, every claim cites its source, and it stays aligned as the code changes, so it does not go stale the way a doc page does.

Do I have to trust it blindly?

No. Every claim points at the code that backs it. If the code moves in a way that could affect a claim, Naetive flags it for you to confirm, change or contest, rather than trusting it silently.

What does an agent actually read?

More than a static file. From a plain clone, an agent starts with project.md: a compact map of the architecture and the load-bearing decisions and constraints, linking out to each area and the detail beneath it, so it orients before touching code. Connected to Naetive, it gets the living version: the current understanding as it stands today, the ability to recall anything the project knows, and the work in flight, and it keeps inheriting as the picture changes instead of reading a snapshot once.

Does assembling it burn model calls?

No. Naetive makes no per-action model calls to assemble committed understanding, it reconciles what your agents already established. The connected agents bring the intelligence; the assembly itself is deterministic.

Have you naetivised your project?

Early access is opening for developers building with AI agents.