Skip to content

SimonsTang/hermes-learning-loop

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

🧬 Hermes Learning Loop

AI Agent OpenClaw Skill MIT License Nous Research

Experience-driven continuous evolution for AI agents — turning every interaction into a lasting improvement.

经验 → 技能 → 改进 → 沉淀 — The complete evolution loop for AI agents.

Adapted from Hermes Agent (Nous Research), localized for OpenClaw.

What It Does

Mechanism Description
Auto Retrospective After complex tasks, automatically review and extract reusable patterns
Three-Layer Memory Instant / Working / Experience / Session retrieval — structured knowledge layers
Error-Driven Improvement When corrected, immediately update related knowledge (inspired by KEPA)
Skill Audit Cycle Periodic review of accumulated experience → upgrade to formal Skills
Progressive Disclosure Load only what's needed, when it's needed — save tokens

Why It Matters

Most AI agents repeat the same mistakes. Hermes Learning Loop breaks that cycle:

  • Agents learn from corrections — not just from scratch
  • Errors become permanent improvements — not forgotten after the session
  • Experience compounds — each task makes the next one better
  • No bloat — only meaningful knowledge is retained

Quick Start

# Via ClawHub (recommended)
clawhub install hermes-learning-loop

# Or manually
cp -r hermes-learning-loop/ ~/.openclaw/workspace/skills/

Then restart OpenClaw and the skill activates automatically.

Key Principles

  1. 不偷懒 — Complex tasks must be reviewed, no skipping
  2. 不造假 — Do not pretend to know what you have not learned
  3. 不囤积 — Timely distillation, do not let MEMORY.md bloat
  4. 不孤岛 — New knowledge must connect to existing knowledge
  5. 不过度 — Simple operations do not need to be captured

Comparison with Existing Skills

Skill Approach
self-learning Config file updates + learning record system
self-improving-agent-cn Error capture + best practice logging
hermes-learning-loop Experience distillation + skill audit + progressive loading

Tech Stack

  • Language: Python + Markdown
  • Platform: OpenClaw
  • Inspiration: Hermes Agent by Nous Research, KEPA error learning

Credits

License

MIT License — see LICENSE file.

About

🧬 Experience-driven continuous evolution skill for AI agents. Adapted from Hermes Agent (Nous Research) for OpenClaw.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors