31 lines
1.4 KiB
Markdown
31 lines
1.4 KiB
Markdown
# Hermes
|
|
|
|
#entity
|
|
|
|
## Summary
|
|
|
|
An AI agent [[harness]] built **entirely around [[skills-as-memory|skills]]** — it not only uses skills but creates and curates them autonomously. Central to [[konstantin]]'s talk; also referenced by [[eugene]] among his tools.
|
|
|
|
## Current Understanding
|
|
|
|
Hermes is the concrete demonstration of "skills as memory": it auto-creates a skill when a task costs >5 tool calls, and runs a two-layer **curator** — pruning skills unused for 30 days (deactivate) / 90 days (archive) and consolidating small skills weekly so their short-descriptions don't eat context. Konstantin reports it grew from 56 → 100 skills and kept working — impossible with classic tools.
|
|
|
|
## Evidence
|
|
|
|
- Konstantin's talk: auto-improvement mechanism, curator, Telegram access to shared git skills — [[2026-07-14-skills-based-on-git]].
|
|
- Eugene lists it among his harness tools ("open clock, Hermes, paperclip") — [[2026-07-14-sebastian-eugene-interview]].
|
|
|
|
## Related Pages
|
|
|
|
- Entity: [[konstantin]], [[eugene]]
|
|
- Concepts: [[skills-as-memory]], [[harness]], [[agentic-loops]], [[context-as-scarce-resource]]
|
|
- Related tools: [[claude-code]], OpenClaude, Codex CLI
|
|
|
|
## Contradictions / Uncertainty
|
|
|
|
- The curator thresholds are Hermes-specific heuristics, not validated standards. Status: tentative.
|
|
|
|
## Next Questions
|
|
|
|
- How do Hermes' auto-consolidation decisions avoid merging skills that should stay distinct?
|