Hermes Agent

Hermes Agent

Hermes 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.

What makes Hermes different:

• 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.
• 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.
• Multi-platform gateway — the same agent runs on Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and 8+ other platforms with full tool access, not just chat.
• Provider-agnostic — swap models and providers mid-workflow without changing anything else. Credential pools rotate across multiple API keys automatically.
• Profiles — run multiple independent Hermes instances with isolated configs, sessions, skills, and memory.
• Extensible — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, and the full Python ecosystem.

People 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.

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.

Docs: https://hermes-agent.nousresearch.com/docs/

Windows install: For setting up Hermes in a repo-centric workspace on Windows, load the hermes-windows-setup skill. It covers prerequisites (git, Python, uv, gh), workspace structure, skills system, memory bridge, multi-agent coordination, and Windows-specific pitfalls.

Quick Start

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

# Interactive chat (default)
hermes

# Single query
hermes chat -q "What is the capital of France?"

# Setup wizard
hermes setup

# Change model/provider
hermes model

# Check health
hermes doctor

CLI Reference

Global Flags

hermes [flags] [command]

  --version, -V             Show version
  --resume, -r SESSION      Resume session by ID or title
  --continue, -c [NAME]     Resume by name, or most recent session
  --worktree, -w            Isolated git worktree mode (parallel agents)
  --skills, -s SKILL        Preload skills (comma-separate or repeat)
  --profile, -p NAME        Use a named profile
  --yolo                    Skip dangerous command approval
  --pass-session-id         Include session ID in system prompt

No subcommand defaults to chat.

Chat

hermes chat [flags]
  -q, --query TEXT          Single query, non-interactive
  -m, --model MODEL         Model (e.g. anthropic/claude-sonnet-4)
  -t, --toolsets LIST       Comma-separated toolsets
  --provider PROVIDER       Force provider (openrouter, anthropic, nous, etc.)
  -v, --verbose             Verbose output
  -Q, --quiet               Suppress banner, spinner, tool previews
  --checkpoints             Enable filesystem checkpoints (/rollback)
  --source TAG              Session source tag (default: cli)

Configuration

hermes setup [section]      Interactive wizard (model|terminal|gateway|tools|agent)
hermes model                Interactive model/provider picker
hermes config               View current config
hermes config edit          Open config.yaml in $EDITOR
hermes config set KEY VAL   Set a config value
hermes config path          Print config.yaml path
hermes config env-path      Print .env path
hermes config check         Check for missing/outdated config
hermes config migrate       Update config with new options
hermes login [--provider P] OAuth login (nous, openai-codex)
hermes logout               Clear stored auth
hermes doctor [--fix]       Check dependencies and config
hermes status [--all]       Show component status

Tools & Skills

hermes tools                Interactive tool enable/disable (curses UI)
hermes tools list           Show all tools and status
hermes tools enable NAME    Enable a toolset
hermes tools disable NAME   Disable a toolset

hermes skills list          List installed skills
hermes skills search QUERY  Search the skills hub
hermes skills install ID    Install a skill
hermes skills inspect ID    Preview without installing
hermes skills config        Enable/disable skills per platform
hermes skills check         Check for updates
hermes skills update        Update outdated skills
hermes skills uninstall N   Remove a hub skill
hermes skills publish PATH  Publish to registry
hermes skills browse        Browse all available skills
hermes skills tap add REPO  Add a GitHub repo as skill source

MCP Servers

hermes mcp serve            Run Hermes as an MCP server
hermes mcp add NAME         Add an MCP server (--url or --command)
hermes mcp remove NAME      Remove an MCP server
hermes mcp list             List configured servers
hermes mcp test NAME        Test connection
hermes mcp configure NAME   Toggle tool selection

Gateway (Messaging Platforms)

hermes gateway run          Start gateway foreground
hermes gateway install      Install as background service
hermes gateway start/stop   Control the service
hermes gateway restart      Restart the service
hermes gateway status       Check status
hermes gateway setup        Configure platforms

