# alpaca-llm-bot-v1

Autonomous LLM trading system (paper-first) powered by:
- Alpaca trading API
- Ollama (curator + decision models)
- Searx ingestion + targeted deep research
- Qdrant memory retrieval for prior similar setups
- Trilium auto-journaling of decisions/trades
- Optional n8n webhook emission for orchestration
- FastAPI dark dashboard

## v1.3 additions
- Retrieval-augmented decisions via Qdrant (`QDRANT_URL`)
- Auto-write trade logs to Trilium (`TRILIUM_URL`, `TRILIUM_TOKEN`)
- n8n signal hook (`N8N_BOT_WEBHOOK`)
- Two-model pipeline: cheap curator + stronger final decision model
- Fee/slippage-aware tiny-bankroll controls

## Run
```bash
cp .env.example .env
# fill Alpaca keys + optional Trilium/N8N vars
python3 -m uvicorn app:app --host 0.0.0.0 --port 8089
```

Dashboard:
- `http://<host>:8089/`

Manual triggers:
```bash
curl -X POST http://127.0.0.1:8089/curate-now
curl -X POST http://127.0.0.1:8089/run-now
```

## Safety
- Keep `PAPER_MODE=true` until stable
- This is experimental software, not financial advice