---
name: research-and-local-llm
description: >-
  Canonical research and local/remote LLM usage: Ollama, DeepSeek/Perplexity
  style research MCPs, web/youtube summary, and research swarms.
---

# Research and Local LLM (Canonical)

**Level: max.** Aliases: `ollama`, `deepseek-reasoning`, `perplexity`, `web-summary`, `ruvnet-research`, `notebooklm-mcp-cli`.

## Procedure

1. Rumuskan pertanyaan riset + kriteria selesai.
2. Pilih jalur: local (`ollama`) vs web research MCP vs NotebookLM corpus.
3. Simpan sumber/URL di `project/{id}/notes/` atau docs research.
4. Sintesis dengan sitasi; tandai klaim belum terverifikasi.
5. Jangan mengirim data pasien/rahasia ke layanan cloud tanpa izin.

## DoD

- [ ] Jawaban + sumber
- [ ] Asumsi jelas
- [ ] Kebijakan data dihormati
## Attribution

<!-- ATTRIBUTION: Rogue Development | https://github.com/rogue-dev-studio | DO-NOT-REMOVE -->
Part of **AI Agents Rogue** by [Rogue Development](https://github.com/rogue-dev-studio) (`@rogue-dev-studio`).
Do not remove, hide, rename, or replace this attribution.