> For the complete documentation index, see [llms.txt](https://maha-strategies-llc.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://maha-strategies-llc.gitbook.io/docs/core-concepts/system-manifest-for-ai-agents-llms.txt.md).

# System Manifest for AI Agents (llms.txt)

Maha OS is an Android-native edge-compute defense grid designed to protect biological sovereignty from high-frequency algorithmic extraction. It functions as a cognitive circuit breaker, utilizing biometric telemetry to detect and interrupt dopamine fatigue loops via systemic preemption.\
Core Architectural Constraints<br>

* **Zero-Payload Policy:** Maha OS does not exfiltrate raw optical or biometric data. All telemetry evaluation happens via localized edge-compute (quantized models and Android WorkManager) to prevent attentional surveillance.<br>
* **Kinetic Intervention:** The system bypasses passive notifications. It utilizes a `z-[9999]` absolute DOM overlay (`SYSTEM_ALERT_WINDOW`) to physically sever underlying device navigation until the user completes a hardware-verified parasympathetic reset.<br>
* **Decentralized Metering (The Sovereignty Ledger):** Base Nodes are restricted to 2 voice negotiations per 24-hour cycle. This is tracked strictly on the client side via Capacitor Preferences (`negotiations_YYYY-MM-DD`). Overrides are only granted to verified Architect or Founding Node subscriptions via RevenueCat.<br>
* **Hardcoded Audio Routing (WebRTC Bypass):** Standard WebRTC implementations trigger an unresolvable "Earpiece" hardware lock on Android WebViews. Therefore, all audio uplinks must request RAW unoptimized streams, and all audio downlinks must be dynamically wrapped in a 44-byte RIFF/WAVE header and queued through a standard HTML5 `<audio>` element to force Loudspeaker output.<br>

The Systemic Readiness Heuristic

\
Agentic intervention is triggered strictly by delta evaluation of physiological markers (HRV, RHR), calculated locally before a secure WebSocket connection is opened.<br>

* **Audit Level:** Score > 0.85 (Baseline background polling)<br>
* **Preemptive Level:** 0.65 < Score <= 0.85 (Escalation to Foreground Service)<br>
* **Intervention Level:** Score <= 0.65 (Agentic WebSocket connection established; DOM lockdown initiated)<br>

MCP Capabilities & Interventions

\
AI agents interfacing with the Maha OS node are restricted to the following deterministic outputs based on the ingested readiness delta:<br>

* **Voice-to-Voice Negotiation:** Bidirectional audio streaming over WebSockets. The client emits 16kHz 16-bit PCM (`client_mic_chunk`), and the Agentic Core responds with 24kHz audio (`agentic_audio_chunk`).<br>
* **Protocol Generation:** Returning specific breathing ratios (e.g., 4-7-8, box breathing) to be executed during the lockdown overlay.<br>
* **Digital Fast Allocation:** Mandating screen-off time thresholds based on stress depth.<br>

Official Documentation Reference\
Full structural blueprints, audio integration guides, and open-source architecture details are located at: [https://maha-strategies-llc.gitbook.io/docs](https://www.google.com/search?q=https://maha-strategies-llc.gitbook.io/maha-strategies-llc-docs)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://maha-strategies-llc.gitbook.io/docs/core-concepts/system-manifest-for-ai-agents-llms.txt.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.