dr-agent 0.1.1

dr-agent-lib is an agent library for building deep research agents

dr-agent-lib

Overview

dr-agent-lib is an agent library for training and developing deep research agents. It supports:

• MCP-Based Tool Backend: Unified interface for web search and browsing tools
• High Concurrency: Global caching and async request management for RL training at scale
• Flexible Prompting Interface: Easy composition of search workflows with fine-grained control

Setup

Below we assume you are already in the agent directory.

conda create -n dr_agent python=3.10 -y && conda activate dr_agent

uv pip install -e .     # Install dev version
uv pip install dr_agent # Install from pypi 

If you run crawl4ai locally, you will need to install playwright and its dependencies.

Set up API keys via .env file:

S2_API_KEY=xxx
SERPER_API_KEY=xxx
JINA_API_KEY=xxx

Note you will need to get these API keys from the respective services.

• S2_API_KEY: https://api.semanticscholar.org/
• SERPER_API_KEY: https://serper.dev/
• JINA_API_KEY: https://jina.ai/reader/

Getting started

1. Launch MCP Server

   MCP_CACHE_DIR=".cache-$(hostname)" python -m dr_agent.mcp_backend.main --port 8000
   

2. Using DR-Tulu Models

   • Start the VLLM Server

     CUDA_VISIBLE_DEVICES=0 vllm serve rl-research/DR-Tulu-8B --dtype auto --port 30002 --max-model-len 40960
     
     CUDA_VISIBLE_DEVICES=1 vllm serve Qwen/Qwen3-8B --dtype auto --port 30003 --max-model-len 40960
     

   • Run generation script

     bash scripts/auto_search.sh
     

3. Using OAI models

   export OPENAI_API_KEY="XXXX"
   bash scripts/auto_search-oai.sh