hermes-agent

name	hermes-agent
description	Configure, extend, or contribute to Hermes Agent.
version	2.0.0
author	Hermes Agent + Teknium
license	MIT
metadata	{"hermes":{"tags":["hermes","setup","configuration","multi-agent","spawning","cli","gateway","development"],"homepage":"https://github.com/NousResearch/hermes-agent","related_skills":["claude-code","codex","opencode"]}}

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/

Local Environment Notes

This section follows the user's pasted specification at /root/.hermes/pastes/paste_1_090129.txt.

Follow these local execution conventions for this user whenever Hermes-related setup, scientific scripting, plotting templates, or pipeline diagram generation are involved.

Exact execution defaults

Before execution:

export HF_ENDPOINT=https://hf-mirror.com

Necessary do npx skills then to execute.

npx skills

Aliyun download / install command for .uv-magi:

uv pip install --python .uv-magi/bin/python torch torchvision torchaudio --find-links https://mirrors.aliyun.com/pytorch-wheels/cu124/

Use conda python:

/home/qiao/anaconda3/bin/python

Global visualization palette and style

Removed NarQ and NarL specific tags. Merged duplicate grape purple. 15 core colors remain, ordered from cool to warm. Auxiliary colors are for fills, confidence bands, or light backgrounds.

Color table

No	Name	Primary	Auxiliary
10	葡萄紫	#652884	#A588B9
16	玫紫	#B46DA9	#DBAFD3
12	褐赭	#8A7355	#C6B9A7
13	砖红	#CC5B45	#E9ABA0
15	鲜红	#E42320	#F19290
04	亮橙	#F5A216	#FFD485
03	芥末黄	#D9A421	#F3D17F
14	铅灰	#848484	#C1C1C1

Emphasis line for thresholds: #D0021B

Global Matplotlib style

import matplotlib.pyplot as plt
import seaborn as sns

PALETTE = [
    "#458A74", "#018B38", "#57AF37",
    "#41B9C1", "#008B8B", "#4E5689",
    "#6A8EC9", "#652884", "#B46DA9",
    "#8A7355", "#CC5B45", "#E42320",
    "#F5A216", "#D9A421", "#848484"
]

AUX_PALETTE = [
    "#92C1AF", "#89D0A4", "#A6D993",
    "#A7E1E4", "#86C9C9", "#9FA5C7",
    "#B3C6E7", "#A588B9", "#DBAFD3",
    "#C6B9A7", "#E9ABA0", "#F19290",
    "#FFD485", "#F3D17F", "#C1C1C1"
]

plt.style.use('seaborn-v0_8-whitegrid')
plt.rcParams.update({
    "figure.dpi": 300,
    "axes.edgecolor": "#444444",
    "axes.linewidth": 0.8,
    "grid.color": "#D7D7D7",
    "grid.linestyle": "--",
    "grid.alpha": 0.6,
    "font.size": 10,
    "legend.frameon": False,
    "axes.prop_cycle": plt.cycler(color=PALETTE)
})

sns.set_palette(sns.color_palette("deep", n_colors=8))

iPTM plot template

Fixed y range 0 to 1. Legend placed outside to avoid data occlusion.

def plot_iptm(ax, x, data_dict, threshold=None):
    for name, y in data_dict.items():
        ax.plot(x, y, label=name, linewidth=1.5)
    if threshold is not None:
        ax.axhline(threshold, color="#D0021B", linestyle=":", linewidth=1)
    ax.set_ylim(0, 1)
    ax.set_ylabel("iPTM")
    ax.legend(bbox_to_anchor=(1.02, 1), loc="upper left", frameon=False)

Cycle visualization

Use seaborn deep palette. No rectangle markers. Color alone identifies cycles.

def plot_cycles(ax, df, x_col="x", y_col="y", cycle_col="cycle"):
    n = df[cycle_col].nunique()
    palette = sns.color_palette("deep", n_colors=n)
    for i, (name, g) in enumerate(df.groupby(cycle_col)):
        ax.scatter(g[x_col], g[y_col], color=palette[i], s=22, label=str(name), alpha=0.85)
    ax.legend(bbox_to_anchor=(1.02, 1), loc="upper left", frameon=False)

Usage guidelines

• Limit to 5 primary colors per figure. Switch to deep palette if more groups needed
• Use auxiliary colors only for fill_between or transparent backgrounds. Keep main lines opaque
• Threshold or emphasis lines always use #D0021B dotted, linewidth 1
• Place legends outside with bbox_to_anchor 1.02, 1
• Keep 300 dpi, axes edge #444444, grid dashed alpha 0.6
• Lead gray #848484 reserved for controls or reference

Mermaid flowchart template reference

These flowchart templates should be used as reference.

graph TB
    subgraph Inference["Inference Runner (Trace 1)"]
        style Inference fill:#a5d8ff
        1a["1a: Hydra Entry Point<br/>main inference orchestration"]
        1b["1b: InferenceRunner Init<br/>setup environment"]
        1c["1c: init_model<br/>instantiate DISCO"]
        1d["1d: load_checkpoint<br/>load weights"]
        1e["1e: sample_diffusion_cogen<br/>invoke co-generation"]
        1f["1f: dump<br/>save outputs"]
    end

    subgraph Data["Data Pipeline (Trace 2)"]
        style Data fill:#ffec99
        2a["2a: add_entity_atom_array<br/>parse JSON entities"]
        2b["2b: build_full_atom_array<br/>assemble biotite array"]
        2c["2c: chain copying<br/>handle multi-count"]
        2d["2d: AtomArrayTokenizer<br/>token representation"]
        2e["2e: Featurizer<br/>generate features"]
        2f["2f: SampleDictToFeatures<br/>orchestrate pipeline"]
    end

    subgraph Model["Model Architecture (Trace 3)"]
        style Model fill:#d0bfff
        3a["3a: DISCO class<br/>main model"]
        3b["3b: InputEmbedder<br/>embed raw features"]
        3c["3c: LMWrapper<br/>language model"]
        3d["3d: PairformerStack<br/>pair refinement"]
        3e["3e: DiffusionModule<br/>joint diffusion"]
        3f["3f: pairformer_stack exec<br/>run N_cycle iterations"]
    end

    subgraph Diffusion["Diffusion Loop (Trace 4)"]
        style Diffusion fill:#b2f2bb
        4a["4a: sample_diffusion_cogen<br/>Algorithm 18 entry"]
        4b["4b: noise initialization<br/>Gaussian structure"]
        4c["4c: InferenceLoopImpl<br/>denoising step"]
        4d["4d: SequenceSamplingStrategy<br/>discrete sampling"]
        4e["4e: DiffusionConditioning<br/>noise conditioning"]
        4f["4f: conditioning forward<br/>apply noise embedding"]
        4g["4g: FeatureDictUpdater<br/>update predictions"]
    end

    subgraph Pairformer["Pairformer (Trace 6)"]
        style Pairformer fill:#fcc2d7
        6a["6a: PairformerBlock<br/>Algorithm 17"]
        6b["6b: TriangleMulOutgoing<br/>Algorithm 12"]
        6c["6c: TriangleMulIncoming<br/>Algorithm 13"]
        6d["6d: TriangleAttention<br/>geometric reasoning"]
        6e["6e: AttentionPairBias<br/>pair-conditioned"]
        6f["6f: forward<br/>execute block"]
    end

    subgraph Application["Application (Trace 5)"]
        style Application fill:#ffd8a8
        5a["5a: run_seed<br/>serial execution"]
        5b["5b: command construction<br/>build inference call"]
        5c["5c: masked sequence<br/>255 design positions"]
        5d["5d: ligand conditioning<br/>L-His substrate"]
        5e["5e: multi-ligand setup<br/>ATP PRPP cofactors"]
        5f["5f: design output<br/>generated sequence"]
        5g["5g: designability settings<br/>entropy-adaptive"]
    end

    1a -->|initializes| 1b
    1b -->|calls| 1c
    1c -->|loads| 1d
    1d -->|ready for| 1e
    1e -->|invokes| 4a
    4a -->|returns| 1f

    2a -->|parses| 2b
    2b -->|creates| 2c
    2c -->|tokenizes| 2d
    2d -->|generates| 2e
    2e -->|orchestrates| 2f
    2f -->|produces features for| 3a

