Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026

GPT Researcher by Assaf Elovic and contributors

An open-source agent that plans research, gathers and filters many web or local sources and writes a cited report, with support for multiple model providers.

AI research agents Open-source deep research agentOpen source · Apache-2.0Free to start

Use it in: CLI Web app API / SDK MCP server Self-hosted Works with: MCP Local models Own API key Multi-agent

Price
Free (OSS)
free and open source
Popularity
#6 in Research
Gid Score 32 / 100 · #155 of 255 ranked AI agents
Trend
Slowing down
downloads down 13.2% over 30 days · up 6.3% last week
Development
Updated recently
latest 3.8.0, 12d ago
Community
30.8K GitHub stars
9,793 package downloads a week

Usage data: latest readings Nov 19 to Nov 21, 2026, last checked Nov 21, 06:30 UTC. Date of each number

What GPT Researcher does

GPT Researcher is an open-source deep research agent from Assaf Elovic and contributors. You use it through a command-line tool, a web app, an SDK, MCP server and self-hosted. Its documentation covers MCP servers, subagents or parallel agents, your own API key and local models. It can run models from OpenAI, Anthropic, Azure, Google, Mistral and xAI and others. It is used from Python. It is free and open source (Apache-2.0); you pay only for the models it calls.

Key facts

MakerAssaf Elovic and contributors
TypeOpen-source deep research agent
LicenseApache-2.0
InterfacesCLI, Web app, SDK, MCP server, Self-hosted
Main languagePython
Open issues and PRs75

Pricing

Free open-source software; users pay their own model and search API costs.

Source: official pricing page, checked Oct 6, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (Apache-2.0)
  • Where you use itCLI, Web app, SDK, MCP server, Self-hosted
  • Supports MCP?Yes
  • Model providersopenai, anthropic, azure, google, mistral, xai, deepseek, qwen, amazon, openrouter, any OpenAI-compatible, local
  • Subagents / multi-agent?Yes
  • Feature comparisonAll agents
  • Closest alternativeBettaFish · all alternatives

What's new in GPT Researcher: November 2026 so far

Full monthly summary

November brought upgraded AI models, improved reliability with timeout handling, and expanded deployment options. Several features for multi-agent workflows and deep research were refined.

Action needed: Default writer model changed to openai:gpt-6-sol; set SMART_LLM environment variable to retain the previous model.
  • Default writer model upgraded to GPT-6 Sol for better quality.
  • LLM calls now timeout after 300 seconds with clear errors instead of hanging indefinitely.
  • Report generation now fails explicitly when all LLM attempts fail, preventing empty results.
  • Prebuilt Docker images available for both AMD64 and ARM64 architectures.

1 release this month · summarised from the official release notes · all months

Get started with GPT Researcher

npmnpm install -g gpt-researcher
PyPIpip install gpt-researcher

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Compare GPT Researcher with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
71
BettaFish666ghj (community project)
432/4 — — — 42.8K+11/day 3.0.011mo ago Free (OSS)
72
Paper Orchestra NewGoogle Research
432/4 — — — 5,493+757/day — Free (OSS)
84
Autoresearchkarpathy
41 — — — 100K+52/day — Free (OSS)
88
HorizonSheng Qiang
402/4 — — — 14.9K+112/day — Free (OSS)
93
DexterVirat Singh
402/4 — — — 28K+22/day 1.1.059d ago Free (OSS)
205
KosmosEdison Scientific
242/4 13.1K up 29.0% down 9.3% — — Free + $200/mo

Head to head: GPT Researcher vs Autoresearch · GPT Researcher vs BettaFish · GPT Researcher vs Consensus · GPT Researcher vs Dexter · GPT Researcher vs Elicit · GPT Researcher vs Horizon · GPT Researcher vs Kosmos · GPT Researcher vs SciSpace Agent

Tools used with GPT Researcher

All tools

What 76 public GitHub projects that depend on GPT Researcher use with it, from their dependency files.

  1. python-dotenv81.6%
  2. LangChain78.9%
  3. Pydantic71.1%
  4. FastAPI67.1%
  5. OpenAI Python Library65.8%
  6. Requests65.8%
  7. Uvicorn63.2%
  8. Beautiful Soup61.8%
  9. python-multipart59.2%
  10. PyMuPDF57.9%

Used far more often here than in AI-built projects overall: what sets GPT Researcher projects apart.

  1. htmldocx53.9% · 3374.4×
  2. pydyf26.3% · 1646.1×
  3. lxml-html-clean50.0% · 1563.8×
  4. markdown226.3% · 823.0×
  5. json5 (Python)48.7% · 507.5×
  6. arxiv55.3% · 314.2×
  7. Unstructured52.6% · 299.3×
  8. Mistune53.9% · 281.2×

Ratings from people who use GPT Researcher

No ratings yet. Used GPT Researcher? Rate it and say what it is good and bad at.

