Hermes Agent ☤

Hermes Agent | Hermes Desktop

The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.

Use any model you want — Nous Portal, OpenRouter, OpenAI, your own endpoint, and many others. Switch with hermes model — no code changes, no lock-in.

Quick Install

Raspberry Pi 2 / IoT — this fork

For Raspberry Pi 2, ARMv7, low-resource edge nodes, MQTT device control, or remote-first RAG, install the maintained pi2-lite branch from this repository:

git clone --branch pi2-lite --depth 1 \
  https://github.com/matttest0080-prog/hermes-agent-iot.git
cd hermes-agent-iot
bash setup-pi2-minimal.sh --profile minimal
source ~/.hermes-venv/bin/activate
hermes setup model
hermes

Keep the clone directory. The Pi2 installer uses an editable Python installation (pip install -e), so the installed hermes command continues to reference this checkout. Moving or deleting hermes-agent-iot can break the environment.

Previous source-deployment snapshot (before the 0.20.0.post1 PyPI packaging work in this branch):

• source version: 0.20.0
• upstream merge commit: 4f1082ba14
• security release commit: af60caf08
• deployment branch: pi2-lite

The fork may intentionally lag the fast-moving upstream main while IoT patches, dependency changes and ARMv7 compatibility are reviewed. The version number alone does not mean that every newer upstream commit is already present.

Install profiles

Three similarly named concepts are intentionally separate:

• Install profiles (hermes-iot setup --profile ...) select one packaged configuration template and record the choice; they never run pip or overwrite an existing ~/.hermes/config.yaml.
• PyPI extras (hermes-agent-iot[minimal], [iot], [rag], [full], [dev]) select dependency sets. Install into a virtual environment first, then run hermes-iot setup --profile NAME.
• Hermes instance profiles (hermes profile ...) are independent runtime homes/configurations and are unrelated to package installation profiles.

Example PyPI path: python -m pip install 'hermes-agent-iot[iot]', followed by hermes-iot setup --profile iot. full and dev target stronger hosts and are not suitable for Raspberry Pi 2 / 1 GB systems.

The initial PyPI wheel contains the Python runtime, CLI entry points, Python plugin modules, and the four profile configuration templates. Repository-level bundled/optional skills, optional MCP catalogs, Desktop/TUI/Web build artifacts, and other source-tree assets are intentionally not copied into the lightweight wheel. Use the branch-specific Git clone installer when those assets are required. In PyPI terminology, full and dev describe dependency sets; they do not turn the wheel into a Desktop bundle.

Consequently, the wheel does not provide the repository's official skills catalog, optional MCP catalog, non-English locale catalog, Dashboard bundle, or prebuilt TUI bundle. Catalog browsing/install commands, localized UI, Dashboard/TUI startup, and source/frontend development require the pi2-lite Git checkout. These features are not silently downloaded by hermes-iot setup.

The wheel build and clean-install smoke tests currently run on x86_64 Linux. They do not constitute physical Raspberry Pi 2 / ARMv7 validation. Do not treat the first PyPI artifact as a verified Pi2 support claim until the same released wheel has completed a clean install and runtime smoke test on physical Pi2 hardware.

The initial release publishes the universal wheel only. It does not publish an sdist whose installation could depend on a source checkout and its release build marker.

Choose the profile that matches the target device and workload:

bash setup-pi2-minimal.sh --profile minimal  # Pi2 / ARMv7 / 1GB RAM baseline
bash setup-pi2-minimal.sh --profile iot      # MQTT, Home Assistant, MCP/ACP and SMS
bash setup-pi2-minimal.sh --profile rag      # IoT + Honcho; remote-first RAG
bash setup-pi2-minimal.sh --profile full     # Stronger Pi, ARM64, x86 edge server or VM
bash setup-pi2-minimal.sh --profile dev      # Full profile + development/test tooling

• minimal: smallest practical Hermes CLI installation for Raspberry Pi 2.
• iot: adds MQTT, Home Assistant, MCP, ACP and SMS integrations.
• rag: adds Honcho and a remote-first RAG configuration; local heavy embedding stacks are not installed by default.
• full: installs the broader Hermes feature set and is not recommended for Raspberry Pi 2 or other 1 GB systems.
• dev: installs full and developer/test dependencies; intended for contributor machines rather than production edge nodes.

Backward-compatible aliases remain available: core → minimal and native → iot.

See README_PI2.md for the complete dependency matrix, configuration templates and safety guidance.

Updating this Pi2 / IoT fork

The Pi2 installer uses an editable checkout and profile-specific dependency sets. The examples below assume the repository was cloned into ~/hermes-agent-iot; if you used another clone directory, replace that path. The hermes executable is installed in the Pi2 virtual environment created by the installer. Opening the repository directory alone does not put it on PATH; activate the environment before running any hermes command:

cd ~/hermes-agent-iot
source ~/.hermes-venv/bin/activate
command -v hermes
hermes --version

If Bash reports hermes: command not found, the virtual environment is not active. Run the activation command above. If ~/.hermes-venv/bin/activate does not exist, complete the profile installation first:

bash setup-pi2-minimal.sh --profile minimal
source ~/.hermes-venv/bin/activate

Preview an update with the branch explicitly selected:

hermes update --check --branch pi2-lite

The CLI may print the generic message Run 'hermes update' to install. That message is not branch-safe for this Pi2 fork. Do not run the bare command; continue to use the explicit pi2-lite branch shown below.

