Hermes Agent

Recent Updates & the Complete Feature Guide

Dr. Farshid Pirahansiah • AI & Computer Vision Engineer
Every feature, with a runnable example — pirahansiah.com

Recent Updates (2026)

Install: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

Setup & Configuration

# Install (uv + python venv + launcher)
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

# Interactive setup wizard + provider picker
hermes setup          # model | tts | terminal | gateway | tools
hermes model           # pick provider + model interactively
hermes doctor          # dependency + config health check
hermes status --all    # component status

# Config is set via CLI (never hand-edit the YAML)
hermes config set model.default Qwen3.5-4B-OptiQ-4bit

Providers & Model Aliases

# User model aliases (resolved before built-ins)
hermes config set model.aliases.cheap gemini/gemini-2.0-flash-lite
# In chat: /model cheap   (session) or --global (persist)

Skills — Procedural Memory

skill_manage create cv-yolo \
  --cat cv
# writes SKILL.md → loads on match

New Skills Installed & Validated 2026-09-06

Installed via hermes skills install / URL, scanned, and verified (valid SKILL.md frontmatter, enabled).

Blocked by security scan (dangerous verdict, --force cannot override): codebase-memory-mcp, openmontage, composio, claude-mem, rlaope/oh-my-hermes. Plugin-only (not flat SKILL.md): witt3rd/oh-my-hermes, agent37/minions. Use curated repo paths or audit before install.

Persistent Memory

Multi-Agent Orchestration

# Spawn isolated subagents in parallel (each = own context + tools)
delegate_task(tasks=[
  {"goal": "Fine-tune YOLOv11 on /data/coco-subset, export ONNX",
   "context": "epochs=50, device=cuda:0"},
  {"goal": "Run SAM2 over /data/video/*.mp4, emit mask JSON"},
  {"goal": "Profile GPU memory under 50 streams with py-spy"}
])
# Coordinator merges verified summaries — no manual glue.

Also: hermes moa (Mixture-of-Agents), hermes kanban (work-queue), --worktree (isolated checkouts).

Bot Mode — Named Agents

hermes bot create cv-alerts \
  --platform telegram \
  --group "CV War Room"
# bot runs autonomously, posts results

Messaging & Group Bots (21+ Platforms)

hermes gateway run          # launch messaging gateway
hermes auth add telegram     # OAuth / token once
hermes send "Eval done: mAP 0.94" --platform telegram

Cron & Scheduling

# Nightly CV eval at 02:00, deliver to Telegram
hermes cron create "0 2 * * *" \
  --name "Nightly CV Eval" \
  --script nightly_eval.py \
  --deliver telegram

# Human-readable schedules also work
hermes cron create "every 2h" --name "Health Ping" --no-agent --script ping.sh
hermes cron list | pause | resume | run ID

Survives reboots; runs headless; notifies on completion or failure.

Research Assistants

Lit sweep → code reproduce → experiment → draft, all agent-driven.

Profiling & Debugging

Artifact Management

Surfaces & Power Features

WebhooksACP / IDEPetsSkinsTTS/STTComputer UseImport Claude/Codex

Complete Feature Catalog

Autonomous tool-callingPersistent memorySkill system (~90+~60)Multi-agent (delegate)MoAKanban queueGit worktreesCheckpoints/rollback35+ providersLocal LLM (oMLX/llama.cpp)Model aliasesFallback poolsBot mode21+ messaging platformsGroup botsCron schedulingWebhooksMCP serversResearch: ArXiv/BibTeXGrounded citationsJupyter live kernelProfiling (GPU/py-spy)Systematic debuggingArtifact lineageHF pushDesktop GUIWeb dashboardInk TUILocal proxyProfiles & distributionsSecrets (1PW/Bitwarden)Managed scopeSkins & petsVoice TTS/STTComputer useACP / IDEImport Claude/CodexEgress proxy

→ Every feature shown above has a working example in this deck.

One Agent. Every Workflow.

pirahansiah.com/farshid/content/research-tools.md

Validated Skills Library installed & scanned

All installed via hermes skills install, security-scanned, and verified (valid SKILL.md, enabled).

Command Cheat Sheet DESK · CLI · MSG · SHELL

Everyday commands — Desktop, CLI chat, messaging, shell. (Verified vs current Hermes source, Sep 2026.)

Hermes as a Dots (OpenAI) Replacement

Dots = OpenAI's always-on agent (GPT-6 Astra, cloud, $100/mo). Hermes rebuilds the same behaviour on your machine, any model.

# 1. Install
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup   # wizard: model, provider, terminal, gateway, tools

# 2. Point it at OpenAI (or any model)
hermes auth add openai-codex   # OAuth, or OPENAI_API_KEY in ~/.hermes/.env
hermes model        # pick model + provider

# 3. Dots-style approval gate
hermes config set approvals.mode smart   # ask only when risky

GPT-6 Astra is Dots' own hosted model, not a public endpoint — run whatever OpenAI model your key can reach instead.

Prompt It Like Dots — Goals, Background, Always-On

# Dots: "every morning, check the market, tell me in Slack"
hermes cron create '0 8 * * *' "check overnight news and message me on Slack if material"

# Dots: "book this trip, ask before you spend"
/goal "book the SF trip within a $2,500 budget" + approvals.mode manual

Thank You

Hermes Agent — Updates & Complete Feature Guide

All Presentations • Notes & Guides • GitHub • Official Docs