{"success": true, "name": "hermes-agent", "description": "Configure, extend, or contribute to Hermes Agent.", "tags": ["hermes", "setup", "configuration", "multi-agent", "spawning", "cli", "gateway", "development"], "related_skills": ["claude-code", "codex", "opencode"], "content": "---\nname: hermes-agent\ndescription: \"Configure, extend, or contribute to Hermes Agent.\"\nversion: 2.0.0\nauthor: Hermes Agent + Teknium\nlicense: MIT\nmetadata:\n hermes:\n tags: [hermes, setup, configuration, multi-agent, spawning, cli, gateway, development]\n homepage: https://github.com/NousResearch/hermes-agent\n related_skills: [claude-code, codex, opencode]\n---\n\n# Hermes Agent\n\nHermes Agent is an open-source AI agent framework by Nous Research that runs in your terminal, messaging platforms, and IDEs. It belongs to the same category as Claude Code (Anthropic), Codex (OpenAI), and OpenClaw — autonomous coding and task-execution agents that use tool calling to interact with your system. Hermes works with any LLM provider (OpenRouter, Anthropic, OpenAI, DeepSeek, local models, and 15+ others) and runs on Linux, macOS, and WSL.\n\nWhat makes Hermes different:\n\n- **Self-improving through skills** — Hermes learns from experience by saving reusable procedures as skills. When it solves a complex problem, discovers a workflow, or gets corrected, it can persist that knowledge as a skill document that loads into future sessions. Skills accumulate over time, making the agent better at your specific tasks and environment.\n- **Persistent memory across sessions** — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends (built-in, Honcho, Mem0, and more) let you choose how memory works.\n- **Multi-platform gateway** — the same agent runs on Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and 10+ other platforms with full tool access, not just chat.\n- **Provider-agnostic** — swap models and providers mid-workflow without changing anything else. Credential pools rotate across multiple API keys automatically.\n- **Profiles** — run multiple independent Hermes instances with isolated configs, sessions, skills, and memory.\n- **Extensible** — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, and the full Python ecosystem.\n\nPeople use Hermes for software development, research, system administration, data analysis, content creation, home automation, and anything else that benefits from an AI agent with persistent context and full system access.\n\n**This skill helps you work with Hermes Agent effectively** — setting it up, configuring features, spawning additional agent instances, troubleshooting issues, finding the right commands and settings, and understanding how the system works when you need to extend or contribute to it.\n\n**Docs:** https://hermes-agent.nousresearch.com/docs/\n\n## Quick Start\n\n```bash\n# Install\ncurl -fsSL https://raw.githubusercontent.com/NousResea
... [33772 chars total, truncated]
2026-05-26 13:46:44
ASSISTANT (hermes, glm-5.1)
Here's your current model info and how to change it:
**`hermes model`** — launches the interactive model/provider picker.
Other ways to check or change model:
```
hermes config # shows current model + provider
hermes config set model.default <model> # set model directly
hermes config set model.provider <provider> # set provider
/model [name] # in-session: show or change model
```
**Current config** (from system): You're running **glm-5.1** on **ollama-cloud**.
Want me to run `hermes config` to show full details, or `hermes model` to open the interactive picker?
2026-05-26 13:46:44
USER (hermes, glm-5.1)
hermes update
2026-05-26 13:51:20
ASSISTANT (hermes, glm-5.1)
2026-05-26 13:51:20
TOOL (hermes, glm-5.1)
{"output": "Using Python 3.11.15 environment at: venv\nResolved 100 packages in 534ms\n Building hermes-agent @ file:///home/ubuntu/.hermes/hermes-agent\nDownloading pydantic-core (2.0MiB)\n Downloaded pydantic-core\n Built hermes-agent @ file:///home/ubuntu/.hermes/hermes-agent\nPrepared 3 packages in 2.00s\nUninstalled 4 packages in 10ms\nInstalled 5 packages in 4ms\n - hermes-agent==0.13.0 (from file:///home/ubuntu/.hermes/hermes-agent)\n + hermes-agent==0.14.0 (from file:///home/ubuntu/.hermes/hermes-agent)\n - pydantic==2.12.5\n + pydantic==2.13.4\n - pydantic-core==2.41.5\n + pydantic-core==2.46.4\n + pytest-timeout==2.4.0\n - python-dotenv==1.2.1\n + python-dotenv==1.2.2\n⚕ Updating Hermes Agent...\n\n→ Fetching updates...\n→ Found 1460 new commit(s)\n ✓ Pre-update snapshot: 20260526-135034-pre-update\n→ Pulling updates...\n ✓ Cleared 59 stale __pycache__ directories\n→ Updating Python dependencies...\n→ Updating Node.js dependencies...\n ✓ repo root\n ✓ ui-tui\n→ Building web UI...\n ✓ Web UI built\n\n✓ Code updated!\n\n→ Syncing bundled skills...\n + 3 new: hermes-s6-container-supervision, baoyu-article-illustrator, kanban-codex-lane\n ↑ 7 updated: maps, google-workspace, ocr-and-documents, notion, arxiv, polymarket, comfyui\n ~ 2 user-modified (kept)\n\n→ Syncing bundled skills to all profiles...\n default: ~2 user-modified\n\n→ Checking configuration for new options...\n ✓ Configuration is up to date\n\n✓ Update complete!\n\nℹ Skill curator — last run 5d ago\n auto: no changes; llm: ## Consolidation Pass — Complete\n \n ### Clusters Processed\n \n **1. AionUI / VPS Agent Infrastructure** (5 → 1)\n - **Umbrella:** `aionui-agent-integration` — already covered ACP integration patterns broadly\n - **Absorbed:** `aionui-vps-service` (V…\n archived 1 skill(s):\n • systemd-stdin-wrapper — pruned (stale)\n full report: hermes curator status\n (This message shows once per curator run. View anytime: hermes curator status)\n → hermes-gateway: draining (up to 75s)...\n\n ✓ Restarted hermes-gateway\n\nTip: You can now select a provider and model:\n hermes model # Select provider and model", "exit_code": 0, "error": null, "approval": "Command required approval (hermes update (restarts gateway, kills running agents)) and was approved by the user."}
[System: Your previous response was truncated by the output length limit. Continue exactly where you left off. Do not restart or repeat prior text. Finish the answer directly.]
2026-05-26 13:51:20
ASSISTANT (hermes, glm-5.1)
Nothing was truncated — the update summary was complete. You're all set on **v0.14.0** with gateway running.