Hermes Agent ☤

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 (200+ models), NVIDIA NIM (Nemotron), Xiaomi MiMo, z.ai/GLM, Kimi/Moonshot, MiniMax, Hugging Face, OpenAI, or your own endpoint. Switch with hermes model — no code changes, no lock-in.

A real terminal interface	Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.
Lives where you do	Telegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription, cross-platform conversation continuity.
A closed learning loop	Agent-curated memory with periodic nudges. Autonomous skill creation after complex tasks. Skills self-improve during use. FTS5 session search with LLM summarization for cross-session recall. Honcho dialectic user modeling. Compatible with the agentskills.io open standard.
Scheduled automations	Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended.
Delegates and parallelizes	Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.
Runs anywhere, not just your laptop	Six terminal backends — local, Docker, SSH, Daytona, Singularity, and Modal. Daytona and Modal offer serverless persistence — your agent's environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster.
Research-ready	Batch trajectory generation, Atropos RL environments, trajectory compression for training the next generation of tool-calling models.

---

Quick Install

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Works on Linux, macOS, WSL2, and Android via Termux. The installer handles the platform-specific setup for you.

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 not supported. Please install WSL2 and run the command above.

After installation:

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

---

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 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       # Update to the latest version
hermes doctor       # Diagnose any issues

📖 Full documentation →

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.

Action	CLI	Messaging platforms
Start chatting	hermes	Run hermes gateway setup + hermes gateway start, then send the bot a message
Start fresh conversation	/new or /reset	/new or /reset
Change model	/model [provider:model]	/model [provider:model]
Set a personality	/personality [name]	/personality [name]
Retry or undo the last turn	/retry, /undo	/retry, /undo
Compress context / check usage	/compress, /usage, /insights [--days N]	/compress, /usage, /insights [days]
Browse skills	/skills or /<skill-name>	/<skill-name>
Interrupt current work	Ctrl+C or send a new message	/stop or send a new message
Platform-specific status	/platforms	/status, /sethome

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

---

Documentation

All documentation lives at hermes-agent.nousresearch.com/docs:

Section	What's Covered
Quickstart	Install → setup → first conversation in 2 minutes
CLI Usage	Commands, keybindings, personalities, sessions
Configuration	Config file, providers, models, all options
Messaging Gateway	Telegram, Discord, Slack, WhatsApp, Signal, Home Assistant
Security	Command approval, DM pairing, container isolation
Tools & Toolsets	40+ tools, toolset system, terminal backends
Skills System	Procedural memory, Skills Hub, creating skills
Memory	Persistent memory, user profiles, best practices
MCP Integration	Connect any MCP server for extended capabilities
Cron Scheduling	Scheduled tasks with platform delivery
Context Files	Project context that shapes every conversation
Architecture	Project structure, agent loop, key classes
Contributing	Development setup, PR process, code style
CLI Reference	All commands and flags
Environment Variables	Complete env var reference

---

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 — clone and go with setup-hermes.sh:

git clone https://github.com/NousResearch/hermes-agent.git
cd hermes-agent
./setup-hermes.sh     # installs uv, creates venv, installs .[all], symlinks ~/.local/bin/hermes
./hermes              # auto-detects the venv, no need to `source` first

Manual path (equivalent to the above):

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

RL Training (optional): The RL/Atropos integration (environments/) ships via the atroposlib and tinker dependencies pulled in by .[all,dev] — no submodule setup required.

---

Community

• 💬 Discord
• 📚 Skills Hub
• 🐛 Issues
• 🔌 HermesClaw — Community WeChat bridge: Run Hermes Agent and OpenClaw on the same WeChat account.

---

Clipboard Troubleshooting

Hermes TUI (standalone) and dashboard both support copying via Ctrl+C / Cmd+C. This requires either:

• A terminal with OSC 52 support enabled, or
• Native clipboard utilities (pbcopy, wl-copy, xclip, xsel, clip.exe) available in PATH and a running display server (X11 or Wayland).

If the UI says "copied" but the text is not in your system clipboard, follow these steps.

Standalone TUI (hermes --tui)

Verify OSC 52 support

Run this in the same terminal you use for Hermes:

printf '\e]52;c;%s\a' "$(echo -n 'test-osc52' | base64)" && echo

Then paste (Cmd+V / Ctrl+Shift+V). If you see test-osc52, OSC 52 works.

If it fails, enable OSC 52 in your terminal:

Terminal	Setting
iTerm2	Preferences → General → Selection → check "Copy to pasteboard"
Kitty	allow_remote_control yes (default: on)
WezTerm	enable_osc52_copy = true
VS Code	Usually works; if blocked, check DevTools console for permission error
GNOME	Enabled by default

tmux users

tmux absorbs OSC 52 unless explicitly configured. Add to ~/.tmux.conf:

set -g set-clipboard on
set -g allow-passthrough on

Then reload: tmux source-file ~/.tmux.conf.

Docker/headless environments

Inside a Docker container, $DISPLAY and $WAYLAND_DISPLAY are typically unset, so native clipboard tools fail immediately. OSC 52 is the only path — it must be supported by your local terminal emulator (the one connected to the container's PTY). If your terminal doesn't support OSC 52, consider:

• Using ssh -X / ssh -Y to forward X11 and run xclip on the host via SSH
• Running Hermes on the host directly, not inside a container
• Writing copied text to a file: /copy saves to ~/.hermes/clipboard.txt (fallback)

Force OSC 52 emission

If your terminal supports OSC 52 but Hermes isn't emitting it (e.g., inside SSH where native tools are skipped), set:

export HERMES_TUI_CLIPBOARD_OSC52=1
hermes --tui

Debug mode

To see exactly which clipboard path Hermes takes:

export HERMES_TUI_DEBUG_CLIPBOARD=1
hermes --tui

Then attempt a copy and watch stderr for messages like:

[clipboard] [native] Linux: no DISPLAY or WAYLAND_DISPLAY — native clipboard unavailable
[clipboard] [native] Linux: clipboard probe complete → xclip
[clipboard] [osc52] no sequence emitted — native clipboard or tmux buffer path in use

Dashboard (hermes dashboard → /chat)

The dashboard uses the browser's Clipboard API. There are two copy paths:

1. Ctrl/Cmd+Shift+C — direct copy from xterm's selection (most reliable)
2. Ink's Ctrl+C — emits OSC 52 → xterm OSC 52 handler → Clipboard API; this is more fragile because the Clipboard API requires a user gesture. In some browsers the OSC 52 response is processed outside the original key event's activation window, causing a silent failure.

If copy doesn't work in the dashboard:

• Use Ctrl+Shift+C (Linux/Windows) or Cmd+Shift+C (macOS) instead
• Check the browser console (F12) for warnings like [dashboard clipboard] OSC 52 write failed
• Ensure the page has clipboard permissions (browser may ask on first use)

Clicking the "copy last response" button also sends /copy over the WebSocket, which suffers from the same OSC 52 timing issue.

When all else fails: file-based fallback

You can save copied text to a file manually:

hermes --tui  # inside TUI, use /copy which includes a file fallback in future versions

Or implement a custom skill that writes the last assistant message to disk.

---

License

MIT — see LICENSE.

Built by Nous Research.