teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 5 Projects Releases Packages Wiki Activity Actions 1
teleo-codex/agents/theseus/musings/research-hermes-agent-nous.md
m3taversal f1094c5e09 leo: add Hermes Agent research brief for Theseus overnight session 
- What: Research musing + queue entry for Hermes Agent by Nous Research
- Why: m3ta assigned deep dive, VPS Theseus picks up at 1am tonight
- Targets: 5 NEW claims + 2 enrichments across ai-alignment and collective-intelligence

Pentagon-Agent: Leo <D35C9237-A739-432E-A3DB-20D52D1577A9>
2026-04-05 19:35:11 +01:00

4.3 KiB
Raw Blame History

created status name description type research_question belief_targeted
2026-04-05 seed research-hermes-agent-nous Research brief — Hermes Agent by Nous Research for KB extraction. Assigned by m3ta via Leo. musing What does Hermes Agent's architecture reveal about agentic knowledge systems, and how does its skills/memory design relate to Agentic Taylorism and collective intelligence? Multiple — B3 (agent architectures), Agentic Taylorism claims, collective-agent-core

Hermes Agent by Nous Research — Research Brief

Assignment

From m3ta via Leo (2026-04-05). Deep dive on Hermes Agent for KB extraction to ai-alignment and foundations/collective-intelligence.

What It Is

Open-source, self-improving AI agent framework. MIT license. 26K+ GitHub stars. Fastest-growing agent framework in 2026.

Primary sources:

  • GitHub: NousResearch/hermes-agent (main repo)
  • Docs: hermes-agent.nousresearch.com/docs/
  • @Teknium on X (Nous Research founder, posts on memory/skills architecture)

Key Architecture (from Leo's initial research)

  1. 4-layer memory system:

    • Prompt memory (MEMORY.md — always loaded, persistent identity)
    • Session search (SQLite + FTS5 — conversation retrieval)
    • Skills/procedural (reusable markdown procedures, auto-generated)
    • Periodic nudge (autonomous memory evaluation)

  2. 7 pluggable memory providers: Honcho, OpenViking (ByteDance), Mem0, Hindsight, Holographic, RetainDB, ByteRover

  3. Skills = Taylor's instruction cards. When agent encounters a task with 5+ tool calls, it autonomously writes a skill file. Uses agentskills.io open standard. Community skills via ClawHub/LobeHub.

  4. Self-evolution repo (DSPy + GEPA): Auto-submits improvements as PRs for human review

  5. CamoFox: Firefox fork with C++ fingerprint spoofing for web browsing

  6. 6 terminal backends: local, Docker, SSH, Daytona, Singularity, Modal

  7. Gateway layer: Telegram, Discord, Slack, WhatsApp, Signal, Email

  8. Release velocity: 6 major releases in 22 days, 263 PRs merged in 6 days

Extraction Targets

NEW claims (ai-alignment):

  1. Self-improving agent architectures converge on skill extraction as the primary learning mechanism (Hermes skills, Voyager skills, SWE-agent learned tools — all independently discovered "write a procedure when you solve something hard")
  2. Agent self-evolution with human review gates is structurally equivalent to our governance model (DSPy + GEPA → auto-PR → human merge)
  3. Memory architecture for persistent agents converges on 3+ layer separation (prompt/session/procedural/long-term) — Hermes, Letta, and our codex all arrived here independently

NEW claims (foundations/collective-intelligence):

  1. Individual agent self-improvement (Hermes) is structurally different from collective knowledge accumulation (Teleo) — the former optimizes one agent's performance, the latter builds shared epistemic infrastructure
  2. Pluggable memory providers suggest memory is infrastructure not feature — validates separation of knowledge store from agent runtime

ENRICHMENT candidates:

  1. Enrich "Agentic Taylorism" claims — Hermes skills system is DIRECT evidence. Knowledge codification as markdown procedure files = Taylor's instruction cards. The agent writes the equivalent of a foreman's instruction card after completing a complex task.
  2. Enrich collective-agent-core — Hermes architecture confirms harness > model (same model, different harness = different capability). Connects to Stanford Meta-Harness finding (6x performance gap from harness alone).

What They DON'T Do (matters for our positioning)

  • No epistemic quality layer (no confidence levels, no evidence requirements)
  • No CI scoring or contribution attribution
  • No evaluator role — self-improvement without external review
  • No collective knowledge accumulation — individual optimization only
  • No divergence tracking or structured disagreement
  • No belief-claim cascade architecture

This is the gap between agent improvement and collective intelligence. Hermes optimizes the individual; we're building the collective.

Pre-Screening Notes

Check existing KB for overlap before extracting:

  • collective-agent-core.md — harness architecture claims
  • Agentic Taylorism claims in grand-strategy and ai-alignment
  • Any existing Nous Research or Hermes claims (likely none)