Menú
Configure, extend, or contribute to OpenAgents.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Browser automation via Playwright MCP (official Microsoft headless browser)
Image generation and manipulation via MCP
PDF parsing and extraction via MCP
Autonomous tool discovery, evaluation, and integration for agent self-enhancement
Route OpenOS tasks to the correct product skill.
Enrich CRM contacts with LinkedIn and décideur data.
| name | openagents |
| description | Configure, extend, or contribute to OpenAgents. |
| version | 2.3.0 |
| author | OpenAgents + Teknium |
| license | MIT |
| platforms | ["linux","macos","windows"] |
| metadata | {"hermes":{"tags":["hermes","setup","configuration","multi-agent","spawning","cli","gateway","development"],"homepage":"https://github.com/RemiPelloux/OpenAgents","related_skills":["open-ecosystem-hub","open-app","open-memory","claude-code","codex","opencode"]}} |
OpenAgents is an open-source AI agent framework by Nous Research that runs in your terminal, a native desktop app, messaging platforms, and IDEs. It's in 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. OpenAgents works with any LLM provider (OpenRouter, Anthropic, OpenAI, Google, DeepSeek, xAI, local models, and 20+ others) and runs on Linux, macOS, Windows, and WSL.
What makes OpenAgents different:
People use OpenAgents 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 OpenAgents 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://openagents.nousresearch.com/docs/
This skill is a concise operating guide, not the complete source of truth for every OpenAgents feature. If a OpenAgents feature, command, or setting is not mentioned here, do not treat that absence as evidence that it does not exist. Check the live repository and official docs before giving a negative answer.
Good verification targets:
hermes --help, hermes <command> --help, and openagents_cli/main.py# Install (shell installer — sets up uv, Python, the venv, and the launcher)
curl -fsSL https://openagents.nousresearch.com/install.sh | bash
# Or via PyPI (ships the TUI bundle + shell launcher)
pip install openagents # or: uv pip install openagents
# Interactive chat (default surface; set display.interface: tui to launch the Ink TUI instead)
hermes
# Single query
hermes chat -q "What is the capital of France?"
# Setup wizard / pick model+provider / health check
hermes setup
hermes model
hermes doctor
# Other surfaces
hermes desktop # launch the native desktop app (alias: hermes gui)
hermes dashboard # web admin panel + embedded chat
hermes proxy # OpenAI-compatible local proxy backed by your OAuth provider
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.
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)
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 doctor [--fix] Check dependencies and config
hermes status [--all] Show component status
Credentials (OAuth + API keys, with pooling) are managed under hermes auth — see the Credentials & Pools section below.
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
hermes mcp serve Run OpenAgents 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
How the built-in MCP client connects servers (stdio/HTTP), auto-discovers
their tools, and exposes them as first-class tools, plus catalog install
(hermes mcp install <name>): skill_view(name="openagents", file_path="references/native-mcp.md").
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 (20+): Telegram, Discord, Slack, WhatsApp (Baileys bridge + official Business Cloud API), iMessage (Photon — hermes photon setup, the BlueBubbles successor with no Mac relay), Signal, Email, SMS, Matrix, Mattermost, Microsoft Teams, LINE, SimpleX, ntfy, Google Chat, Home Assistant, DingTalk, Feishu, WeCom, Weixin (WeChat), Raft (agent network), API Server, Webhooks. Open WebUI connects via the API Server adapter. Most adapters ship under plugins/platforms/, so new ones drop in without touching core.
Platform docs: https://openagents.nousresearch.com/docs/user-guide/messaging/
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
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
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
Full setup, route config, payload templating, and event-driven agent-run
patterns: skill_view(name="openagents", file_path="references/webhooks.md").
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
hermes auth Interactive credential manager
hermes auth add [PROVIDER] Add OAuth or API-key credential
(e.g. nous, openai-codex, qwen-oauth, anthropic)
hermes auth list [PROVIDER] List pooled credentials
hermes auth remove P INDEX Remove by provider + index
hermes auth reset PROVIDER Clear exhaustion status
Multiple credentials per provider form a pool that rotates automatically and skips exhausted keys.
hermes insights [--days N] Usage analytics
hermes update Update to latest version
hermes desktop / gui Launch the native desktop app
hermes dashboard Web admin panel + embedded chat
hermes proxy OpenAI-compatible local proxy backed by an OAuth provider
hermes portal Quick setup / sign in via Nous Portal
hermes kanban <verb> Multi-agent work-queue board (init/create/list/show/assign/…)
hermes pairing list/approve/revoke DM authorization
hermes plugins list/install/remove Plugin management
hermes secrets bitwarden … External secret store (Bitwarden Secrets Manager)
hermes memory setup/status/off Memory provider config
hermes send Send a one-off message through a gateway platform
hermes completion bash|zsh Shell completions
hermes acp ACP server (IDE integration)
hermes claw migrate Migrate from OpenClaw
hermes uninstall Uninstall Hermes
For the full, authoritative command list run hermes --help (and hermes <command> --help). Plugin- and provider-supplied subcommands (e.g. hermes photon setup for iMessage) only appear once their plugin is installed/active.
Type these during an interactive chat session. New commands land fairly
often; if something below looks stale, run /help in-session for the
authoritative list or see the live slash commands reference.
The registry of record is openagents_cli/commands.py — every consumer
(autocomplete, Telegram menu, Slack mapping, /help) derives from it.
/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
/snapshot [sub] Create or restore state snapshots of OpenAgents config/state (CLI)
/background <prompt> Run prompt in background
/queue <prompt> Queue for next turn
/steer <prompt> Inject a message after the next tool call without interrupting
/agents (/tasks) Show active agents and running tasks
/resume [name] Resume a named session
/goal [text|sub] Set a standing goal OpenAgents works on across turns until achieved
(subcommands: status, pause, resume, clear)
/redraw Force a full UI repaint (CLI)
/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
/busy [sub] Control what Enter does while OpenAgents is working (CLI)
(subcommands: queue, steer, interrupt, status)
/indicator [style] Pick the TUI busy-indicator style (CLI)
(styles: kaomoji, emoji, unicode, ascii)
/footer [on|off] Toggle gateway runtime-metadata footer on final replies
/skin [name] Change theme (CLI)
/statusbar Toggle status bar (CLI)
/tools Manage tools (CLI)
/toolsets List toolsets (CLI)
/skills Search/install skills (CLI)
/skill <name> Load a skill into session
/reload-skills Re-scan ~/.openagents/skills/ for added/removed skills
/reload Reload .env variables into the running session (CLI)
/reload-mcp Reload MCP servers
/cron Manage cron jobs (CLI)
/curator [sub] Background skill maintenance (status, run, pin, archive, …)
/kanban [sub] Multi-profile collaboration board (tasks, links, comments)
/plugins List plugins (CLI)
/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 OpenAgents to latest (gateway)
/topic [sub] Enable or inspect Telegram DM topic sessions (gateway)
/platforms (/gateway) Show platform connection status (gateway)
/branch (/fork) Branch the current session
/handoff <platform> Hand the live session off to a messaging platform (CLI)
/fast Toggle priority/fast processing
/browser Open CDP browser connection
/history Show conversation history (CLI)
/save Save conversation to file (CLI)
/copy [N] Copy the last assistant response to clipboard (CLI)
/paste Attach clipboard image (CLI)
/image Attach local image file (CLI)
/help Show commands
/commands [page] Browse all commands (gateway)
/usage Token usage
/insights [days] Usage analytics
/status Session info (gateway)
/profile Active profile info
/debug Upload debug report (system info + logs) and get shareable links
/quit (/exit, /q) Exit CLI
~/.openagents/config.yaml Main configuration
~/.openagents/.env API keys and secrets (under $OPENAGENTS_HOME if set)
$OPENAGENTS_HOME/skills/ Installed skills
~/.openagents/sessions/ Gateway routing index, request dumps, *.jsonl transcripts (and optional per-session JSON snapshots when sessions.write_json_snapshots: true)
~/.openagents/state.db Canonical session store (SQLite + FTS5)
~/.openagents/logs/ Gateway and error logs
~/.openagents/auth.json OAuth tokens and credential pools
~/.openagents/openagents/ Source code (if git-installed)
Profiles use ~/.openagents/profiles/<name>/ with the same layout.
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, interface (cli/tui), tool_progress, show_reasoning, show_cost, language |
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) |
curator | enabled, consolidate (false — opt-in aux-model skill consolidation), interval_hours, stale_after_days |
Full config reference: https://openagents.nousresearch.com/docs/user-guide/configuration
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 |
| OpenCode Zen | API key | OPENCODE_ZEN_API_KEY |
| OpenCode Go | API key | OPENCODE_GO_API_KEY |
| Qwen OAuth | OAuth | hermes auth add 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://openagents.nousresearch.com/docs/integrations/providers
Enable/disable via hermes tools (interactive) or hermes tools enable/disable NAME.
| Toolset | What it provides |
|---|---|
web | Web search and content extraction |
search | Web search only (subset of web) |
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 and image-to-image editing |
video | Video analysis (video_analyze) and generation |
x_search | First-class X (Twitter) search (X OAuth or API key) |
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 |
todo | In-session task planning and tracking |
kanban | Multi-agent work-queue tools (gated to workers) |
debugging | Extra introspection/debug tools (off by default) |
safe | Minimal, low-risk toolset for locked-down sessions |
spotify | Spotify playback and playlist control |
homeassistant | Smart home control (off by default) |
discord | Discord integration tools |
discord_admin | Discord admin/moderation tools |
feishu_doc | Feishu (Lark) document tools |
feishu_drive | Feishu (Lark) drive tools |
yuanbao | Yuanbao integration tools |
rl | Reinforcement learning tools (off by default) |
Full enumeration lives in toolsets.py as the TOOLSETS dict; _HERMES_CORE_TOOLS is the default bundle most platforms inherit from.
Tool changes take effect on /reset (new session). They do NOT apply mid-conversation to preserve prompt caching.
OpenAgents injects project-level instructions into the system prompt by reading context files from the working directory. The discovery order is first match wins — only one project context source is loaded per session.
| File (in priority order) | Discovery | Use when |
|---|---|---|
.hermes.md / HERMES.md | Walks parents up to the git root, stops at git root | You want hierarchical project rules (root + per-package overrides) |
AGENTS.md / agents.md | Cwd only — subdirectory and parent copies are ignored | You want portable agent instructions that work the same in Hermes, Claude Code, Codex, etc. |
CLAUDE.md / claude.md | Cwd only | Same as AGENTS.md, Claude-flavored |
.cursorrules / .cursor/rules/*.mdc | Cwd only | Migrating from Cursor |
SOUL.md (in $OPENAGENTS_HOME) is independent and always loaded when present — it sets the agent's identity, not project rules.
.hermes.md when you want Hermes-specific behavior that lives above the cwd (root + subtree), or when you want rules to inherit from a parent directory. The parent walk stops at the git root, so a home-level .hermes.md won't leak into every project (a git repo's root is the boundary).AGENTS.md when the same project will also be worked on by other agents (Codex, Claude Code, OpenCode). Those tools all have their own conventions for AGENTS.md, and the "cwd only" contract keeps the file portable.~/.openagents/AGENTS.md (or any other home-level location). When OpenAgents runs with that directory as cwd, the file loads — but only for that one directory. For cross-project context, use SOUL.md (in $OPENAGENTS_HOME, identity-only) or install a skill via hermes skills install.Each context file is capped at 20,000 characters. Files longer than that get head + tail truncated (the middle is dropped, with a [...truncated...] marker). For large project rules, prefer splitting into multiple skills over cramming one file.
All context files pass through the threat-pattern scanner before reaching the system prompt. Patterns matching prompt injection or promptware are replaced with a [BLOCKED: ...] placeholder. This means an AGENTS.md containing obvious injection attempts won't reach the model — the scanner blocks the content, not the file, so the rest of the file still loads.
hermes --ignore-rules skips auto-injection of all project context files (.hermes.md, AGENTS.md, CLAUDE.md, .cursorrules) and SOUL.md identity, plus user config, plugins, and MCP servers. Use it to isolate whether a problem is your setup or OpenAgents itself.
.hermes.md# My Project
Hermes: when working in this repo, follow these rules.
## Build
- Always run `make test` before declaring a change done.
- Use `uv run` for Python, not `pip install`.
## Style
- Prefer `pathlib.Path` over `os.path`.
- No `print()` in production code — use the `logger`.
That file at /home/me/projects/myrepo/.hermes.md is auto-loaded when OpenAgents runs in any subdirectory of /home/me/projects/myrepo, but not when it runs in /home/me/other-project.
Common "why is OpenAgents 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 is on by default — tool output (terminal stdout, read_file, web content, subagent summaries, etc.) is scanned for strings that look like API keys, tokens, and secrets before it enters the conversation context and logs. Leave it enabled for normal use:
hermes config set security.redact_secrets true # keep enabled globally
Restart required. security.redact_secrets is snapshotted at import time — toggling it mid-session (e.g. via export HERMES_REDACT_SECRETS=false from a tool call) will NOT take effect for the running process. Tell the user to change it in config from a terminal, then start a new session. This is deliberate — it prevents an LLM from flipping the toggle on itself mid-task.
Disable only when you deliberately need raw credential-like strings for debugging or redactor development:
hermes config set security.redact_secrets false
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)
By default (approvals.mode: manual), OpenAgents 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-riskoff — 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=1Note: YOLO / approvals.mode: off does NOT turn off secret redaction. They are independent.
Some shell-hook integrations require explicit allowlisting before they fire. Managed via ~/.openagents/shell-hooks-allowlist.json — prompted interactively the first time a hook wants to run.
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 messages from messaging platforms are auto-transcribed.
Provider priority (auto-detected):
pip install faster-whisperGROQ_API_KEYVOICE_TOOLS_OPENAI_KEYMISTRAL_API_KEYConfig:
stt:
enabled: true
provider: local # local, groq, openai, mistral
local:
model: base # tiny, base, small, medium, large-v3
| 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.
Run additional OpenAgents processes as fully independent subprocesses — separate sessions, tools, and environments.
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 |
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)
OpenAgents 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 'openagents'", 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)
# 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)
# 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)
delegate_task for quick subtasks — less overhead than spawning a full process-w (worktree mode) when spawning agents that edit code — prevents git conflictshermes chat -q for fire-and-forget — no PTY needed\r vs \n issues with prompt_toolkitcronjob tool instead of spawning — handles delivery and retryFour systems run alongside the main conversation loop. Quick reference
here; full developer notes live in AGENTS.md, user-facing docs under
website/docs/user-guide/features/.
delegate_task)Spawn a subagent with an isolated context + terminal session.
delegate_task(goal, context, toolsets).delegate_task(tasks=[{goal, ...}, ...]) runs children in
parallel, capped by delegation.max_concurrent_children (default 3).delegate_task(background=true) returns a handle
immediately and keeps the parent loop going; the child's result
re-enters the conversation as a new turn when it finishes.leaf (default; cannot re-delegate) vs orchestrator
(can spawn its own workers, bounded by delegation.max_spawn_depth).cronjob or
terminal(background=True, notify_on_complete=True).Config: delegation.* in config.yaml.
Durable scheduler — cron/jobs.py + cron/scheduler.py. Drive it via
the cronjob tool, the hermes cron CLI (list, add, edit,
pause, resume, run, remove), or the /cron slash command.
