A · leads
AutoGPT
97.9
188,072 stars · MIT
AI Agents
AutoGPT leads by 5.0 · narrow
A · leads
97.9
188,072 stars · MIT
B
92.9
264,096 stars · MIT
AutoGPT 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. Both projects are written mainly in Python. The composite score is 97.9 for AutoGPT and 92.9 for hermes-agent.
hermes-agent has 264,096 GitHub stars to AutoGPT's 188,072, a gap of 76,024 (1.40×). Forks are 45,866 for AutoGPT and 59,569 for hermes-agent. On the log scale used inside this pair, adoption is 97 versus 100, and the fork community is 98 versus 100.
Push history: AutoGPT 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 676 for AutoGPT (0.004 per star) and 53,403 for hermes-agent (0.202 per star). Issue-health scores are 96 and 34; activity scores are 100 and 100.
Both AutoGPT and hermes-agent are listed as MIT. 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 AI Agents, both AutoGPT (188,072 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: AutoGPT is open source, hermes-agent is open source.
The lead is split. AutoGPT is furthest ahead on issue health (96 to 34), while hermes-agent is furthest ahead on adoption (100 to 97). Choose the dimension a rollout cannot compromise on.
AutoGPT finishes ahead at 97.9 against hermes-agent at 92.9, a 5.0 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 | AutoGPT | hermes-agent |
|---|---|---|
| GitHub stars | 188,072 | 264,096 |
| Forks | 45,866 | 59,569 |
| Open issues | 676 | 53,403 |
| Adoption | 97 | 100 |
| Activity | 100 | 100 |
| Community | 98 | 100 |
| Issue health | 96 | 34 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 97.9 | 92.9 |
AutoGPT is an experimental agent project that tries to break a goal into tool-using steps. It is a reference point in autonomous-agent work more than a finished business suite.
The agent that grows with you
hermes-agent has more GitHub stars: 264,096 versus 188,072 for AutoGPT. The gap is 76,024 stars.
Both were last pushed on 17 November 2026.
Yes. This catalog marks both AutoGPT and hermes-agent as self-hostable. Confirm each project's deploy docs before you plan a migration.
AutoGPT 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. 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.
AutoGPT scores 97.9 and hermes-agent scores 92.9. This page calls that a narrow lead for AutoGPT.