# assafelovic/gpt-researcher

An autonomous agent that conducts deep research on any data using any LLM providers

Repository: https://github.com/assafelovic/gpt-researcher
Canonical: https://ross.abutalabs.com/products/gpt-researcher
Homepage: https://gptr.dev
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, python, agent, automation, research, search, webscraping, llms, deepresearch, mcp, mcp-server
Last push: 2026-08-24T06:58:46+00:00

## Health v2 (maintenance only)
Score: 96/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 86
- inputs: {"age_days": 1209, "days_push": 9, "days_rel": 9, "gap_med": 14.0, "n_releases_24m": 41}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 29160, forks 3959 (observed 2026-08-28T04:11:53.121016+00:00)

## What it is
GPT Researcher is an open-source autonomous deep research agent that plans research questions, scrapes web and local sources, and produces detailed cited research reports using any LLM provider. It is available as a Python package, Docker image, web app, and MCP server, with parallelized planner/execution agents for speed and reliability.

## Use cases
- generate deep research reports with citations on any topic
- automate market research and competitor analysis
- build a custom domain-specific research agent
- run an MCP research server for Claude or other LLM clients
- research company briefs, stock analysis, or trend reports
- aggregate and summarize information from multiple web sources automatically

## When to choose
- you need long, factual, cited research reports rather than short LLM answers
- you want an open-source alternative to closed deep-research products
- you need to plug research capabilities into your app via Python or MCP
- you want to customize research agents for specific domains or sources

## When to avoid
- you need a simple chatbot without web research
- you cannot incur LLM API costs, since each task consumes tokens
- you need fully deterministic, verifiable outputs without LLM hallucination risk
- you want a lightweight tool without web scraping infrastructure

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, rag, web-scraping, search-engine, llm-inference, mcp, sdk
- domain: artificial-intelligence, large-language-models
- platform: python, self-hosted, cross-platform
- tags: deep-research, autonomous-agent, research-reports, multi-agent, citations, open-source, ai-agents, retrieval-augmented-generation, natural-language-processing, automation, research, docker, web-server

## Member repositories
- assafelovic/gpt-researcher (main) score 96

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:53.121016+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 2026-08-29T16:53:10.343520+00:00, confidence not recorded.
  - readme: https://github.com/assafelovic/gpt-researcher (fetched 2026-08-28T04:11:53.121016+00:00, sha ea3bc825953b)
  - homepage: https://gptr.dev (fetched 2026-08-29T07:50:21.574874+00:00, sha 0c4c5774fa20)
  - site_page: https://docs.gptr.dev/docs/gpt-researcher/getting-started/introduction (fetched 2026-08-29T07:50:21.577597+00:00, sha c31830ccb009)
  - registry_pypi: https://pypi.org/pypi/gpt-researcher/json (fetched 2026-08-29T07:50:21.581523+00:00, sha d89f0a2c4ba8)
- Data as of 2026-08-30T08:39:29.467469+00:00.