A
goose
90.9
56,716 stars · Apache-2.0
AI Agents
hermes-agent leads by 2.0 · narrow
A
90.9
56,716 stars · Apache-2.0
B · leads
92.9
264,096 stars · MIT
goose versus hermes-agent is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. goose is written mainly in Rust; hermes-agent is written mainly in Python. The composite score is 90.9 for goose and 92.9 for hermes-agent.
hermes-agent has 264,096 GitHub stars to goose's 56,716, a gap of 207,380 (4.66×). Forks are 6,608 for goose and 59,569 for hermes-agent. On the log scale used inside this pair, adoption is 88 versus 100, and the fork community is 80 versus 100.
Push history: goose was last pushed on 17 November 2026 (0 days ago), and hermes-agent was last pushed on 17 November 2026 (0 days ago). Open issues stand at 530 for goose (0.009 per star) and 53,403 for hermes-agent (0.202 per star). Issue-health scores are 84 and 34; activity scores are 100 and 100.
goose 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. hermes-agent is listed as MIT, 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. License scores in this pair are 96 for goose and 96 for hermes-agent. This is a procurement signal, not legal advice.
In AI Agents, both goose (56,716 stars) and hermes-agent (264,096 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: goose is open source, hermes-agent is open source.
The lead is split. goose is furthest ahead on issue health (84 to 34), while hermes-agent is furthest ahead on fork community (100 to 80). Choose the dimension a rollout cannot compromise on.
hermes-agent finishes ahead at 92.9 against goose at 90.9, a 2.0 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 | goose | hermes-agent |
|---|---|---|
| GitHub stars | 56,716 | 264,096 |
| Forks | 6,608 | 59,569 |
| Open issues | 530 | 53,403 |
| Adoption | 88 | 100 |
| Activity | 100 | 100 |
| Community | 80 | 100 |
| Issue health | 84 | 34 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 90.9 | 92.9 |
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
The agent that grows with you
hermes-agent has more GitHub stars: 264,096 versus 56,716 for goose. The gap is 207,380 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both goose and hermes-agent as self-hostable. Confirm each project's deploy docs before you plan a migration.
goose 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. hermes-agent is listed as MIT, 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.
hermes-agent scores 92.9 and goose scores 90.9. This page calls that a narrow lead for hermes-agent.