For an actual Pi2 update, use the branch-safe git procedure and rerun the same profile installer so the low-resource dependency set is restored:

cd ~/hermes-agent-iot

# Review local changes first; do not update a dirty checkout blindly.
git status --short

# Explicitly select the Pi2 branch before fetching or merging.
git switch pi2-lite
git fetch origin pi2-lite
git merge --ff-only origin/pi2-lite

source ~/.hermes-venv/bin/activate
bash setup-pi2-minimal.sh --profile minimal

# Verify that the checkout stayed on the Pi2 branch.
test "$(git branch --show-current)" = "pi2-lite"
git status --short

Replace minimal with the profile originally installed (iot, rag, full or dev). The generic hermes update --branch pi2-lite command is not the preferred Pi2 profile update path because Hermes updates reinstall the broader dependency group; if you use it, rerun the original profile installer afterwards. Never run a bare hermes update here: its default target is main, not pi2-lite. Review or preserve local changes before pulling; do not use a hard reset as a routine update method.

Upstream Hermes full installer

The installers below install the official NousResearch/hermes-agent build. Use them for general desktop/server installations; they do not install this fork's Pi2 profiles or MQTT additions.

Linux, macOS, WSL2, Termux

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

Windows (native, PowerShell)

Heads up: Native Windows runs Hermes without WSL — CLI, gateway, TUI, and tools all work natively. If you'd rather use WSL2, the Linux/macOS one-liner above works there too. Found a bug? Please file issues.

Run this in PowerShell:

iex (irm https://hermes-agent.nousresearch.com/install.ps1)

The installer handles everything: uv, Python 3.11, Node.js, ripgrep, ffmpeg, and a portable Git Bash (MinGit, unpacked to %LOCALAPPDATA%\hermes\git — no admin required, completely isolated from any system Git install). Hermes uses this bundled Git Bash to run shell commands.

If you already have Git installed, the installer detects it and uses that instead. Otherwise a ~45MB MinGit download is all you need — it won't touch or interfere with any system Git.

Android / Termux: The tested manual path is documented in the Termux guide. On Termux, Hermes installs a curated .[termux] extra because the full .[all] extra currently pulls Android-incompatible voice dependencies.

Windows: Native Windows is fully supported — the PowerShell one-liner above installs everything. If you'd rather use WSL2, the Linux command works there too. Native Windows install lives under %LOCALAPPDATA%\hermes; WSL2 installs under ~/.hermes as on Linux.

After installation:

source ~/.bashrc    # reload shell (or: source ~/.zshrc)
hermes              # start chatting!

Troubleshooting

Windows Defender or antivirus flags uv.exe as malware

If your antivirus (Bitdefender, Windows Defender, etc.) quarantines uv.exe from the Hermes bin folder (%LOCALAPPDATA%\hermes\bin\uv.exe), this is a false positive. The file is Astral's uv — the Rust Python package manager Hermes bundles to manage its Python environment. ML-based antivirus engines commonly flag unsigned Rust binaries that download and install packages.

To verify your copy is authentic:

# Install GitHub CLI if needed
winget install --id GitHub.cli

# Login to GitHub
gh auth login

# Run verification
$uv = "$env:LOCALAPPDATA\hermes\bin\uv.exe"
$ver = (& $uv --version).Split(' ')[1]
[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12
$zip = "$env:TEMP\uv.zip"
Invoke-WebRequest "https://github.com/astral-sh/uv/releases/download/$ver/uv-x86_64-pc-windows-msvc.zip" -OutFile $zip -UseBasicParsing
gh attestation verify $zip --repo astral-sh/uv
Expand-Archive $zip "$env:TEMP\uv_x" -Force
(Get-FileHash "$env:TEMP\uv_x\uv.exe").Hash -eq (Get-FileHash $uv).Hash

If attestation says "Verification succeeded" and the last line prints True, you're good.

To whitelist Hermes:

• Windows Defender: Run PowerShell as Admin → Add-MpPreference -ExclusionPath "$env:LOCALAPPDATA\hermes\bin"
• Bitdefender: Add an exception in the Bitdefender console (Protection > Antivirus > Settings > Manage Exceptions)
• Whitelist the folder, not the file hash — Hermes updates uv and the hash changes every version

For more context, see the upstream Astral reports: astral-sh/uv#13553, astral-sh/uv#15011, astral-sh/uv#10079.

