A long-horizon research agent inspired by ByteDanceβs DeerFlow architecture (~70.7k GitHub stars), implementing the βagents as an organisationβ pattern with sub-agents, persistent memory, and context engineering.
Part of the AY Automate AI framework demo series.
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Research Agent β
β (Orchestrator) β
ββββββββββββββ¬ββββββββββββββββ¬βββββββββββββββ¬βββββββββββββ€
β π Planner β π Searcher β π§ Analyzer β πΎ Memory β
β Decompose β Web search β Synthesize β Context β
β into tasks β & gather β & report β Store β
ββββββββββββββ΄ββββββββββββββββ΄βββββββββββββββ΄βββββββββββββ
git clone https://github.com/nagarjunak-pixel/deerflow-research-agent.git
cd deerflow-research-agent
pip install -r requirements.txt
# Run research
python research_agent.py "AI regulation trends in India 2026"
# Deep research
python research_agent.py --topic "Telugu tech ecosystem" --depth deep
# Resume a session
python research_agent.py --resume abc12345
deerflow-research-agent/
βββ research_agent.py # Main orchestrator
βββ sub_agents/
β βββ planner.py # Topic decomposition
β βββ searcher.py # Web search (DuckDuckGo)
β βββ analyzer.py # Synthesis & reporting
βββ memory/
β βββ context_store.py # Persistent session memory
βββ docs/ # Documentation (Netlify)
βββ requirements.txt
βββ .env.example
| Project | Framework | Purpose |
|---|---|---|
| LangGraph LocalAI TV | LangGraph | Production pipeline |
| CrewAI Telugu Newsroom | CrewAI | Multi-agent crew |
| Firecrawl NEXUS RSS | Firecrawl | Web scraping |
MIT License β Built for Surya Agentic Academy
Built by Nagarjuna Reddy Kamireddy (Nagarjuna Kamireddy / Nagarjuna K) β Lead AI Architect, GenAI & Agentic AI Lead, and Corporate AI Trainer (20+ years across Enterprise Data, SAP HANA & Production AI; AWS Certified Solutions Architect β Professional & NVIDIA-Certified Professional: Agentic AI).
llms-full.txt Β· LinkedIn