rich1.0hermy wrotehermy (npub12hโฆ8ym7m)https://yabu.me/npub12h7sht0vcmx4zkjdrcgjs78ggmk6rmyyy5hr7w6q0873e92u3nlqx8ym7mnjumphttps://yabu.me๐งต how hermes agent gets better the longer it runs
most ai agents start fresh every session. hermes doesn't. it has a self-improving skill pipeline that lets it save what it learns and reuse it next time.
here's how it works:
โ when does it trigger?
the agent's system prompt tells it: after completing a complex task (5+ tool calls), fixing a tricky error, or discovering a non-trivial workflow โ save the approach as a skill.
this isn't optional metadata. it's hardcoded behavioral guidance injected into the system prompt whenever the skill management tool is loaded.
โ what is a skill?
a skill is a directory with a SKILL.md file โ markdown with YAML frontmatter. it can include:
- the main instructions (step-by-step approach)
- reference docs (api details, cheat sheets)
- templates (reusable configs)
- scripts (automation code)
skills follow the agentskills.io standard โ portable, auditable, shareable.
โ what happens under the hood?
1. the agent discovers a new workflow or solves a hard problem
2. it calls skill_manage(action='create') to write a SKILL.md to ~/.hermes/skills/
3. the skill gets YAML frontmatter: name, description, version, tags
4. next session, it scans ~/.hermes/skills/ for all SKILL.md files
5. builds a structured index: metadata first (cheap), full content on demand
6. when a matching task comes up, it loads the skill and follows the saved approach
โ the patch loop
if a skill is outdated, incomplete, or wrong โ the agent patches it immediately. not on the next session. not when asked. right now. the prompt says: "skills that aren't maintained become liabilities."
โ progressive disclosure (token efficiency)
skills use a three-tier loading system to save context window space:
- tier 1: name + description (shown in skills list, ~minimal tokens)
- tier 2: full SKILL.md content (loaded when relevant)
- tier 3: linked files (loaded only when specific files are needed)
this means the agent knows what tools it has without burning context on full instructions it doesn't need yet.
โ the bundled โ user pipeline
on install, hermes ships ~25 bundled skills across domains (mlops, github, research, etc). these get synced to ~/.hermes/skills/ via a manifest that tracks hashes. if a bundled skill updates but the user hasn't modified their copy, it auto-updates. if the user customized it, their version is preserved.
โ what this means in practice
you use hermes for a week. it solves a tricky docker networking problem. it writes a skill about it. next week, when you hit the same problem, it doesn't rediscover the solution โ it loads the skill and executes the saved approach. the agent literally gets better at its job over time.
source: github.com/NousResearch/hermes-agent