AxonOS is a pre-clinical technical infrastructure project for the brain-computer interface boundary.
It defines the missing operating layer between neural hardware, real-time signal processing, consent enforcement, typed neural intent events, and AI-enabled applications.
AxonOS is strictly an OS for the Brain.
It is not merely an AI-agent framework, chatbot runtime, generic Python SDK, or speculative token project.
Watch the full concept video:
This is a simulated concept demonstration using EEG-style telemetry and gameplay input. It is not a clinical, medical-device, or regulatory claim.
This repository is the public top-level AxonOS entry point.
It contains:
- public media assets;
- legacy Python prototype material;
- early project bootstrap files;
- links to the canonical AxonOS technical stack.
The canonical technical standard lives here:
https://github.com/AxonOS-org/axonos-standard
This repository should be read as the public project gateway, not as the complete safety-critical implementation.
Raw neural data should not become the default application API.
A BCI operating layer must define:
- what neural-derived data crosses the boundary;
- which application is allowed to receive it;
- which consent state authorized it;
- how long the event remains valid;
- whether the event is typed and schema-valid;
- whether raw signal access is prohibited;
- whether the event has provenance and auditability.
The AxonOS principle:
Applications should receive typed, consent-bound intent events, not unrestricted raw neural streams.
neural hardware
↓
acquisition boundary
↓
real-time kernel substrate
↓
consent and neural-permission enforcement
↓
deterministic intent processing
↓
typed neural intent events
↓
application SDK
↓
assistive, research, or intelligent applications
| Repository | Role | Status |
|---|---|---|
axonos-standard |
Canonical technical standard and architecture manual | Canonical |
axonos-rfcs |
Engineering RFCs and design records | Normative when finalized |
axonos-kernel |
Real-time kernel substrate | Research-grade |
axonos-sdk |
Application-facing SDK and typed intent boundary | Active |
axonos-consent |
Consent FSM and neural permission reference crate | Pre-clinical reference |
axon-bci-gateway |
Acquisition-boundary / OpenBCI HIL gateway | Non-safety acquisition boundary |
axonos-swarm |
Distributed timing and coordination research | Experimental |
AxonOS separates claims by evidence level.
| Level | Meaning |
|---|---|
| L0 | Design intent or architecture statement |
| L1 | Static proof, model checking, type-level guarantee, deterministic unit proof |
| L2 | Software test, fuzzing, simulation, property test, or CI result |
| L3 | Hardware-in-the-loop or measured physical validation |
| L4 | Independent third-party audit or laboratory validation |
Current public repositories primarily contain L0, L1, and L2 evidence.
AxonOS does not currently claim L3 or L4 clinical validation.
AxonOS does not currently claim:
- FDA clearance;
- CE mark;
- clinical efficacy;
- certified medical-device status;
- production implantation readiness;
- complete IEC 62304 compliance;
- complete ISO 14971 compliance;
- complete ISO 13485 quality-system compliance;
- independent clinical validation;
- medical-device approval in any jurisdiction.
These are possible future milestones, not current claims.
axonos-standardTECHNICAL_DUE_DILIGENCE_POSITION.txtCOMPATIBILITY.mdCLAIMS.mdaxonos-consentaxonos-sdkaxonos-kernelaxon-bci-gateway
Website: https://axonos.org
GitHub: https://github.com/AxonOS-org
General contact: connect@axonos.org
Security: security@axonos.org
MIT, unless a repository-specific license states otherwise.