Autoresearch vs GPT Researcher
Autoresearch (karpathy) and GPT Researcher (Assaf Elovic and contributors) side by side on public data, as of Nov 20, 2026.
Autoresearch has 3.3x the GitHub stars of GPT Researcher (100K against 30.8K). GPT Researcher shipped 3 stable releases in the past 90 days.
Which should you choose?
Choose Autoresearch if
- you prefer the more widely used tool, with more docs and answers around (Gid Score 40 against 32)
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 work in the terminal
- you want subagents or several agents working in parallel
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 | Autoresearch | GPT Researcher |
|---|---|---|
| Gid Score | 40 | 32 |
| Usage data as of | Nov 19 | Nov 19 |
| Rank by Gid Score | #85 | #151 |
| Downloads, last 7 days | — | 8,611 |
| Downloads, 7-day change | — | down 5.1% |
| Downloads, 30-day change | — | down 10.8% |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 100K | 30.8K |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 15 | 0 |
| Latest stable release | — | 3.8.0 · 11d ago |
| Stable releases, 90 days | — | 3 |
| Terminal-Bench (best run) | — | — |
| Price | Free (OSS) | Free (OSS) |
| License | MIT | Apache-2.0 |
| First released | March 2026 | — |
| Interfaces | Self-hosted | CLI, 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
Autoresearch
Andrej Karpathy's experiment in letting an AI agent do ML research on its own: the agent edits a small GPT training script, trains for a fixed five minutes on one GPU, keeps a change only if validation bits per byte improve, and repeats overnight.
Pricing: Open source under the MIT licence; it needs your own NVIDIA GPU (tested on an H100) and a coding agent you point at program.md.
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
Autoresearch vs GPT Researcher: common questions
Which is more popular, Autoresearch or GPT Researcher?
Autoresearch has a Gid Score of 40 against 32 for GPT Researcher. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.
Do Autoresearch and GPT Researcher support local models?
GPT Researcher documents support for local models; Autoresearch's documentation does not.
Do Autoresearch and GPT Researcher support MCP servers?
GPT Researcher documents support for MCP servers; Autoresearch's documentation does not.