System-level install (persistent across reboots, runs as systemd service):

# sudo strips PATH — use full path to hermes binary
sudo $(which hermes) gateway install --system   # Install as system service (not --user)
sudo $(which hermes) gateway start --system
sudo $(which hermes) gateway status --system
sudo $(which hermes) gateway restart --system

PITFALL — env vars not loaded by systemd: After adding vars to ~/.hermes/.env, the systemd service won't see them. Add EnvironmentFile=/home/vamsee/.hermes/.env to the service file:

sudo sed -i '/WorkingDirectory/a EnvironmentFile=/home/vamsee/.hermes/.env' /etc/systemd/system/hermes-gateway.service
sudo systemctl daemon-reload
sudo $(which hermes) gateway restart --system

Supported platforms: Telegram, Discord, Slack, WhatsApp, Signal, Email, SMS, Matrix, Mattermost, Home Assistant, DingTalk, Feishu, WeCom, API Server, Webhooks, Open WebUI.

Platform docs: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/

Sessions

hermes sessions list        List recent sessions
hermes sessions browse      Interactive picker
hermes sessions export OUT  Export to JSONL
hermes sessions rename ID T Rename a session
hermes sessions delete ID   Delete a session
hermes sessions prune       Clean up old sessions (--older-than N days)
hermes sessions stats       Session store statistics

Cron Jobs

hermes cron list            List jobs (--all for disabled)
hermes cron create SCHED    Create: '30m', 'every 2h', '0 9 * * *'
hermes cron edit ID         Edit schedule, prompt, delivery
hermes cron pause/resume ID Control job state
hermes cron run ID          Trigger on next tick
hermes cron remove ID       Delete a job
hermes cron status          Scheduler status

Webhooks

hermes webhook subscribe N  Create route at /webhooks/<name>
hermes webhook list         List subscriptions
hermes webhook remove NAME  Remove a subscription
hermes webhook test NAME    Send a test POST

Profiles

hermes profile list         List all profiles
hermes profile create NAME  Create (--clone, --clone-all, --clone-from)
hermes profile use NAME     Set sticky default
hermes profile delete NAME  Delete a profile
hermes profile show NAME    Show details
hermes profile alias NAME   Manage wrapper scripts
hermes profile rename A B   Rename a profile
hermes profile export NAME  Export to tar.gz
hermes profile import FILE  Import from archive

Credential Pools

hermes auth add             Interactive credential wizard
hermes auth list [PROVIDER] List pooled credentials
hermes auth remove P INDEX  Remove by provider + index
hermes auth reset PROVIDER  Clear exhaustion status

Other

hermes insights [--days N]  Usage analytics
hermes update               Update to latest version
hermes pairing list/approve/revoke  DM authorization
hermes plugins list/install/remove  Plugin management
hermes honcho setup/status  Honcho memory integration
hermes memory setup/status/off  Memory provider config
hermes completion bash|zsh  Shell completions
hermes acp                  ACP server (IDE integration)
hermes claw migrate         Migrate from OpenClaw
hermes uninstall            Uninstall Hermes

Slash Commands (In-Session)

Type these during an interactive chat session.

Session Control

/new (/reset)        Fresh session
/clear               Clear screen + new session (CLI)
/retry               Resend last message
/undo                Remove last exchange
/title [name]        Name the session
/compress            Manually compress context
/stop                Kill background processes
/rollback [N]        Restore filesystem checkpoint
/background <prompt> Run prompt in background
/queue <prompt>      Queue for next turn
/resume [name]       Resume a named session

Configuration

/config              Show config (CLI)
/model [name]        Show or change model
/provider            Show provider info
/prompt [text]       View/set system prompt (CLI)
/personality [name]  Set personality
/reasoning [level]   Set reasoning (none|low|medium|high|xhigh|show|hide)
/verbose             Cycle: off → new → all → verbose
/voice [on|off|tts]  Voice mode
/yolo                Toggle approval bypass
/skin [name]         Change theme (CLI)
/statusbar           Toggle status bar (CLI)

Tools & Skills

/tools               Manage tools (CLI)
/toolsets            List toolsets (CLI)
/skills              Search/install skills (CLI)
/skill <name>        Load a skill into session
/cron                Manage cron jobs (CLI)
/reload-mcp          Reload MCP servers
/plugins             List plugins (CLI)

Info

/help                Show commands
/commands [page]     Browse all commands (gateway)
/usage               Token usage
/insights [days]     Usage analytics
/status              Session info (gateway)
/profile             Active profile info

Exit

/quit (/exit, /q)    Exit CLI

Key Paths & Config

~/.hermes/config.yaml       Main configuration
~/.hermes/.env              API keys and secrets
~/.hermes/skills/           Installed skills
~/.hermes/sessions/         Session transcripts
~/.hermes/logs/             Gateway and error logs
~/.hermes/auth.json         OAuth tokens and credential pools
~/.hermes/hermes-agent/     Source code (if git-installed)

Profiles use ~/.hermes/profiles/<name>/ with the same layout.

Config Sections

Edit with hermes config edit or hermes config set section.key value.

Skill-Specific Config

Some skills declare their own config keys in SKILL.md frontmatter under metadata.hermes.config. Hermes stores these under skills.config.* in ~/.hermes/config.yaml, prompts for missing values during hermes config migrate, and shows them in hermes config under ◆ Skill Settings.

Example:

metadata:
  hermes:
    config:
      - key: wiki.path
        description: Path to the LLM Wiki knowledge base directory
        default: "~/wiki"

Stored in config as:

skills:
  config:
    wiki:
      path: /home/user/wiki

Useful commands:

hermes config check
hermes config migrate
hermes config set skills.config.wiki.path /home/user/wiki
hermes config

Current learned behavior/pitfalls:

• Hermes stores skill-specific config under skills.config.* in config.yaml, even when prompts display the logical key (for example wiki.path).
• In the audited install, the only discovered skill-declared custom config key across built-in Hermes skills plus external workspace-hub skill dirs was wiki.path from llm-wiki.
• Verify the configured path actually exists before accepting a migrated default; one observed config had wiki.path=/home/vamsee/wiki even though that directory was missing, while the real workspace wiki root lived at /mnt/local-analysis/workspace-hub/knowledge/wikis.
• hermes config is the quickest way to verify skill settings after config set; hermes config check may still report optional web env vars as missing even when toolsets are enabled.
• Approval-mode naming is inconsistent across this codebase: runtime approval logic in tools/approval.py recognizes manual, smart, and off, while hermes_cli/web_server.py exposes ask, yolo, and deny. Treat manual/smart/off as authoritative for runtime behavior unless the UI mapping is verified in the current build.
• Web tool availability is backend-credential driven. If hermes doctor reports missing EXA_API_KEY, PARALLEL_API_KEY, TAVILY_API_KEY, FIRECRAWL_API_KEY, or FIRECRAWL_API_URL, then web_search/web_extract are not fully enabled regardless of the toolset toggle.

To audit which installed skills declare custom config, search SKILL frontmatter for metadata.hermes.config / key: entries across both built-in and external skill directories.

Full config reference: https://hermes-agent.nousresearch.com/docs/user-guide/configuration

Providers

18 providers supported. Set via hermes model or hermes setup.

Plus: AI Gateway, OpenCode Zen, OpenCode Go, MiniMax CN, GitHub Copilot ACP.

Full provider docs: https://hermes-agent.nousresearch.com/docs/integrations/providers

Approval Mode Caveat

Hermes currently has a config/UI mismatch in some builds:

• Runtime approval engine (tools/approval.py) uses approvals.mode values: manual, smart, off
• Some web UI schemas (hermes_cli/web_server.py) may still show: ask, yolo, deny

Prefer editing approvals.mode directly in config.yaml or via hermes config set approvals.mode ... using the runtime values manual, smart, or off.

