Imported from lorenzobelpassi/lorenzo-hermes-skills (autonomous-ai-agents/hermes-agent/SKILL.md). Install upstream with npx skills add lorenzobelpassi/lorenzo-hermes-skills --skill hermes-agent. Copyright stays with the author (MIT).

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 10+ 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/

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 (ID can be a hub identifier OR a direct https://…/SKILL.md URL; pass --name to override when frontmatter has no name)
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

Supported platforms: Telegram, Discord, Slack, WhatsApp, Signal, Email, SMS, Matrix, Mattermost, Home Assistant, DingTalk, Feishu, WeCom, BlueBubbles (iMessage), Weixin (WeChat), API Server, Webhooks. Open WebUI connects via the API Server adapter.

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

Agent-facing pattern: context-linked jobs. When multiple scheduled agents serve the same operating system, avoid duplicate research by creating one upstream "lead bank" / "signal router" job and passing its recent output into downstream jobs via cron context_from when using the cronjob tool. Example: daily shared lead bank → Tuesday editorial draft + Friday column draft. Downstream prompts should explicitly say "use injected lead bank first; fresh search only for verification/gaps" and list reused items so later jobs know what was consumed.

Cron context-sharing pattern

When multiple scheduled agents cover overlapping research, create a shared upstream "lead bank" / "signal bank" job and pass it into downstream jobs via context_from instead of letting each job repeat the same searches. Pattern:

1. Daily upstream job: dedupe recent outputs from existing jobs, mark already-covered items, split public-safe vs internal-only material, and maintain a verification queue.
2. Downstream weekly/draft jobs: update prompts to say "use the shared lead bank first; only search fresh to verify/fill gaps".
3. Use context_from=["<upstream_job_id>"] when creating/updating downstream jobs.
4. Trigger the upstream job once with cron run after creation to seed context.

This reduces duplicate web research, makes agents synergistic, and gives later jobs a memory of what was already used.

Autonomous editorial/research desk pattern

When the user wants Hermes to "act constantly" or replace a recurring blogger/researcher workflow, prefer scheduled human-in-the-loop draft jobs over automatic publishing. Create separate cron jobs for each recurring column/brief, deliver to the active messaging channel (origin is often best), and require the prompt to include: do not publish automatically, include source notes, label uncertainty, and do not invent named facts. Save an operating doc with job IDs and schedules, then verify with hermes cron list.

See references/autonomous-editorial-cron-pattern.md for the reusable workflow and guardrails.

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

Fallback Providers\n\nFallback providers are tried in order when the primary model fails with rate-limit, overload, or connection errors.\n\n\nhermes fallback list (ls) Show current fallback chain\nhermes fallback add Add a provider+model to the chain (interactive picker — cannot be scripted)\nhermes fallback remove (rm) Pick an entry to delete (interactive picker)\nhermes fallback clear Remove all fallback entries\n\n\nThe fallback chain is stored as fallback_providers: [] in ~/.hermes/config.yaml. To add entries non-interactively, edit config.yaml directly:\n\nyaml\nfallback_providers:\n - provider: anthropic\n model: claude-haiku-3-5\n - provider: openrouter\n model: anthropic/claude-sonnet-4-5\n\n\nPitfall: hermes fallback add and hermes model are both interactive TUI pickers — they have no CLI flags for non-interactive/scripted use. Always edit config.yaml directly when automating.

Recommended fallback chain (Lorenzo's setup as of May 2026):

fallback_providers:
- model: claude-sonnet-4.5
  provider: copilot
- model: claude-haiku-4.5
  provider: copilot
- model: meta-llama/llama-3.3-70b-instruct:free
  provider: openrouter
- model: gpt-4o-mini
  provider: openai

Rationale: Copilot subscription covers gpt-4.1 (primary) + both claude fallbacks at no extra cost. OpenRouter free tier for llama. OpenAI key as final paid safety net.

Pitfall — Copilot model names use dots for version decimals: GitHub Copilot API uses claude-sonnet-4.5, claude-haiku-4.5, gpt-4.1 etc. (dots). Using dashes (e.g. claude-sonnet-4-5) returns HTTP 403. Always verify available model IDs by calling https://api.githubcopilot.com/models with the token before setting config.

Pitfall — gpt-4.1-mini is not available on Copilot: The Copilot model catalog does not include gpt-4.1-mini. Use gpt-4o-mini as the delegation model instead.

Pitfall — OpenRouter free models come and go: google/gemini-2.0-flash-exp:free was removed without notice. When a free model returns 404, check available free models with:

import urllib.request, json, re
with open('/Users/lorenzobelpassi/.hermes/.env') as f: env = f.read()
key = re.search(r'OPENROUTER_API_KEY=(\S+)', env).group(1)
req = urllib.request.Request('https://openrouter.ai/api/v1/models', headers={'Authorization': f'Bearer {key}'})
data = json.loads(urllib.request.urlopen(req, timeout=15).read())
for m in sorted(m['id'] for m in data['data'] if ':free' in m['id']): print(m)

Reliable free options as of May 2026: meta-llama/llama-3.3-70b-instruct:free, nousresearch/hermes-3-llama-3.1-405b:free.

