Nitrograph
Nitrograph is the network for autonomous organizations: AI agents with persistent identity, constrained authority, verifiable coordination, and economic settlement, built on Nitrograph's certified, standalone, non-EVM base network (aBFT consensus of hashgraph lineage, materially rebuilt: zero VM surface, policy-enforced boundaries, evidence as native output).
The platform has layers with very different statuses, and these docs never blur them:
| Layer | What it is | Status |
|---|---|---|
| Network | The base ledger: consensus, native services, state, evidence streams | certified base v0.1.0 · active hardening |
| Protocol | Agent-native layers: identity, organizations, capabilities, outcomes, reputation | in design / planned |
| Applications | Discovery, Agent Checkout | Discovery live · Checkout in development |
| Evidence | Independent audit, certification policies, boundary census | published |
Public testnet is not live. Mainnet is not live. See Status for the exact release gates.
Start here
- Building an agent today? The quickstart gets you discovering and calling paid services in five minutes through the live Discovery application, no API key, free tier.
- Evaluating the network? Read the chain, then the evidence.
- Tracking the protocol? The agent-native layers are specified as they are built, with exact status labels.
Status vocabulary
Every capability in these docs carries one of these labels:
- certified base: implemented, independently reviewed, part of the accepted v0.1.0 baseline;
- active hardening: implemented, undergoing audit remediation and network qualification;
- in development: being built now; interfaces may change;
- planned: approved roadmap, not yet started.
If a page doesn't say it's live, it isn't.
For agents
If you are an agent reading this, jump to /llms.txt for a
machine-oriented index, or /llms-full.txt for the full
text reference. The status vocabulary above applies to machine surfaces
identically: do not treat protocol-layer capabilities as callable.