Getting Started

hermes              # Interactive CLI — start a conversation
hermes model        # Choose your LLM provider and model
hermes tools        # Configure which tools are enabled
hermes config set   # Set individual config values
hermes config get   # Print individual config values
hermes gateway      # Start the messaging gateway (Telegram, Discord, etc.)
hermes setup        # Run the full setup wizard (configures everything at once)
hermes claw migrate # Migrate from OpenClaw (if coming from OpenClaw)
hermes update       # Official managed installs; Pi2 fork users: see update instructions above
hermes doctor       # Diagnose any issues

📖 Full documentation →

Skip the API-key collection — Nous Portal

Hermes works with whatever provider you want — that's not changing. But if you'd rather not collect five separate API keys for the model, web search, image generation, TTS, and a cloud browser, Nous Portal covers all of them under one subscription:

• 300+ models — pick any of them with /model <name>
• Tool Gateway — web search (Firecrawl), image generation (FAL), text-to-speech (OpenAI), cloud browser (Browser Use), all routed through your sub. No extra accounts.

One command from a fresh install:

hermes setup --portal

That logs you in via OAuth, sets Nous as your provider, and turns on the Tool Gateway. Check what's wired up any time with hermes portal info. Full details on the Tool Gateway docs page.

You can still bring your own keys per-tool whenever you want — the gateway is per-backend, not all-or-nothing.

CLI vs Messaging Quick Reference

Hermes has two entry points: start the terminal UI with hermes, or run the gateway and talk to it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once you're in a conversation, many slash commands are shared across both interfaces.

For the full command lists, see the CLI guide and the Messaging Gateway guide.

Documentation

Upstream Hermes documentation lives at hermes-agent.nousresearch.com/docs. This IoT fork adds the local Pi2 and robotics guides listed below.

Raspberry Pi 2 and IoT profiles

This fork also carries opt-in low-resource profiles while preserving the upstream Agent, Gateway, tool, plugin, memory, cron, MCP, and ACP architecture:

• Pi2 quickstart and profile guide
• Detailed Raspberry Pi 2 manual
• Robotics architecture and safety guidance

Start with bash setup-pi2-minimal.sh --profile minimal, or select iot or rag for MQTT/Home Assistant and remote-first RAG dependencies. Heavy browser, media, local embedding, and desktop surfaces remain opt-in on constrained hosts.

Migrating from OpenClaw

If you're coming from OpenClaw, Hermes can automatically import your settings, memories, skills, and API keys.

During first-time setup: The setup wizard (hermes setup) automatically detects ~/.openclaw and offers to migrate before configuration begins.

Anytime after install:

hermes claw migrate              # Interactive migration (full preset)
hermes claw migrate --dry-run    # Preview what would be migrated
hermes claw migrate --preset user-data   # Migrate without secrets
hermes claw migrate --overwrite  # Overwrite existing conflicts

What gets imported:

• SOUL.md — persona file
• Memories — MEMORY.md and USER.md entries
• Skills — user-created skills → ~/.hermes/skills/openclaw-imports/
• Command allowlist — approval patterns
• Messaging settings — platform configs, allowed users, working directory
• API keys — allowlisted secrets (Telegram, OpenRouter, OpenAI, Anthropic, ElevenLabs)
• TTS assets — workspace audio files
• Workspace instructions — AGENTS.md (with --workspace-target)

See hermes claw migrate --help for all options, or use the openclaw-migration skill for an interactive agent-guided migration with dry-run previews.

Contributing

We welcome contributions! See the Contributing Guide for development setup, code style, and PR process.

Quick start for contributors — use the standard installer, then work from the full git checkout it creates at $HERMES_HOME/hermes-agent (usually ~/.hermes/hermes-agent). This matches the layout used by hermes update, the managed venv, lazy dependencies, gateway, and docs tooling.

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
cd "${HERMES_HOME:-$HOME/.hermes}/hermes-agent"
uv pip install -e ".[all,dev]"
scripts/run_tests.sh

Manual clone fallback (for throwaway clones/CI where you intentionally do not want the managed install layout):

Create the venv outside the cloned source tree — a venv inside the directory the agent operates from can be wiped by a relative-path command the agent runs against its own checkout, destroying the running runtime mid-session.

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv ~/.hermes/venvs/hermes-dev --python 3.11
source ~/.hermes/venvs/hermes-dev/bin/activate
uv pip install -e ".[all,dev]"
scripts/run_tests.sh

Community

• 💬 Discord
• 📚 Skills Hub
• 🐛 Issues
• 🔌 computer-use-linux — Linux desktop-control MCP server for Hermes and other MCP hosts, with AT-SPI accessibility trees, Wayland/X11 input, screenshots, and compositor window targeting.
• 🔌 HermesClaw — Community WeChat bridge: Run Hermes Agent and OpenClaw on the same WeChat account.

License

MIT — see LICENSE.

Upstream Hermes Agent is built by Nous Research. This Raspberry Pi / IoT fork is maintained by matttest0080-prog.

Bundled plugins, skills and third-party components may include their own license or notice files; those terms apply to the corresponding components.