Skip to content

About

Example: deep research agent in Python using AgentSearch

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep research agent (Python, AgentSearch + OpenAI Agents SDK)

A small research agent that breaks a question into sub-questions, searches the live web with AgentSearch, and writes a cited markdown report. Search is free (25 searches/day per user, no AgentSearch key).

Run

python3 -m venv .venv && . .venv/bin/activate
pip install -r requirements.txt

export OPENAI_API_KEY=sk-...
python research.py "What are the main approaches to long-term memory for LLM agents in 2026?"

# No LLM key? Search-only mode:
python research.py --no-llm "LLM agent memory approaches" -n 3

A full run uses about 3-5 free searches. To let the agent read whole pages (agentsearch_extract, $0.005 per call in USDC on Base via x402), run pip install "openai-agents-agentsearch[paid]" and set AGENTSEARCH_WALLET_PRIVATE_KEY to a new wallet funded with a little USDC. Spend is capped at $1.00 per process by default (AGENTSEARCH_MAX_TOTAL_ATOMIC).

Package: https://pypi.org/project/openai-agents-agentsearch/

MIT

About

Example: deep research agent in Python using AgentSearch

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages