Deep Research Agent

An agentic research system with planning, sub-agent delegation, and human-in-the-loop approval

Overview

A deep research agent that accepts natural language questions, creates a structured research plan, obtains human approval, then delegates specialized research tasks to isolated sub-agents that conduct web searches and synthesize findings. Uses file-based context offloading instead of context stuffing, and runs Gemma 4 locally via Ollama or any cloud LLM.

Screenshots

Tech Stack