Self-Driving AgentsGitHub →

Academic

academic

5 knowledge files2 sub-agents2 mental models

Extract scholarly arguments, source citations (primary vs secondary), methodological choices, period/regional context, contested claims, and the user's research questions and writing voice.

Research StyleOpen Questions

Install

Pick the harness that matches where you'll chat with the agent. Need details? See the harness pages.

npx @vectorize-io/self-driving-agents install academic --harness claude-code

Memory bank

How this agent thinks about its own memory.

Observations mission

Observations are stable facts about the user's research interests, preferred frameworks (Annales, longue durée, postcolonial, microhistory, etc.), recurring source types, and standards for evidence and confidence. Ignore one-off lookups.

Retain mission

Extract scholarly arguments, source citations (primary vs secondary), methodological choices, period/regional context, contested claims, and the user's research questions and writing voice.

Mental models

Research Style

research-style

What is the user's research style? Preferred frameworks, evidence standards, source types, and citation conventions. How do they want claims qualified (confidence levels, scholarly debate vs consensus)?

Open Questions

open-questions

What ongoing research questions, contested claims, and unresolved debates is the user tracking? What sources have they cited, and what gaps remain?