Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

GPT Researcher vs Horizon

GPT Researcher (Assaf Elovic and contributors) and Horizon (Sheng Qiang) side by side on public data, as of Nov 20, 2026.

GPT Researcher has 2.1x the GitHub stars of Horizon (30.8K against 14.8K). GPT Researcher shipped 3 stable releases in the past 90 days.

Which should you choose?

Choose GPT Researcher if

  • you need to run local models
  • you want to use your own model API key
  • you want to switch between model providers (11 documented against 0)
  • you want subagents or several agents working in parallel

Choose Horizon if

  • you prefer the more widely used tool, with more docs and answers around (Gid Score 41 against 32)

Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.

Side-by-side numbers

Metric GPT ResearcherHorizon
Gid Score3241
Usage data as ofNov 19Nov 19
Rank by Gid Score#151#82
Downloads, last 7 days8,611—
Downloads, 7-day changedown 5.1%—
Downloads, 30-day changedown 10.8%—
VS Code installs——
Marketplace rating——
GitHub stars30.8K14.8K
Homebrew installs, 30 days——
Hacker News mentions, 30 days00
Latest stable release3.8.0 · 11d ago—
Stable releases, 90 days3—
Terminal-Bench (best run)——
PriceFree (OSS)Free (OSS)
LicenseApache-2.0MIT
First released—February 2026
InterfacesCLI, Web app, SDK, MCP server, Self-hosted—
Models——

A dash means there is no public data for that metric as of Nov 20, 2026.

Trends

GitHub starsrunning total
GPT ResearcherHorizon

GPT Researcher

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.

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

Latest release 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

Full GPT Researcher profile

Horizon

Self-hosted AI news radar: it collects items from your feeds and forums, filters and deduplicates them, and delivers a ranked daily briefing in English or Chinese with context and community discussion, by email, Feishu or WeChat.

Pricing: Open source under the MIT licence; check the website for any paid hosted plans.

Full Horizon profile

GPT Researcher vs Horizon: common questions

Which is more popular, GPT Researcher or Horizon?

Horizon has a Gid Score of 41 against 32 for GPT Researcher. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.

Do GPT Researcher and Horizon support local models?

GPT Researcher documents support for local models; Horizon's documentation does not.

Do GPT Researcher and Horizon support MCP servers?

GPT Researcher documents support for MCP servers; Horizon's documentation does not.