A · leads
gpt-researcher
97.4
30,757 stars · Apache-2.0
Workflow Automation
gpt-researcher leads by 10.0 · clear
A · leads
97.4
30,757 stars · Apache-2.0
B
87.4
18,618 stars · AGPL-3.0
gpt-researcher versus Windmill is a Workflow Automation comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. gpt-researcher is written mainly in Python; Windmill is written mainly in Rust. The composite score is 97.4 for gpt-researcher and 87.4 for Windmill.
gpt-researcher has 30,757 GitHub stars to Windmill's 18,618, a gap of 12,139 (1.65×). Forks are 4,236 for gpt-researcher and 1,165 for Windmill. On the log scale used inside this pair, adoption is 100 versus 95, and the fork community is 100 versus 85.
Push history: gpt-researcher was last pushed on 12 November 2026 (4 days ago), and Windmill was last pushed on 17 November 2026 (0 days ago). Open issues stand at 56 for gpt-researcher (0.002 per star) and 889 for Windmill (0.048 per star). Issue-health scores are 96 and 70; activity scores are 92 and 100.
gpt-researcher is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Windmill is listed as AGPL-3.0, which this catalog treats as a network copyleft grant. Letting users interact with a modified copy over a network can trigger a duty to offer them the corresponding source. License scores in this pair are 96 for gpt-researcher and 52 for Windmill. This is a procurement signal, not legal advice.
In Workflow Automation, both gpt-researcher (30,757 stars) and Windmill (18,618 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: gpt-researcher is open source, Windmill is open source.
The lead is split. gpt-researcher is furthest ahead on license flexibility (96 to 52), while Windmill is furthest ahead on recent activity (100 to 92). Choose the dimension a rollout cannot compromise on.
gpt-researcher finishes ahead at 97.4 against Windmill at 87.4, a 10.0 point clear margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | gpt-researcher | Windmill |
|---|---|---|
| GitHub stars | 30,757 | 18,618 |
| Forks | 4,236 | 1,165 |
| Open issues | 56 | 889 |
| Adoption | 100 | 95 |
| Activity | 92 | 100 |
| Community | 100 | 85 |
| Issue health | 96 | 70 |
| License | 96 | 52 |
| Self-hosting | 100 | 100 |
| Composite | 97.4 | 87.4 |
An autonomous agent that conducts deep research on any data using any LLM providers
Windmill runs scripts and approval flows as internal apps, with workers you can scale. It is used by teams that want automation closer to a developer platform than a no-code zap.
gpt-researcher has more GitHub stars: 30,757 versus 18,618 for Windmill. The gap is 12,139 stars.
Windmill was pushed more recently: 17 November 2026 versus 12 November 2026 for gpt-researcher. That is 4 days apart.
Yes. This catalog marks both gpt-researcher and Windmill as self-hostable. Confirm each project's deploy docs before you plan a migration.
gpt-researcher is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Windmill is listed as AGPL-3.0, which this catalog treats as a network copyleft grant. Letting users interact with a modified copy over a network can trigger a duty to offer them the corresponding source. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
gpt-researcher scores 97.4 and Windmill scores 87.4. This page calls that a clear lead for gpt-researcher.