• manual — normal approval prompts
• smart — auxiliary LLM auto-approves clearly safe commands, auto-denies clearly dangerous ones, escalates uncertain cases
• off — bypass approval prompts entirely

Treat ask/yolo/deny as stale UI labels unless you have verified the mapping in your installed build.

Toolsets

Enable/disable via hermes tools (interactive) or hermes tools enable/disable NAME.

Tool changes take effect on /reset (new session). They do NOT apply mid-conversation to preserve prompt caching.

Voice & Transcription

STT (Voice → Text)

Voice messages from messaging platforms are auto-transcribed.

Provider priority (auto-detected):

1. Local faster-whisper — free, no API key: pip install faster-whisper
2. Groq Whisper — free tier: set GROQ_API_KEY
3. OpenAI Whisper — paid: set VOICE_TOOLS_OPENAI_KEY

Config:

stt:
  enabled: true
  provider: local        # local, groq, openai
  local:
    model: base          # tiny, base, small, medium, large-v3

TTS (Text → Voice)

Voice commands: /voice on (voice-to-voice), /voice tts (always voice), /voice off.

Spawning Additional Hermes Instances

Run additional Hermes processes as fully independent subprocesses — separate sessions, tools, and environments.

When to Use This vs delegate_task

One-Shot Mode

terminal(command="hermes chat -q 'Research GRPO papers and write summary to ~/research/grpo.md'", timeout=300)

# Background for long tasks:
terminal(command="hermes chat -q 'Set up CI/CD for ~/myapp'", background=true)

Interactive PTY Mode (via tmux)

Hermes uses prompt_toolkit, which requires a real terminal. Use tmux for interactive spawning:

# Start
terminal(command="tmux new-session -d -s agent1 -x 120 -y 40 'hermes'", timeout=10)

# Wait for startup, then send a message
terminal(command="sleep 8 && tmux send-keys -t agent1 'Build a FastAPI auth service' Enter", timeout=15)

# Read output
terminal(command="sleep 20 && tmux capture-pane -t agent1 -p", timeout=5)

# Send follow-up
terminal(command="tmux send-keys -t agent1 'Add rate limiting middleware' Enter", timeout=5)

# Exit
terminal(command="tmux send-keys -t agent1 '/exit' Enter && sleep 2 && tmux kill-session -t agent1", timeout=10)

Multi-Agent Coordination

# Agent A: backend
terminal(command="tmux new-session -d -s backend -x 120 -y 40 'hermes -w'", timeout=10)
terminal(command="sleep 8 && tmux send-keys -t backend 'Build REST API for user management' Enter", timeout=15)

# Agent B: frontend
terminal(command="tmux new-session -d -s frontend -x 120 -y 40 'hermes -w'", timeout=10)
terminal(command="sleep 8 && tmux send-keys -t frontend 'Build React dashboard for user management' Enter", timeout=15)

# Check progress, relay context between them
terminal(command="tmux capture-pane -t backend -p | tail -30", timeout=5)
terminal(command="tmux send-keys -t frontend 'Here is the API schema from the backend agent: ...' Enter", timeout=5)

Session Resume

# Resume most recent session
terminal(command="tmux new-session -d -s resumed 'hermes --continue'", timeout=10)

# Resume specific session
terminal(command="tmux new-session -d -s resumed 'hermes --resume 20260225_143052_a1b2c3'", timeout=10)

Tips

• Prefer delegate_task for quick subtasks — less overhead than spawning a full process
• Use -w (worktree mode) when spawning agents that edit code — prevents git conflicts
• Set timeouts for one-shot mode — complex tasks can take 5-10 minutes
• Use hermes chat -q for fire-and-forget — no PTY needed
• Use tmux for interactive sessions — raw PTY mode has \r vs \n issues with prompt_toolkit
• For scheduled tasks, use the cronjob tool instead of spawning — handles delivery and retry

Troubleshooting

Voice not working

1. Check stt.enabled: true in config.yaml
2. Verify provider: pip install faster-whisper or set API key
3. Restart gateway: /restart

Tool not available

1. hermes tools — check if toolset is enabled for your platform
2. Some tools need env vars (check .env)
3. /reset after enabling tools
4. For web tool debugging, verify the provider vars are actually present in both the current shell environment and ~/.hermes/.env (EXA_API_KEY, PARALLEL_API_KEY, TAVILY_API_KEY, FIRECRAWL_API_KEY, FIRECRAWL_API_URL). hermes doctor reports availability from real runtime config — don't assume a transient shell export or another process has made them persistent.

