TEAM ATTENTION IS A STUDIO /// WE DROP · WE DOCUMENT · WE REPEAT /// NOTHING IS SACRED /// EVENTS / PROTOCOLS / ESSAYS / VIDEOS / PROGRAMS /// EST. 2024 · SEOUL ↔ SAN FRANCISCO /// NO VC · DROP = REVENUETEAM ATTENTION IS A STUDIO /// WE DROP · WE DOCUMENT · WE REPEAT /// NOTHING IS SACRED /// EVENTS / PROTOCOLS / ESSAYS / VIDEOS / PROGRAMS /// EST. 2024 · SEOUL ↔ SAN FRANCISCO /// NO VC · DROP = REVENUETEAM ATTENTION IS A STUDIO /// WE DROP · WE DOCUMENT · WE REPEAT /// NOTHING IS SACRED /// EVENTS / PROTOCOLS / ESSAYS / VIDEOS / PROGRAMS /// EST. 2024 · SEOUL ↔ SAN FRANCISCO /// NO VC · DROP = REVENUETEAM ATTENTION IS A STUDIO /// WE DROP · WE DOCUMENT · WE REPEAT /// NOTHING IS SACRED /// EVENTS / PROTOCOLS / ESSAYS / VIDEOS / PROGRAMS /// EST. 2024 · SEOUL ↔ SAN FRANCISCO /// NO VC · DROP = REVENUE
TEAMATTENTION/DROPS
← Back All Drops/Drop #008/ Content/APR 12 2026/Archived

Hermes Agent

Essay Drop
Manifesto

Agents generate Skills. The next harness layer.

About

Nous Research's Hermes Agent implements a closed learning loop where agents generate and improve their own skills. The old paradigm: humans write skills, agents execute. Hermes: agents do complex work, auto-generate reusable skills, and self-improve with each repetition. The author of skill generation has moved from human to AI.

Highlights
  • 01Agents make skills themselves and fix them as they run
  • 02FTS5-based session search for past-conversation recall
  • 03Honcho for accumulating user models
  • 0415 channels unified behind one gateway (Telegram/Slack/Discord/…)
  • 056 backends: local, Docker, SSH, Daytona, …
  • 06Modal + Daytona serverless hibernation — idle cost 0
  • 07Only agent with closed learning loop built-in
  • 08Who writes skills shifted: human → agent, human sets direction only
Key Concepts
Closed Learning Loop

Agent runs tasks, creates reusable skills, and improves them on every reuse — a self-tuning feedback loop.

Skill Generation

Reusable procedures generated automatically by the agent after complex tasks. Previously written by humans.

Session Recall

FTS5-based retrieval of past conversations and context to improve agent decisions.

Quotes

Agents make skills themselves and fix them as they run

Goobong Jeong

The big shift is who authors the skills

Goobong Jeong
Previous Drop
#007 Managed vs IronClaw
Next Drop
#009 Thin Harness / Fat Skills