A
agent-desktop
95.9
24,948 stars · Apache-2.0
Workflow Automation
gpt-researcher leads by 1.5 · narrow
A
95.9
24,948 stars · Apache-2.0
B · leads
97.4
30,757 stars · Apache-2.0
agent-desktop versus gpt-researcher is a Workflow Automation comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. agent-desktop is written mainly in Rust; gpt-researcher is written mainly in Python. The composite score is 95.9 for agent-desktop and 97.4 for gpt-researcher.
gpt-researcher has 30,757 GitHub stars to agent-desktop's 24,948, a gap of 5,809 (1.23×). Forks are 1,864 for agent-desktop and 4,236 for gpt-researcher. On the log scale used inside this pair, adoption is 98 versus 100, and the fork community is 90 versus 100.
Push history: agent-desktop was last pushed on 17 November 2026 (0 days ago), and gpt-researcher was last pushed on 12 November 2026 (4 days ago). Open issues stand at 260 for agent-desktop (0.010 per star) and 56 for gpt-researcher (0.002 per star). Issue-health scores are 84 and 96; activity scores are 100 and 92.
Both agent-desktop and gpt-researcher are listed as Apache-2.0. 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. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In Workflow Automation, both agent-desktop (24,948 stars) and gpt-researcher (30,757 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: agent-desktop is open source, gpt-researcher is open source.
The lead is split. agent-desktop is furthest ahead on recent activity (100 to 92), while gpt-researcher is furthest ahead on issue health (96 to 84). Choose the dimension a rollout cannot compromise on.
gpt-researcher finishes ahead at 97.4 against agent-desktop at 95.9, a 1.5 point narrow 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 | agent-desktop | gpt-researcher |
|---|---|---|
| GitHub stars | 24,948 | 30,757 |
| Forks | 1,864 | 4,236 |
| Open issues | 260 | 56 |
| Adoption | 98 | 100 |
| Activity | 100 | 92 |
| Community | 90 | 100 |
| Issue health | 84 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 95.9 | 97.4 |
Computer use CLI for AI agents
An autonomous agent that conducts deep research on any data using any LLM providers
gpt-researcher has more GitHub stars: 30,757 versus 24,948 for agent-desktop. The gap is 5,809 stars.
agent-desktop was pushed more recently: 17 November 2026 versus 12 November 2026 for gpt-researcher. That is 4 days apart.
Yes. This catalog marks both agent-desktop and gpt-researcher as self-hostable. Confirm each project's deploy docs before you plan a migration.
agent-desktop 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. 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. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
gpt-researcher scores 97.4 and agent-desktop scores 95.9. This page calls that a narrow lead for gpt-researcher.