A · leads
hermes-agent
92.9
264,096 stars · MIT
AI Agents
hermes-agent leads by 7.2 · clear
A · leads
92.9
264,096 stars · MIT
B
85.7
42,732 stars · GPL-3.0
hermes-agent versus openhuman is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. hermes-agent is written mainly in Python; openhuman is written mainly in Rust. The composite score is 92.9 for hermes-agent and 85.7 for openhuman.
hermes-agent has 264,096 GitHub stars to openhuman's 42,732, a gap of 221,364 (6.18×). Forks are 59,569 for hermes-agent and 4,220 for openhuman. On the log scale used inside this pair, adoption is 100 versus 85, and the fork community is 100 versus 76.
Push history: hermes-agent was last pushed on 17 November 2026 (0 days ago), and openhuman was last pushed on 16 November 2026 (1 day ago). Open issues stand at 53,403 for hermes-agent (0.202 per star) and 311 for openhuman (0.007 per star). Issue-health scores are 34 and 84; activity scores are 100 and 100.
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. openhuman is listed as GPL-3.0, which this catalog treats as a strong copyleft grant. Distributing a modified binary typically means offering the corresponding source of that program. License scores in this pair are 96 for hermes-agent and 64 for openhuman. This is a procurement signal, not legal advice.
In AI Agents, both hermes-agent (264,096 stars) and openhuman (42,732 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: hermes-agent is open source, openhuman is open source.
The lead is split. hermes-agent is furthest ahead on license flexibility (96 to 64), while openhuman is furthest ahead on issue health (84 to 34). Choose the dimension a rollout cannot compromise on.
hermes-agent finishes ahead at 92.9 against openhuman at 85.7, a 7.2 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 | hermes-agent | openhuman |
|---|---|---|
| GitHub stars | 264,096 | 42,732 |
| Forks | 59,569 | 4,220 |
| Open issues | 53,403 | 311 |
| Adoption | 100 | 85 |
| Activity | 100 | 100 |
| Community | 100 | 76 |
| Issue health | 34 | 84 |
| License | 96 | 64 |
| Self-hosting | 100 | 100 |
| Composite | 92.9 | 85.7 |
The agent that grows with you
The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
hermes-agent has more GitHub stars: 264,096 versus 42,732 for openhuman. The gap is 221,364 stars.
hermes-agent was pushed more recently: 17 November 2026 versus 16 November 2026 for openhuman. That is 1 days apart.
Yes. This catalog marks both hermes-agent and openhuman as self-hostable. Confirm each project's deploy docs before you plan a migration.
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. openhuman is listed as GPL-3.0, which this catalog treats as a strong copyleft grant. Distributing a modified binary typically means offering the corresponding source of that program. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
hermes-agent scores 92.9 and openhuman scores 85.7. This page calls that a clear lead for hermes-agent.