# mshumer/OpenDeepResearcher

Repository: https://github.com/mshumer/OpenDeepResearcher
Canonical: https://ross.abutalabs.com/products/opendeepresearcher
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2025-05-02T02:41:44+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 19, release rhythm 35, longevity 41
- inputs: {"age_days": 576, "days_push": 488, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2791, forks 359 (observed 2026-08-28T04:07:22.067249+00:00)

## What it is
A Jupyter Notebook (with a Gradio UI variant) implementing an autonomous AI research agent that iteratively generates search queries, fetches and evaluates web pages, and compiles a comprehensive report. It orchestrates SERPAPI for search, Jina for content extraction, and OpenRouter-hosted LLMs for query generation, relevance judgment, and report writing.

## Use cases
- run deep research on a topic and get a cited report
- automate multi-round web research with an LLM agent
- generate search queries iteratively until enough context is gathered
- extract relevant context from web pages automatically
- build a deep research agent similar to OpenAI's deep research
- research assistant that searches Google and summarizes findings

## When to choose
- you want a lightweight, hackable deep-research agent as a notebook
- you already have OpenRouter, SERPAPI, and Jina API keys
- you want to study or extend an iterative agentic research loop
- you prefer a quick Colab-based tool over a self-hosted service

## When to avoid
- you need a production-grade service with auth, UI, and persistence
- you want to avoid paid third-party API dependencies
- you need local/offline research without external search APIs
- you need a maintained package with tests rather than a notebook prototype

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, search-engine, llm-inference, web-scraping
- domain: artificial-intelligence
- platform: python, cross-platform
- tags: deep-research, jupyter-notebook, gradio, serpapi, openrouter, jina, iterative-research, async, ai-agents, retrieval-augmented-generation, search, natural-language-processing, web-server

## Member repositories
- mshumer/OpenDeepResearcher (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.067249+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:15:16.485129+00:00, confidence not recorded.
  - readme: https://github.com/mshumer/OpenDeepResearcher (fetched 2026-08-28T04:07:22.067249+00:00, sha 6b9917cd4f67)
- Data as of 2026-08-30T08:39:29.467469+00:00.