Deep Research for Obsidian integrates with OpenAI to power an intelligent research assistant inside Obsidian. It can query academic databases and the web, ingest PDFs and reference metadata, produce concise summaries, highlight missing links in your knowledge graph, and propose an exploration path to further your study. All outputs are stored as markdown notes with citations, allowing seamless integration with your existing note-taking workflow.

Triagent provides a tri-agent architecture consisting of Strategist, Researcher, and Executor modules. The Strategist breaks down high-level goals into actionable steps, the Researcher retrieves and synthesizes data from documents, APIs, and web sources, and the Executor performs tasks like generating text, creating files, or invoking HTTP requests. Built on top of OpenAI language models and extensible via a plugin system, Triagent supports memory management, concurrent processing, and external API integrations. Developers can configure prompts, set resource limits, and visualize task progress through a CLI or web dashboard, simplifying multi-step automation pipelines.