# btahir/open-deep-research

Open source alternative to Gemini Deep Research. Generate reports with AI based on search results.

Repository: https://github.com/btahir/open-deep-research
Canonical: https://ross.abutalabs.com/products/btahir-open-deep-research
Homepage: https://opendeepresearch.vercel.app
Language: TypeScript
License: MIT
License Family: permissive
Archived: true
Last push: 2025-12-15T07:25:10+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 57, release rhythm 35, longevity 44
- inputs: {"age_days": 617, "days_push": 261, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2141, forks 206 (observed 2026-08-28T04:06:18.374665+00:00)

## What it is
An open-source web application that replicates Gemini's Deep Research by searching the web, extracting page content, and generating AI-written reports with a model of your choice (Gemini, GPT, Claude, DeepSeek, or local models). It includes a knowledge base for saving reports, local file analysis, and export to PDF, Word, and text.

## Use cases
- generate an in-depth research report on a topic automatically
- open source alternative to Gemini deep research
- summarize web search results into a structured report with AI
- research a topic using my own choice of LLM instead of a locked-in provider
- analyze uploaded PDF or DOCX documents and produce a report
- build a personal knowledge base of AI research reports
- run deep research with local models for privacy

## When to choose
- you want deep-research-style reports without paying for a proprietary product
- you need flexibility over which AI provider or local model generates the report
- you want to combine web sources with your own local documents
- you prefer self-hosting and MIT-licensed tooling

## When to avoid
- you need fully autonomous multi-agent research with citation verification
- you have no API keys for search providers or LLMs and cannot obtain them
- you need enterprise-grade knowledge management beyond browser local storage

## Facets
- artifact type: application
- maturity: active
- function: rag, search-engine, llm-inference, web-scraping, pdf, chat-interface
- domain: artificial-intelligence, large-language-models, web-development, developer-tools
- platform: self-hosted, browser
- tags: deep-research, report-generation, openai, gemini, anthropic, deepseek, jina-ai, knowledge-base, nextjs, firecrawl, search, natural-language-processing, web-server, nodejs

## Member repositories
- btahir/open-deep-research (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:18.374665+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 2026-08-30T02:51:21.116720+00:00, confidence not recorded.
  - readme: https://github.com/btahir/open-deep-research (fetched 2026-08-28T04:06:18.374665+00:00, sha 5d4fe1b0085b)
  - homepage: https://opendeepresearch.vercel.app (fetched 2026-08-29T10:31:41.744389+00:00, sha 5b14185aa9d4)
- Data as of 2026-08-30T08:39:29.467469+00:00.