A · level
hermes-agent
92.9
264,096 stars · MIT
AI Agents
Too close to call · 92.9 to 92.6
A · level
92.9
264,096 stars · MIT
B · level
92.6
117,459 stars · MIT
hermes-agent versus taste-skill 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; taste-skill is written mainly in JavaScript. The composite score is 92.9 for hermes-agent and 92.6 for taste-skill.
hermes-agent has 264,096 GitHub stars to taste-skill's 117,459, a gap of 146,637 (2.25×). Forks are 59,569 for hermes-agent and 7,858 for taste-skill. On the log scale used inside this pair, adoption is 100 versus 94, and the fork community is 100 versus 82.
Push history: hermes-agent was last pushed on 17 November 2026 (0 days ago), and taste-skill was last pushed on 08 November 2026 (8 days ago). Open issues stand at 53,403 for hermes-agent (0.202 per star) and 10 for taste-skill (0.000 per star). Issue-health scores are 34 and 96; activity scores are 100 and 92.
Both hermes-agent and taste-skill 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 hermes-agent (264,096 stars) and taste-skill (117,459 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, taste-skill is open source.
The lead is split. hermes-agent is furthest ahead on fork community (100 to 82), while taste-skill is furthest ahead on issue health (96 to 34). Choose the dimension a rollout cannot compromise on.
Composite score: hermes-agent 92.9, taste-skill 92.6. The margin is under one point, so this page calls a tie. Use the dimension breakdown rather than the headline number.
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 | taste-skill |
|---|---|---|
| GitHub stars | 264,096 | 117,459 |
| Forks | 59,569 | 7,858 |
| Open issues | 53,403 | 10 |
| Adoption | 100 | 94 |
| Activity | 100 | 92 |
| Community | 100 | 82 |
| Issue health | 34 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 92.9 | 92.6 |
The agent that grows with you
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
hermes-agent has more GitHub stars: 264,096 versus 117,459 for taste-skill. The gap is 146,637 stars.
hermes-agent was pushed more recently: 17 November 2026 versus 08 November 2026 for taste-skill. That is 8 days apart.
Yes. This catalog marks both hermes-agent and taste-skill 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. taste-skill 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.
Neither tool clears a one-point margin. hermes-agent scores 92.9 and taste-skill scores 92.6.