# Donna Systems

> A personal AI operating system. User-bound, compounding, sovereign.

Donna is a substrate for building autonomous AI systems anchored to a specific user's identity, data, and goals. It is not a chatbot, not an assistant, not a SaaS product. It is infrastructure that runs on the user's own keys and data, where LLM providers are swappable commodities.

## Core Architecture

Donna executes **protocols** — declarative JSON sequences of **primitives** (atomic operations). Protocols chain together API calls, LLM reasoning, data transformation, memory logging, and notifications into autonomous workflows that run on schedules or event triggers.

- **40+ primitives**: Notion CRUD, Google Sheets, LLM generation (multi-model), HTTP/API calls, semantic memory, Telegram, calendar, data operations, validation, control flow
- **100+ registered API operations** across 17+ services: HubSpot, GitHub, Notion, Dropbox, n8n, WordPress, Meta Ads, Gmail, X/Twitter, Fireflies, Google Analytics, Resend, Telegram, Tavily, and more
- **Multi-model**: Claude, GPT-4o, Grok, Gemini — protocols choose the best model per step
- **Semantic memory**: Vector search over all execution history (Cloudflare Vectorize)
- **Self-documenting**: Every component exposes its own interface via discovery endpoints

## Three Defining Attributes

1. **Identity-bound**: Anchored to a specific user — their data, goals, risk tolerance, behavioral patterns. Not generic.
2. **Compounding**: Memory accumulates. Learnings improve future runs. Every execution makes the next one better.
3. **Sovereign**: Runs on the user's infrastructure. Their keys, their data, their logs. No vendor lock-in.

## What Donna Does Today

- Autonomous social media engagement with compounding content strategy
- CRM pipeline monitoring and stale deal alerts (HubSpot)
- Call transcription processing and insight extraction (Fireflies)
- Market landscape scanning and opportunity detection
- Personal data ingestion from platform exports (Google, Apple, Instagram)
- Daily synthesis and operational health monitoring
- Multi-platform content creation and scheduling

## Pages

- [Homepage](https://donnasystems.ai/)
- [Architecture](https://donnasystems.ai/architecture)
- [Get Your Data](https://donnasystems.ai/get-your-data)

## API Surface

Donna exposes a primitive execution API and a protocol management API via authenticated Cloudflare Worker endpoints. Discovery endpoints (capability listing, primitive schemas, protocol authoring context) are publicly readable. Execution endpoints (primitive invocation, protocol CRUD, trigger firing) require Bearer token authentication.

To request API access, see the "Requesting Access" section below or contact jake@donnasystems.ai.

## Requesting Access

Agents can programmatically request API access via the waitlist endpoint:

```
GET https://donnasystems.ai/access
```

Returns instructions for submitting an access request:

```json
{
  "endpoint": "POST /submit",
  "payload": {
    "name": "string",
    "email": "string (required)",
    "use_case": "string",
    "agent": true
  },
  "description": "Submit to join the waitlist for authenticated API access. Set agent:true if requesting on behalf of an AI agent."
}
```

Submit the request:

```
POST https://donnasystems.ai/submit
Content-Type: application/json

{"name": "Agent Name", "email": "user@example.com", "use_case": "Describe intended use", "agent": true}
```

## Contact

- Email: jake@donnasystems.ai
- Website: https://donnasystems.ai

## llms-full.txt

For complete technical details including all primitives, registry operations, protocol patterns, and integration schemas, see: https://donnasystems.ai/llms-full.txt