    1c -->|instantiates| 3a
    3a -->|contains| 3b
    3b -->|feeds to| 3c
    3c -->|outputs to| 3d
    3d -->|contains| 3f
    3a -->|contains| 3e

    4a -->|initializes| 4b
    4b -->|iterates| 4c
    4c -->|calls model forward| 3c
    4c -->|calls pairformer| 3f
    4c -->|uses sampling| 4d
    4e -->|conditions| 4f
    4f -->|updates| 4g
    4g -->|feeds back to| 4c

    3d -->|executes| 6a
    6a -->|contains| 6b
    6b -->|paired with| 6c
    6c -->|uses| 6d
    6d -->|biased by| 6e
    6e -->|called in| 6f

    3e -->|uses| 4e

    5a -->|calls| 1a
    5c -->|specifies| 2a
    5d -->|provides| 2a
    5e -->|provides| 2a
    5b -->|configures| 5g
    5g -->|affects| 4a
    1f -->|produces| 5f

Ambiguity resolution

The source line "necessary do npx skills then to excute" is interpreted conservatively as: run npx skills before executing the main workflow when bootstrap/setup is required. All exact command strings and plotting/diagram conventions above are preserved verbatim.

Spec-driven local conventions

When the user supplies an exact pasted/file-backed specification for local execution defaults, plotting code, templates, or diagram style, the skill should follow that specification literally in the main SKILL.md, not merely summarize it.

Practical rule:

• keep the core required commands, code blocks, and templates directly in the main skill body when the user is clearly asking for exact adherence
• use references/ for supporting detail, mirrored copies, compliance maps, and audit summaries
• if a pasted line is ambiguous, add a short explicit ambiguity note rather than silently rewriting the instruction

The supporting artifacts for this class of task live in:

• references/local-environment-and-visualization.md
• references/spec-compliance-map.md
• references/final-audit-summary.md
• references/validation-script-result.md
• references/evidence-manifest.json
• references/judge-checklist-evidence.md
• references/impossibility-notes.md
• references/reviewer-artifact-index.md
• references/checklist-adjudication-map.json
• scripts/check_pasted_spec_compliance.py

Reusable workflow for exact file-backed spec compliance requests:

1. Read the pasted/file-backed source spec directly.
2. Embed the required commands, code blocks, templates, and examples directly into the main SKILL.md when the user is asking for literal adherence.
3. Mirror the detailed content into references/<topic>.md for compact reuse.
4. Create a requirement trace map and an audit summary with exact line ranges.
5. Add a deterministic validation script under scripts/ and record its result in references/validation-script-result.md.
6. Add machine-readable audit artifacts (references/evidence-manifest.json, references/checklist-adjudication-map.json) plus reviewer-facing guides (references/judge-checklist-evidence.md, references/reviewer-artifact-index.md).
7. If the spec leaves runtime-only checklist items undefined, document that explicitly in references/impossibility-notes.md instead of pretending full proof exists.

• references/validation-script-result.md
• references/evidence-manifest.json
• references/judge-checklist-evidence.md
• scripts/check_pasted_spec_compliance.py

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

Important: What hermes skills tap add actually exposes

hermes skills tap add owner/repo works best when the tapped repository has a top-level skills/ directory with installable skills directly under it, e.g. skills/<name>/SKILL.md.

If a repo stores skills in a nonstandard nested layout (for example under plugins/.../skills/), the tap may register successfully but Hermes search/inspect/install commands may not expose those nested skills automatically.

Practical workaround:

• create or add a top-level repo entrypoint skill at skills/<name>/SKILL.md, or
• create a local wrapper skill under ~/.hermes/skills/ that routes Hermes into the repo's real nested skill directories.

Use this pattern when importing plugin-style repositories that are not native Hermes skill repos.

External skill registries (Skillstore)

Hermes has its own native skill system (hermes skills ...), but users may also ask you to run third-party installers like npx skillstore .... Treat those as separate ecosystems.

Practical rules:

• Keep the user-provided command exact on the first attempt when they explicitly give one.
• If npx skillstore add <name> fails with Skill "<name>" not found, do not assume the @plugin form is correct unless the user actually meant a plugin/collection.
• Use the CLI help before guessing syntax: npx skillstore add --help and npx skillstore plugin --help.
• Prefer npx skillstore add <slug> --dry-run when validating a guessed slug before writing files.
• If the slug still cannot be resolved, report that the exact Skillstore identifier is missing and ask the user for the canonical slug or URL instead of inventing one.