Model/provider issues

1. hermes doctor — check config and dependencies
2. hermes login — re-authenticate OAuth providers
3. Check .env has the right API key

Changes not taking effect

• Tools/skills: /reset starts a new session with updated toolset
• Config changes: /restart reloads gateway config
• Code changes: Restart the CLI or gateway process

After hermes update — stashed local changes restored

When hermes update stashes and restores local changes, inspect the diff carefully before committing:

• The hermes launcher shebang may get rewritten from portable #!/usr/bin/env python3 to a hardcoded venv path like #!/home/user/.hermes/hermes-agent/.venv/bin/python3. Do NOT commit this — it breaks other machines. Fix: git checkout hermes to revert to the portable shebang.
• package-lock.json changes (npm dependency updates) ARE safe to commit if you have a fork.
• The source repo is NousResearch/hermes-agent.git (upstream) — you cannot push directly. To sync custom changes across machines, either fork the repo or track config in your own repo (e.g. workspace-hub/config/agents/hermes/).

Skills not showing

1. hermes skills list — verify installed
2. hermes skills config — check platform enablement
3. Load explicitly: /skill name or hermes -s name

Gateway issues

Check logs first:

grep -i "failed to send\|error" ~/.hermes/logs/gateway.log | tail -20

Where to Find Things

Contributor Quick Reference

For occasional contributors and PR authors. Full developer docs: https://hermes-agent.nousresearch.com/docs/developer-guide/

Project Layout

hermes-agent/
├── run_agent.py          # AIAgent — core conversation loop
├── model_tools.py        # Tool discovery and dispatch
├── toolsets.py           # Toolset definitions
├── cli.py                # Interactive CLI (HermesCLI)
├── hermes_state.py       # SQLite session store
├── agent/                # Prompt builder, compression, display, adapters
├── hermes_cli/           # CLI subcommands, config, setup, commands
│   ├── commands.py       # Slash command registry (CommandDef)
│   ├── config.py         # DEFAULT_CONFIG, env var definitions
│   └── main.py           # CLI entry point and argparse
├── tools/                # One file per tool
│   └── registry.py       # Central tool registry
├── gateway/              # Messaging gateway
│   └── platforms/        # Platform adapters (telegram, discord, etc.)
├── cron/                 # Job scheduler
├── tests/                # ~3000 pytest tests
└── website/              # Docusaurus docs site

Config: ~/.hermes/config.yaml (settings), ~/.hermes/.env (API keys).

Adding a Tool (3 files)

1. Create tools/your_tool.py:

import json, os
from tools.registry import registry

def check_requirements() -> bool:
    return bool(os.getenv("EXAMPLE_API_KEY"))

def example_tool(param: str, task_id: str = None) -> str:
    return json.dumps({"success": True, "data": "..."})

registry.register(
    name="example_tool",
    toolset="example",
    schema={"name": "example_tool", "description": "...", "parameters": {...}},
    handler=lambda args, **kw: example_tool(
        param=args.get("param", ""), task_id=kw.get("task_id")),
    check_fn=check_requirements,
    requires_env=["EXAMPLE_API_KEY"],
)

2. Add import in model_tools.py → _discover_tools() list.

3. Add to toolsets.py → _HERMES_CORE_TOOLS list.

All handlers must return JSON strings. Use get_hermes_home() for paths, never hardcode ~/.hermes.

