Hermes Agentvs Claude Code

Claude Code is Anthropic's agentic coding tool. It reads your codebase, edits files, runs commands and works with git, and it runs in the terminal, IDE extensions, a desktop app and the web. Hermes Agent is the agent around that work. It answers on more than 20 messaging platforms, runs scheduled jobs, keeps memory and works with the model you pick.

A bundled Hermes Agent skill, claude-code, is listed in the skills catalog as 'Delegate coding to Claude Code CLI (features, PRs).' Claude Code itself signs in with a Claude account, a Claude Console API key or a cloud provider.

If you already use Claude Code, hermes migrate claude-code brings your setup into Hermes Agent, installing the official agent-importers plugin when it is missing. Your global CLAUDE.md becomes memory entries, and your MCP servers, Bash permission rules and skills come along. It shows a preview before it writes anything and never imports credentials, and hermes import-agent --sync pulls in later changes.

Hermes Agent answers on more than 20 messaging platforms, including Telegram, WhatsApp, Slack, Signal and Microsoft Teams, from one background gateway. That gateway owns every session, so the terminal, Hermes Desktop, your chat apps and scheduled jobs share one conversation. You schedule jobs in natural language or cron syntax, and on a server or Hermes Cloud the gateway keeps running them with your computer off.

Claude Code's channels, a research preview, push messages from Telegram, Discord or iMessage into a running session. In Slack, mentioning @Claude with a coding task creates a cloud session. Cloud scheduled tasks, also a research preview, run on Pro, Max, Ultra, Team and Enterprise plans with your computer off. Desktop scheduled tasks fire only while the app is open and the computer is awake.

Hermes Agent works with any OpenAI-compatible API. Nous Portal gives it hundreds of models with one login, and local models run through Ollama, vLLM, llama.cpp or SGLang. You pick the provider and model, /model switches mid-session, and your conversation history, memory and skills carry over whichever provider you use. Backup providers are opt-in.

Claude Code uses Claude models, and Anthropic does not support routing it to non-Claude models through any gateway. Hermes Agent can use Claude models with an Anthropic API key, billed per token, or through Nous Portal. A Claude Max sign-in draws only on purchased extra usage credits, not the base Max allowance, and Claude Pro cannot sign in.

Hermes Agent keeps a curated memory of your preferences, projects and environment, and it loads that memory into every session. Full-text search covers all its past CLI and messaging sessions. When it works out a non-trivial workflow, it saves the approach as a skill and refines that skill as it uses it. You can require approval before skill changes land, and a background curator maintains the skills it creates.

Claude Code reads CLAUDE.md files that you write. Its auto memory, on by default in local sessions, stores notes on your machine that Claude writes from your corrections. You add skills to Claude Code as SKILL.md files.

Hermes Agent is open source under the MIT license, and its code is on GitHub. The software is free and local models cost nothing to run. You pay the model provider you choose, or use a Nous Portal plan with Hermes Agent usage included, within limits that reset daily, weekly and monthly. Every paid Nous Portal plan includes one Hermes Cloud agent; larger or extra agents bill daily from credits.

Claude Code is proprietary. The LICENSE file in Anthropic's claude-code repository reads 'All rights reserved' and makes use subject to Anthropic's Commercial Terms of Service. Claude Code comes with Claude's Pro, Max, Ultra, Team and Enterprise plans, and the Free plan does not include it. Its usage counts against the same limits as the Claude apps, and with a Console account it bills API tokens at standard API prices.