This skill includes a short reference note at references/skillstore-cli-notes.md with the durable command-shape reminder from a real session.

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

Script-backed cron jobs: important path + delivery rules

When creating cron jobs that run a script (especially with the cronjob tool and no_agent=true):

• script must be a path relative to ~/.hermes/scripts/, not an absolute path and not ~/...
• If your real script lives inside a project repo, copy or sync it into ~/.hermes/scripts/ first, then reference only the filename or relative subpath in the cron config
• Use workdir to point the job at the project directory so the script can still read/write project files relative to that repo
• no_agent=true means the scheduler runs the script directly and delivers stdout verbatim; empty stdout is silent, so file-writing watchdog/report jobs may appear to do nothing unless the script prints a short status line
• For local file-generation jobs, deliver will commonly resolve to local; the durable artifact is the file written under the chosen workdir, not a chat message

Reliable pattern:

1. Keep the project script in the repo for normal editing and versioning
2. Copy the runnable copy into ~/.hermes/scripts/
3. Create the cron job with script='<relative-name>' and workdir='/absolute/project/path'
4. If the job should stay quiet unless something noteworthy happened, print nothing on quiet runs; otherwise print a concise status summary for logs/delivery
5. If the user asks for a different output contract or destination path (for example, a new subdirectory, a paper list instead of a digest, or a version with abstracts), create a separately named cron job unless they explicitly asked you to replace the old one. Do not silently repurpose an existing recurring job.
6. If the user explicitly asks to replace or delete the old version, first list jobs to get the exact old job ID, then create and verify the replacement job before removing the old one. This avoids leaving the user without a working recurring task if the new script or schedule is wrong. Treat local file cleanup as a separate step from cron removal unless the user clearly asked for disk cleanup too.
7. For local report-generation jobs, store durable artifacts inside the requested project subdirectory: a state file, a rolling index file, and date-stamped daily reports.
8. When the user asks to run a no_agent=true local report job immediately, do not treat cronjob(action='run') as sufficient verification of finished output. Trigger the cron run, then verify the durable artifact itself — check the target state/report/index files for a new run record or rerun the underlying project script once in the job's workdir and confirm whether it produced new items or a deduplicated no-change pass.

For literature-monitoring jobs specifically, see references/cron-literature-watchers.md for a reusable pattern covering RSS trackers, PubMed trackers, local state files, and source-specific abstract/summary extraction fallbacks.

For a reusable example covering daily literature / report-generation jobs that write artifacts into a project directory, see references/cron-local-report-jobs.md.

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 (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.

Section	Key options
model	default, provider, base_url, api_key, context_length
agent	max_turns (90), tool_use_enforcement
terminal	backend (local/docker/ssh/modal), cwd, timeout (180)
compression	enabled, threshold (0.50), target_ratio (0.20)
display	skin, tool_progress, show_reasoning, show_cost
stt	enabled, provider (local/groq/openai/mistral)
tts	provider (edge/elevenlabs/openai/minimax/mistral/neutts)
memory	memory_enabled, user_profile_enabled, provider
security	tirith_enabled, website_blocklist
delegation	model, provider, base_url, api_key, max_iterations (50), reasoning_effort
checkpoints	enabled, max_snapshots (50)

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

Providers

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

Provider	Auth	Key env var
OpenRouter	API key	OPENROUTER_API_KEY
Anthropic	API key	ANTHROPIC_API_KEY
Nous Portal	OAuth	hermes auth
OpenAI Codex	OAuth	hermes auth
GitHub Copilot	Token	COPILOT_GITHUB_TOKEN
Google Gemini	API key	GOOGLE_API_KEY or GEMINI_API_KEY
DeepSeek	API key	DEEPSEEK_API_KEY
xAI / Grok	API key	XAI_API_KEY
Hugging Face	Token	HF_TOKEN
Z.AI / GLM	API key	GLM_API_KEY
MiniMax	API key	MINIMAX_API_KEY
MiniMax CN	API key	MINIMAX_CN_API_KEY
Kimi / Moonshot	API key	KIMI_API_KEY
Alibaba / DashScope	API key	DASHSCOPE_API_KEY
Xiaomi MiMo	API key	XIAOMI_API_KEY
Kilo Code	API key	KILOCODE_API_KEY
AI Gateway (Vercel)	API key	AI_GATEWAY_API_KEY
OpenCode Zen	API key	OPENCODE_ZEN_API_KEY
OpenCode Go	API key	OPENCODE_GO_API_KEY
Qwen OAuth	OAuth	hermes login --provider qwen-oauth
Custom endpoint	Config	model.base_url + model.api_key in config.yaml
GitHub Copilot ACP	External	COPILOT_CLI_PATH or Copilot CLI