Pitfall — provider name must be copilot, not githubcopilot: The githubcopilot provider string is not recognized by the auxiliary client or fallback resolver. Use copilot everywhere (fallback_providers, delegation.provider). Using githubcopilot silently fails with "unknown provider 'githubcopilot'" in gateway.error.log and the fallback is skipped entirely.

Pitfall — claude-haiku-3-5 is not a valid model name: The correct versioned name is claude-haiku-3-5-20241022. Anthropic returns HTTP 404 for the unversioned alias — exhausts all 3 retry attempts before moving to the next fallback.

GitHub Copilot token: use COPILOT_GITHUB_TOKEN in .env. OAuth tokens from gh auth login (gho_..., 40 chars) are the most reliable — get one with gh auth token. Fine-grained PATs (github_pat_11...) are accepted by the code but rejected by GitHub's API at runtime with "Personal Access Tokens are not supported for this endpoint." Classic PATs (ghp_...) also do NOT work. Best practice: run gh auth login, then python3 -c "import subprocess; print(subprocess.check_output(['gh','auth','token']).decode().strip())" and paste the gho_ token into .env. After adding, hermes gateway restart to pick it up.\n\nDocs: https://hermes-agent.nousresearch.com/docs/user-guide/features/fallback-providers\n\n### Credential Pools\n\n\nhermes auth add Interactive credential wizard\nhermes auth list [PROVIDER] List pooled credentials\nhermes auth remove P INDEX Remove by provider + index\nhermes auth reset PROVIDER Clear exhaustion status\n

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 (requires honcho plugin)
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
/personality [name]  Set personality
/reasoning [level]   Set reasoning (none|minimal|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)

Gateway

/approve             Approve a pending command (gateway)
/deny                Deny a pending command (gateway)
/restart             Restart gateway (gateway)
/sethome             Set current chat as home channel (gateway)
/update              Update Hermes to latest (gateway)
/platforms (/gateway) Show platform connection status (gateway)

Utility

/branch (/fork)      Branch the current session
/fast                Toggle priority/fast processing
/browser             Open CDP browser connection
/history             Show conversation history (CLI)
/save                Save conversation to file (CLI)
/paste               Attach clipboard image (CLI)
/image               Attach local image file (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_HOME/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.

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

Providers

20+ providers supported. Set via hermes model or hermes setup.

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

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.

Security & Privacy Toggles

Common "why is Hermes doing X to my output / tool calls / commands?" toggles — and the exact commands to change them. Most of these need a fresh session (/reset in chat, or start a new hermes invocation) because they're read once at startup.

Secret redaction in tool output

Secret redaction is off by default — tool output (terminal stdout, read_file, web content, subagent summaries, etc.) passes through unmodified. If the user wants Hermes to auto-mask strings that look like API keys, tokens, and secrets before they enter the conversation context and logs:

hermes config set security.redact_secrets true       # enable globally

Restart required. security.redact_secrets is snapshotted at import time — toggling it mid-session (e.g. via export HERMES_REDACT_SECRETS=true from a tool call) will NOT take effect for the running process. Tell the user to run hermes config set security.redact_secrets true in a terminal, then start a new session. This is deliberate — it prevents an LLM from flipping the toggle on itself mid-task.

Disable again with:

hermes config set security.redact_secrets false

PII redaction in gateway messages

Separate from secret redaction. When enabled, the gateway hashes user IDs and strips phone numbers from the session context before it reaches the model:

hermes config set privacy.redact_pii true    # enable
hermes config set privacy.redact_pii false   # disable (default)

Command approval prompts

By default (approvals.mode: manual), Hermes prompts the user before running shell commands flagged as destructive (rm -rf, git reset --hard, etc.). The modes are:

• manual — always prompt (default)
• smart — use an auxiliary LLM to auto-approve low-risk commands, prompt on high-risk
• off — skip all approval prompts (equivalent to --yolo)

hermes config set approvals.mode smart       # recommended middle ground
hermes config set approvals.mode off         # bypass everything (not recommended)

Per-invocation bypass without changing config:

• hermes --yolo …
• export HERMES_YOLO_MODE=1

Note: YOLO / approvals.mode: off does NOT turn off secret redaction. They are independent.

Shell hooks allowlist

Some shell-hook integrations require explicit allowlisting before they fire. Managed via ~/.hermes/shell-hooks-allowlist.json — prompted interactively the first time a hook wants to run.

Disabling the web/browser/image-gen tools

To keep the model away from network or media tools entirely, open hermes tools and toggle per-platform. Takes effect on next session (/reset). See the Tools & Skills section above.

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
4. Mistral Voxtral — set MISTRAL_API_KEY

Config:

stt:
  enabled: true
  provider: local        # local, groq, openai, mistral
  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. In gateway: /restart. In CLI: exit and relaunch.

