How sakshamsingh22/quorum-multi-agent-research works
Quorum is a multi-agent research assistant with both a Streamlit workspace and a CLI entry point. A topic is validated, searched, used to select and read a public source, synthesized into a structured report, and critiqued; the UI presents progress and results. The graph separates orchestration, agent stages, and web tools/security. The README documents the four-stage flow; sampled source shows the orchestration and tool wiring, but not every UI detail.
Main entry points: app.py Streamlit workspace · pipeline.py Stage orchestration · agents.py Search agent · tools.py Page extraction
Components 15
User interfaces
- Streamlit workspace
app.py - CLI pipeline
pipeline.py - Report and critique
app.py
Research workflow
- Stage orchestration
pipeline.py - Search agent
agents.py - Reader agent
agents.py - Report writer
agents.py - Report critic
agents.py
Research tools
- Web search
tools.py - Page extraction
tools.py - URL validation
security.py
Other components
- Researcher
- Tavily Search
- Mistral model
- Public web pages
Connections 21
- Researcher → Streamlit workspace: submits topic
README.md - Researcher → CLI pipeline: enters topic
README.md - CLI pipeline → Stage orchestration: runs
pipeline.py - Streamlit workspace → Search agent: invokes
app.py - Streamlit workspace → Reader agent: invokes
app.py - Streamlit workspace → Report writer: invokes
app.py - Streamlit workspace → Report critic: invokes
app.py - Stage orchestration → Search agent: invokes
pipeline.py - Stage orchestration → Reader agent: invokes
pipeline.py - Stage orchestration → Report writer: invokes
pipeline.py - Stage orchestration → Report critic: invokes
pipeline.py - Search agent → Web search: uses tool
agents.py - Reader agent → Page extraction: uses tool
agents.py - Web search → Tavily Search: searches
tools.py - Page extraction → URL validation: validates URL
tools.py - Page extraction → Public web pages: fetches page
tools.py - Search agent → Mistral model: runs model
agents.py - Reader agent → Mistral model: runs model
agents.py - Report writer → Mistral model: runs model
agents.py - Report critic → Mistral model: runs model
agents.py - Streamlit workspace → Report and critique: renders
app.py