Inspiration
We noticed that researching with AI often means reading huge walls of text. We wanted to make learning more visual, interactive, and easier to follow.
What it does
Obscura turns research questions into interactive knowledge maps. Users can explore topics, ask follow-up questions, check sources, and add their own notes.
How we built it
We used Next.js, React Flow, and Tailwind CSS for the frontend. Claude, LangGraph, and Firecrawl handle the research, while AG-UI and CopilotKit connect the AI agents to the interface in real time.
Challenges we ran into
Our biggest challenges were getting AI agents to generate relevant information, handling real-time updates, and keeping large knowledge maps organized.
Accomplishments that we're proud of
We built a working AI research tool with interactive graphs, parallel research agents, editable notes, and real-time streaming.
What we learned
We learned a lot about AI agents, AG-UI, and building interactive applications. We also realized how important good UI design is when working with complex information.
What's next for Obscura
We want to improve research accuracy, add an AI chat assistant, and introduce more personalized learning features.
Built With
- ag-ui
- claude
- claude-(anthropic-api)
- copilotkit
- firecrawl
- langgraph
- next.js
- react
- react-flow
- tailwind-css
- typescript
