JARVIS RD Assistant¶
A self-hosted research workspace for discovering, organizing, and interrogating scientific literature. JARVIS links generated claims to retrieved source text, combines literature work with spaced-repetition learning and project tasks, and can run model inference on infrastructure you control with Ollama.
If you configure a cloud model through LiteLLM, relevant prompts and source excerpts are sent to that provider. Generated outputs can still be incomplete or wrong; read Methods and limitations before relying on verification badges, consensus views, or extracted evidence.
Get started¶
- Read the User Guide — what JARVIS does and how to use every feature, from your first sign-in to Telegram check-ins.
- Install & operate it — clone, run the onboarding wizard, and deploy solo, on a LAN, or behind a tunnel.
Explore¶
- Research Feed & Library — discover, save, and triage papers.
- Ask — Cross-paper RAG — question your whole library at once.
- Pulse and Learning Cards — a personalised feed and spaced-repetition review.
- Deployment, Requirements, and Security — everything an operator needs.
- Architecture and Engineering Standards — for contributors.
This site is a generated read-only view. Canonical edit targets are the Markdown files in the repository — always edit the source, not the HTML.