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

Toolsets

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

Toolset	What it provides
web	Web search and content extraction
browser	Browser automation (Browserbase, Camofox, or local Chromium)
terminal	Shell commands and process management
file	File read/write/search/patch
code_execution	Sandboxed Python execution
vision	Image analysis
image_gen	AI image generation
tts	Text-to-speech
skills	Skill browsing and management
memory	Persistent cross-session memory
session_search	Search past conversations
delegation	Subagent task delegation
cronjob	Scheduled task management
clarify	Ask user clarifying questions
messaging	Cross-platform message sending
search	Web search only (subset of web)
todo	In-session task planning and tracking
rl	Reinforcement learning tools (off by default)
moa	Mixture of Agents (off by default)
homeassistant	Smart home control (off by default)

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)

Provider	Env var	Free?
Edge TTS	None	Yes (default)
ElevenLabs	ELEVENLABS_API_KEY	Free tier
OpenAI	VOICE_TOOLS_OPENAI_KEY	Paid
MiniMax	MINIMAX_API_KEY	Paid
Mistral (Voxtral)	MISTRAL_API_KEY	Paid
NeuTTS (local)	None (pip install neutts[all] + espeak-ng)	Free

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

	delegate_task	Spawning hermes process
Isolation	Separate conversation, shared process	Fully independent process
Duration	Minutes (bounded by parent loop)	Hours/days
Tool access	Subset of parent's tools	Full tool access
Interactive	No	Yes (PTY mode)
Use case	Quick parallel subtasks	Long autonomous missions

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: gh auth login tokens do NOT work for Copilot API. You must use the Copilot-specific OAuth device code flow via hermes model → GitHub Copilot.

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

TUI startup fails with --expose-gc is not allowed in NODE_OPTIONS

If hermes --tui dies immediately with a Node error like:

/home/qiao/anaconda3/bin/node: --expose-gc is not allowed in NODE_OPTIONS

then the TUI launcher is injecting --expose-gc into NODE_OPTIONS, but this Node build only allows it as a direct CLI flag.

How to confirm:

NODE_OPTIONS='--expose-gc' node -e 'console.log("ok")'          # fails
node --expose-gc -e 'console.log(typeof global.gc)'              # succeeds

Where to inspect in source:

• hermes_cli/main.py TUI launcher code that mutates env["NODE_OPTIONS"]

Correct fix:

• keep --max-old-space-size=8192 in NODE_OPTIONS if desired
• remove --expose-gc from NODE_OPTIONS
• pass --expose-gc directly in the Node argv used to launch dist/entry.js

Safe workaround until patched:

hermes          # use classic CLI instead of `hermes --tui`

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 bot silent: Must enable Message Content Intent in Bot → Privileged Gateway Intents.
• 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.

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

Looking for...	Location
Config options	hermes config edit or Configuration docs
Available tools	hermes tools list or Tools reference
Slash commands	/help in session or Slash commands reference
Skills catalog	hermes skills browse or Skills catalog
Provider setup	hermes model or Providers guide
Platform setup	hermes gateway setup or Messaging docs
MCP servers	hermes mcp list or MCP guide
Profiles	hermes profile list or Profiles docs
Cron jobs	hermes cron list or Cron docs
Memory	hermes memory status or Memory docs
Env variables	hermes config env-path or Env vars reference
CLI commands	hermes --help or CLI reference
Gateway logs	~/.hermes/logs/gateway.log
Session files	~/.hermes/sessions/ or hermes sessions browse
Source code	~/.hermes/hermes-agent/

---

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