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

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
4. Copilot 403 on specific models: Model names on Copilot use dots for version decimals — claude-sonnet-4.5, not claude-sonnet-4-5. Using dashes causes HTTP 403. Verify the actual model list: python3 -c "import urllib.request,json,re,open as o; env=open('/Users/lorenzobelpassi/.hermes/.env').read(); t=re.search(r'COPILOT_GITHUB_TOKEN=(\S+)',env).group(1); r=urllib.request.urlopen(urllib.request.Request('https://api.githubcopilot.com/models',headers={'Authorization':f'Bearer {t}','Copilot-Integration-Id':'vscode-chat'})); [print(m['id']) for m in json.loads(r.read())['data']]"

Changes not taking effect

• Tools/skills: /reset starts a new session with updated toolset
• Config changes: In gateway: /restart. In CLI: exit and relaunch.
• Code changes: Restart the CLI or gateway process

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

WAL file too large

Run hermes doctor --fix — it performs a SQLite checkpoint and reclaims space. Safe to run anytime. Symptom: hermes doctor reports "WAL file is large (Xmb)".

Gateway issues

Check logs first:

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

Common gateway problems:

• Gateway dies on SSH logout: Enable linger: sudo loginctl enable-linger $USER
• Gateway dies on WSL2 close: WSL2 requires systemd=true in /etc/wsl.conf for systemd services to work. Without it, gateway falls back to nohup (dies when session closes).
• Gateway crash loop: Reset the failed state: systemctl --user reset-failed hermes-gateway

Platform-specific issues

Discord diagnostic flow → references/discord-setup-diagnostics.md; token/auth recovery runbook → references/discord-token-recovery.md

• Cron script agent can't find Google OAuth token: Hermes cron script jobs (no_agent: true, run via .sh) look for token files by hardcoded path. If a script expects ~/.hermes/gmail_token.pickle but the actual token is ~/.hermes/selva_outreach_token.pickle, create a symlink: ln -sf ~/.hermes/selva_outreach_token.pickle ~/.hermes/gmail_token.pickle. The token must have the required scopes (e.g. Drive) — check with python3 -c "import pickle; t=pickle.load(open('~/.hermes/selva_outreach_token.pickle','rb')); print(t.scopes)". Test the script directly before relying on cron.
• Discord token invalid / overwritten: If logs show 401 Unauthorized, LoginFailure('Improper token has been passed.'), or repeated Discord reconnect timeouts, validate DISCORD_BOT_TOKEN against https://discord.com/api/v10/users/@me before restarting repeatedly. Restore a known-good token from backup/snapshot or Discord Developer Portal, set DISCORD_ALLOWED_USERS to the numeric personal user ID, then hermes gateway restart.
• Discord bot silent: Must enable Message Content Intent in Bot → Privileged Gateway Intents.
• Discord bot connected but seems offline: The mcp_send_message target list only shows Telegram/active DM channels. Discord being absent from that list does NOT mean it's down — check hermes gateway status and ~/.hermes/logs/gateway.log for [Discord] Safely reconciled N slash command(s) to confirm it's live.
• Discord channel names stale in mcp_send_message list: The target list is cached and does NOT reflect Discord channel renames. If Lorenzo renames a channel, the old name still appears. Don't trust the display name — use the topic ID for targeting, or ask Lorenzo for the current name.
• Discord bot ignores all messages / DISCORD_ALLOWED_USERS misconfigured: DISCORD_ALLOWED_USERS in ~/.hermes/.env must be set to your personal Discord user ID, not the bot's own ID. Symptom: bot is running, token is valid, but no messages are processed. Fix: get your user ID via Discord → Settings → Advanced → Developer Mode → right-click your username → Copy User ID, then set DISCORD_ALLOWED_USERS=<your_id> in .env and restart the gateway.
• Slack bot only works in DMs: Must subscribe to message.channels event. Without it, the bot ignores public channels.
• Windows HTTP 400 "No models provided": Config file encoding issue (BOM). Ensure config.yaml is saved as UTF-8 without BOM.

Vision tool only accepts HTTP/HTTPS URLs

mcp_vision_analyze rejects local file paths (e.g. /tmp/foo.png, /Users/…/Desktop/shot.png). It returns "Invalid image source" for any file:// or bare path. To analyze a local image, either:

• Serve it temporarily (python3 -m http.server 8080 then use http://localhost:8080/file.png)
• Or ask the user to paste/share via a URL, or just describe what they see directly.

Auxiliary models not working

If auxiliary tasks (vision, compression, session_search) fail silently, the auto provider can't find a backend. Either set OPENROUTER_API_KEY or GOOGLE_API_KEY, or explicitly configure each auxiliary task's provider:

hermes config set auxiliary.vision.provider <your_provider>
hermes config set auxiliary.vision.model <model_name>

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, context compression, memory, model routing, credential pooling, skill dispatch
├── 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 to toolsets.py → _HERMES_CORE_TOOLS list.

Auto-discovery: any tools/*.py file with a top-level registry.register() call is imported automatically — no manual list needed.

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

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