repowiserepowise

MCP server

nousresearch / hermes-agent

The agent that grows with you

★ 261,697stars on GitHubPythonMIT
Install hermes-agentView on GitHub★ 262kSee this for your own repoAsk this codebase

Repowise maps public repos from their source. Not affiliated with nousresearch. What is Repowise?

github.com/nousresearch/hermes-agentIndexed at 13ce0c5

What is hermes-agent?

hermes-agent is an AI agent built by Nous Research for running tasks from a terminal or from chat apps such as Telegram, Discord and Slack. It can use many model providers, creates skills from its own experience, improves those skills during use, and searches past conversations. The project is written mainly in Python, with TypeScript used for its desktop app. To install it, run git clone https://github.com/nousresearch/hermes-agent.git and follow the steps below. Its code health is 5.3 out of 10 (Needs_work), ranked #211 of 4,000+ indexed repos. The last commit to hermes-agent was on Aug 19, 2026, and 2,790 people have contributed.

As of commit 13ce0c5, indexed Aug 19, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentshermes-agent.md

Repo facts: type, license, health, rank, contributors
hermes-agent facts
TypeMCP server
LicenseMIT
Code health5.3 / 10 (Needs_work)
Health rank#211 of 4,000+ indexed repos
Last commitAug 19, 2026
Contributors2,790
Bus factor2
Size8,758 files, 2,120,703 lines

Install hermes-agent

Commands copied from the README

  1. 1Clone the hermes-agent repository.
    git clone https://github.com/nousresearch/hermes-agent.git
  2. 2Move into the hermes-agent folder.
    cd hermes-agent
  3. 3Reload your shell so the new command is on the path.
    source ~/.bashrc # reload shell (or: source ~/.zshrc)

Releases on GitHub (latest v0.23.1, Nov 10, 2026)

Full install notes on GitHub

Explore hermes-agent

Ask about this code in your agent

This connects Repowise to hermes-agent's code. It does not install hermes-agent. To install hermes-agent, use the install steps.

Useful if you want to change or fork hermes-agent: your agent can ask how it is put together and get answers that cite its files.

Show the connect command (Claude Code, Cursor, Codex, VS Code)

Run it in a terminal, then type /mcp in Claude Code and sign in with Repowise. No key to paste.

Docs
bash
claude mcp add --transport http repowise https://api.repowise.dev/mcp/nousresearch/hermes-agent
Claude Code, Claude, Cursor and VS Code sign you in on first use, free. Codex and Windsurf need an API key: sign in to create one.Sign in for a key

This repo is public, so anyone with a free Repowise account can connect.

Try asking

  • get_overview()
  • get_answer("how is hermes-agent put together?")
  • get_why("why is hermes-agent structured this way?")

How to use hermes-agent

  1. 1Start the interactive CLI and begin a conversation.
    hermes # start chatting!

Ask about hermes-agent

Answers come from hermes-agent's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of nousresearch/hermes-agent from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

nousresearch/hermes-agent FAQ

What is hermes-agent?

hermes-agent is an AI agent built by Nous Research that runs in a terminal or through chat apps such as Telegram, Discord and Slack. It creates and improves skills from experience and can search its past conversations.

How does hermes-agent work?

hermes-agent takes input from the terminal interface or from its messaging gateway, which runs as a single process. It then uses the model provider you select, with options including Nous Portal, OpenRouter and OpenAI, and can call tools to carry out tasks.

How do I install hermes-agent?

Run the install script with curl on Linux, macOS, WSL2 or Termux, or run the PowerShell installer on native Windows. After installation, reload your shell and run the hermes command to start chatting. See the install steps

What language is hermes-agent written in?

hermes-agent is written mainly in Python, with TypeScript, JavaScript, Shell, Rust and C++ files also in the repository. The Python files are the largest group by count.

How is the hermes-agent code organized?

hermes-agent is split into 24 modules, and the largest by file count are tests, apps, website, optional-skills and ui-tui. The core CLI lives in hermes_cli and the messaging gateway lives in gateway.

When should I use hermes-agent?

Use hermes-agent when you want an agent that works from a terminal and from messaging apps, keeps memory across sessions and runs scheduled tasks without supervision. It can run on a cloud server rather than only on your laptop.

What license does hermes-agent use?

hermes-agent is released under the MIT license, identified as MIT in its license metadata. That license permits use, modification and redistribution of the code.

Code health

5.3out of 10Needs work

Hotspots average 3.7, the place fixes pay off most.

Full health report

On the leaderboards:#6 of 6 Coding agents#60 of 64 Python repos

Key features of hermes-agent

  • A full terminal interface with multiline editing, slash-command autocomplete, conversation history and streaming tool output.
  • One gateway process connects the agent to Telegram, Discord, Slack, WhatsApp, Signal and the CLI, with voice memo transcription.
  • The agent curates its own memory, creates skills after complex tasks and improves them during use.
  • Session search uses FTS5 with LLM summarization to recall earlier conversations across sessions.
  • A built-in cron scheduler sends results to any connected platform and runs tasks unattended.
  • Subagents can be spawned for parallel workstreams, and the agent can run in local, Docker, SSH, Modal, Daytona and other terminal backends.

How nousresearch/hermes-agent works

Input enters through the terminal interface started by hermes_cli/main.py, which is also a hotspot file in the hermes_cli package, or through the messaging gateway in gateway/run.py, which runs one process that connects the chat platforms. hermes_state.py is listed as a hotspot file and handles the agent's state. acp_adapter/server.py is an entry point for the ACP adapter that exposes the agent to other clients. The desktop app's Electron main process is in apps/desktop/electron/main.ts. The tests directory is the largest module by file count.

The codebase has 8,758 files and 100,728 symbols in 24 modules, led by Python, TypeScript and JavaScript. Code health is 5.3 out of 10, rated needs work.