Bergschloss/Refine-Cycle-for-Hermes-Agent

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_session_end hook.

By BergschlossAgentReference information

ORIGINAL REPOSITORY

GitHub activity

Bergschloss/Refine-Cycle-for-Hermes-Agent ↗

Stars: 43
Forks: 1
Open issues and PRs: 0
Repository size: ~75,794 KB
Default branch: main
Created: Aug 6, 2026
Repository updated: Oct 30, 2026
Last push: Oct 22, 2026
Language: Python
License: MIT

Topics ai-agent · continuous-learning · hermes-agent · hermes-plugin · nous-research · python · self-improving-agent

Repository-wide figures from GitHub, checked Nov 4, 2026. Stars are endorsements, not a Mega AI Hub quality rating. Repository size is GitHub’s estimate; a ZIP download may differ.

Resource information

Original repository: Bergschloss/Refine-Cycle-for-Hermes-Agent
Credit basis: GitHub repository owner or organization; individual authorship is not asserted
Publisher: Bergschloss
Upstream last modified: Oct 30, 2026
Official website: https://github.com/Bergschloss/Refine-Cycle-for-Hermes-Agent
Languages: Python
Access: Open original GitHub repository; publisher terms apply
Last checked: Nov 4, 2026
License: MIT
Last record update: Nov 4, 2026