by Bergschloss · Codex Skill · ★ 42
Refine Cycle for Hermes Agent Your agent keeps repeating the same mistake. This makes it stop. Refine Cycle looks across recent sessions, finds those repeating problems, and saves one small lesson when the evidence is strong enough. Later, it checks whether the same problem came back. Cross-session by design. Hermes can learn from the conversation in front of it, but some problems return across different sessions: the same failed command, the same wrong assumption, the same workaround you have to explain twice.
| Stars | 42 |
| Forks | 1 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 70.8789741179948/100 |
| Last Updated | 2026-10-09 |
| Created | 2026-08-06 |
| Platforms | python |
| Est. Tokens | ~15k |
Explore other popular codex skill tools:
Refine-Cycle-for-Hermes-Agent is Self-improvement loop for Hermes Agent: reads its own trajectory, proposes and applies the smallest skill/memory edit (create/patch), journaled with rollback. /refine command, refine_run tool, on_sess. It is categorized as a Codex Skill with 42 GitHub stars.
Refine-Cycle-for-Hermes-Agent is primarily written in Python. It covers topics such as ai-agent, continuous-learning, hermes-agent.
You can find installation instructions and usage details in the Refine-Cycle-for-Hermes-Agent GitHub repository at github.com/Bergschloss/Refine-Cycle-for-Hermes-Agent. The project has 42 stars and 1 forks, indicating an active community.
Refine-Cycle-for-Hermes-Agent is released under the MIT license, making it free to use and modify according to the license terms.