Adding a Slash Command

1. Add CommandDef to COMMAND_REGISTRY in hermes_cli/commands.py
2. Add handler in cli.py → process_command()
3. (Optional) Add gateway handler in gateway/run.py

All consumers (help text, autocomplete, Telegram menu, Slack mapping) derive from the central registry automatically.

Agent Loop (High Level)

run_conversation():
  1. Build system prompt
  2. Loop while iterations < max:
     a. Call LLM (OpenAI-format messages + tool schemas)
     b. If tool_calls → dispatch each via handle_function_call() → append results → continue
     c. If text response → return
  3. Context compression triggers automatically near token limit

Testing

source venv/bin/activate  # or .venv/bin/activate
python -m pytest tests/ -o 'addopts=' -q   # Full suite
python -m pytest tests/tools/ -q            # Specific area

• Tests auto-redirect HERMES_HOME to temp dirs — never touch real ~/.hermes/
• Run full suite before pushing any change
• Use -o 'addopts=' to clear any baked-in pytest flags

Commit Conventions

type: concise subject line

Optional body.

Types: fix:, feat:, refactor:, docs:, chore:

Key Rules

• Never break prompt caching — don't change context, tools, or system prompt mid-conversation
• Message role alternation — never two assistant or two user messages in a row
• Use get_hermes_home() from hermes_constants for all paths (profile-safe)
• Config values go in config.yaml, secrets go in .env
• New tools need a check_fn so they only appear when requirements are met

External Skill Directories (Wiring Repo Ecosystem Skills)

Hermes can scan external skill directories alongside ~/.hermes/skills/. This is how you connect a repo ecosystem's skill library (e.g. workspace-hub's .claude/skills/) to Hermes.

Configuration

Add external_dirs under skills in ~/.hermes/config.yaml:

skills:
  external_dirs:
    - /mnt/local-analysis/workspace-hub/.claude/skills
    - ~/.agents/skills          # other shared dirs
    - ${SKILLS_REPO}/skills     # env var expansion supported

Behavior:

• Read-only — Hermes indexes external skills but never writes to them. New skills always go to ~/.hermes/skills/.
• Local precedence — if the same skill name exists locally and externally, the local version wins.
• Full integration — external skills appear in system prompt, skills_list, skill_view, and as /skill-name slash commands.
• Non-existent paths silently skipped — safe for optional/conditional dirs.

Filtering Large Skill Libraries

External repos may have archived/internal directories with thousands of skills that would bloat the system prompt. The scan exclusion list is in agent/skill_utils.py:

EXCLUDED_SKILL_DIRS = frozenset((
    ".git", ".github", ".hub",
    "_archive", "_internal", "_runtime", "_core",
    "session-logs",
))

The default Hermes only excludes .git/.github/.hub. For workspace-hub's convention of _archive/ (2,166 archived skills) and _internal/, _runtime/, _core/ dirs, you must patch EXCLUDED_SKILL_DIRS.

Surviving hermes update

hermes update does git pull on the source repo, which overwrites local patches. To persist patches across updates:

1. Save the diff as a .patch file in your repo's harness patches dir:

   cd ~/.hermes/hermes-agent
   git diff agent/skill_utils.py > ~/workspace-hub/config/agents/hermes/patches/exclude-archive-skill-dirs.patch
   

2. The harness-update.sh script auto-applies all *.patch files after each update:

   for pf in "$PATCH_DIR"/*.patch; do
     git -C "$hermes_dir" apply --check "$pf" 2>/dev/null && \
       git -C "$hermes_dir" apply "$pf"
   done
   

3. If a patch fails to apply (upstream changed the code), the harness logs it and continues — check logs after updates.

Verification

After configuring, restart Hermes and check:

# Count what gets indexed (should exclude _archive etc.)
find /path/to/external/skills -name 'SKILL.md' \
  -not -path '*/_archive/*' -not -path '*/_internal/*' \
  -not -path '*/_runtime/*' -not -path '*/_core/*' \
  -not -path '*/session-logs/*' | wc -l

Changes take effect on next session start (config loaded at startup).