GPT Researcher news

All AI agent news

  1. Release GitHub Releases

    GPT Researcher 3.8.0 released

    Default writer model: SMART_LLM is now openai:gpt-6-sol (was openai:gpt-5.4). Set SMART_LLM to keep the previous model.; LLM idle timeout: an LLM call that sends nothing for 300 seconds now fails with a clear error instead of hanging the run. Tune it with…

What changed: recent GPT Researcher releases

3 stable releases in the last 90 days · Monthly summary · Full changelog

3.8.0
  • Default writer model: SMART_LLM is now openai:gpt-6-sol (was openai:gpt-5.4). Set SMART_LLM to keep the previous model.
  • LLM idle timeout: an LLM call that sends nothing for 300 seconds now fails with a clear error instead of hanging the run. Tune it with LLM_TIMEOUT (0 disables it).
  • generate_report now raises when every LLM attempt fails, instead of returning an empty report.
  • Prebuilt Docker images for linux/amd64 and linux/arm64 on GHCR: ghcr.io/assafelovic/gpt-researcher and ghcr.io/assafelovic/gpt-researcher-frontend-nextjs, tagged with the version and latest
  • Research observer: an optional lifecycle observer for integrations that want structured progress events
  • MiniMax regional providers and Flash defaults, a configurable TypeSafe base URL, and Deploy on Render with a render.yaml blueprint
3.7.0
  • Benchmark, method and code: evals/context_filter/
  • Python 3.12+ is now required.
  • Default context filter: without a TypeSafe key, the default is now keyword ranking instead of
  • Retriever plugins: ship a search provider as its own package via the gpt_researcher.retrievers entry point
  • Fixed the frontend WebSocket opening a second connection on a new research run
  • Multi-agent sections no longer repeat each other's content
Earlier releases
3.6.1
  • fix: restore main, add CI, and land 97 queued PRs
  • fix(readme): restore broken star history chart
  • docs: document scholarly retriever configuration
  • chore(deps): update python-pptx requirement from >=1.0.0 to >=1.0.2
  • chore: remove the dead poetry dependency block, test the declared Python floor
  • Add agent observability with Monocle
3.6.0
  • security: sanitize untrusted content, add SECURITY.md, pin brotli
  • Fix silently dropped token limits, real usage-based cost tracking, and research pipeline robustness
  • Add Deep Agents example: GPT Researcher as the research engine in a LangChain deep agent
  • Resolve post-merge conflicts: 4 retriever/context fixes (supersedes #1895-1898)
  • Retriever hardening: 20 guard fixes against malformed results (supersedes #1837…
  • Scraper robustness: 6 fixes (title/PDF-detection/temp-file/dimensions) (supersedes #1824…
3.5.1
  • fix: add MAX_REVISIONS guard to prevent infinite revision loop
  • Improve SimpleQA eval observability with structured logging and latency metadata
  • feat(retrievers): add Brave Search support
  • Abstain instead of fabricating a report when no content was gathered
  • fix(deep-research): keep oversized context from collapsing to empty
  • feat(retrievers): add fastCRW search retriever
3.5.0
  • feat: add ModelsLab image generation provider
  • fix: NameError when STRATEGIC_LLM lacks colon separator
  • fix: properly resolve report_type imports in websocket_manager and re…
  • Fix: resolve unhashable dict error in detailed report context deduplication
  • Add Codex CLI plugin manifest
  • fix: eliminate process-level env pollution from MCP retriever setup

GPT Researcher prices over time

Token prices of OpenAI modelsnewest OpenAI model in each family, output price per 1M tokens
OpenAI FlagshipOpenAI Mini

GPT Researcher popularity and usage data

GPT Researcher was downloaded 9,793 times from npm and PyPI in the week ending Nov 19, 2026, up 6.3% on the week before and down 13.2% over the last 30 days compared with the 30 before. The GitHub repository has 30.8K stars, 619 of them added in the last 30 days. The latest stable release is 3.8.0, published Nov 9, 2026; there was 1 stable release in the past 30 days.

Downloads per daynpm and PyPI, 7-day average 1,399/day
GitHub starsrunning total 30.8K
Website rankTranco list; a lower rank means more traffic #1,563,103

Download the raw daily series: gpt-researcher.csv

Gid Score breakdown

Adoption22
Community62
Attention—
Momentum37

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 19, 2026Nov 21, 06:24 UTC
GitHub starsNov 21, 2026Nov 21, 06:26 UTC
Website rank (Tranco)Nov 20, 2026Nov 21, 06:30 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

GPT Researcher FAQ

How much does GPT Researcher cost?

Free open-source software; users pay their own model and search API costs.

Is GPT Researcher open source?

Yes. GPT Researcher is open source, released under the Apache-2.0 license.

How popular is GPT Researcher?

GPT Researcher was downloaded 9,793 times from npm and PyPI in the week ending Nov 19, 2026, up 6.3% on the week before and down 13.2% over the last 30 days compared with the 30 before. The GitHub repository has 30.8K stars, 619 of them added in the last 30 days. The latest stable release is 3.8.0, published Nov 9, 2026; there was 1 stable release in the past 30 days.

What is the latest version of GPT Researcher?

The latest stable release we track is 3.8.0, published on Nov 9, 2026.

What are the alternatives to GPT Researcher?

The closest alternatives in the same category by Gid Score are BettaFish, Paper Orchestra, Autoresearch, Horizon.

For the makers of GPT Researcher badges, corrections

Add a live badge to your README or site:

AgentGid: #6 in Research Gid Score: 32/100 downloads: 9,793/week ▼13% 30d

[![AgentGid: #6 in Research](https://agentgid.com/badges/gpt-researcher-rank.svg)](https://agentgid.com/agents/gpt-researcher/)
[![Gid Score: 32/100](https://agentgid.com/badges/gpt-researcher-score.svg)](https://agentgid.com/agents/gpt-researcher/)
[![downloads: 9,793/week ▼13% 30d](https://agentgid.com/badges/gpt-researcher-downloads.svg)](https://agentgid.com/agents/gpt-researcher/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

npm: gpt-researcher. PyPI: gpt-researcher. GitHub: assafelovic/gpt-researcher. Site rank: gptr.dev on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: github.com, docs.gptr.dev.