"30m", "2h"), "every" phrase
("every monday 9am"), 5-field cron ("0 9 * * *"), or ISO timestamp.skills, model/provider override, script
(pre-run data collection; no_agent=True makes the script the whole
job), context_from (chain job A's output into job B), workdir
(run in a specific dir with its AGENTS.md / CLAUDE.md loaded),
multi-platform delivery..tick.lock file
prevents duplicate ticks across processes, cron sessions pass
skip_memory=True by default, and cron deliveries are framed with a
header/footer instead of being mirrored into the target gateway
session (keeps role alternation intact).User docs: https://openagents.nousresearch.com/docs/user-guide/features/cron
Background maintenance for agent-created skills. Tracks usage, marks idle skills stale, archives stale ones, keeps a pre-run tar.gz backup so nothing is lost.
hermes curator <verb> — status, run, pause, resume,
pin, unpin, archive, restore, prune, backup, rollback./curator <subcommand> mirrors the CLI.created_by: "agent" provenance.
Bundled + hub-installed skills are off-limits. Never deletes —
max destructive action is archive. Pinned skills are exempt from
every auto-transition and every LLM review pass.curator.consolidate: true or
hermes curator run --consolidate. Routine background curation costs
zero tokens.~/.openagents/skills/.usage.json holds
per-skill use_count, view_count, patch_count,
last_activity_at, state, pinned.Config: curator.* (enabled, interval_hours, min_idle_hours,
stale_after_days, archive_after_days, backup.*).
User docs: https://openagents.nousresearch.com/docs/user-guide/features/curator
Durable SQLite board for multi-profile / multi-worker collaboration.
Users drive it via hermes kanban <verb>; dispatcher-spawned workers
see a focused kanban_* toolset gated by HERMES_KANBAN_TASK, and
orchestrator profiles can opt into the broader kanban toolset. Normal
sessions still have zero kanban_* schema footprint unless configured.
init, create, list (alias ls),
show, assign, link, unlink, comment, complete, block,
unblock, archive, tail. Less common: watch, stats, runs,
log, dispatch, daemon, gc.kanban_show, kanban_complete,
kanban_block, kanban_heartbeat, kanban_comment, kanban_create,
kanban_link; profiles that explicitly enable the kanban toolset
outside a dispatcher-spawned task also get kanban_list and
kanban_unblock for board routing.kanban.dispatch_in_gateway: true) — reclaims stale claims,
promotes ready tasks, atomically claims, spawns assigned profiles.
Auto-blocks a task after failure_limit consecutive spawn failures
(default 2; configurable via kanban.failure_limit or per-task
max_retries).HERMES_KANBAN_BOARD pinned in env); tenant is a soft namespace
within a board for workspace-path + memory-key isolation.User docs: https://openagents.nousresearch.com/docs/user-guide/features/kanban
Beyond the CLI and gateway, a few things worth knowing about:
hermes desktop / hermes gui) — native Electron app
for macOS/Linux/Windows: streaming chat, session list, drag-and-drop +
clipboard-paste files, Cmd+K palette, status-bar model picker,
rebindable shortcuts, native notifications, live subagent watch-windows,
VS Code Marketplace themes, and per-profile remote-gateway login (OAuth
or username/password) so a thin local GUI can drive a heavy remote agent.hermes dashboard) — full admin panel: configure
every messaging channel, the MCP catalog, webhooks/hooks, memory, and a
complete profile builder (model + skills + MCPs) from the browser, plus
an embedded hermes --tui chat. Secured behind an OAuth/token gate.hermes proxy) — exposes a
http://localhost:port OpenAI API backed by whichever OAuth provider
you're signed into (Claude Pro, ChatGPT Pro, SuperGrok). Point Codex
CLI, Aider, Cline, Continue, or any script at it — no API key.memory tool batch operations — pass an operations array of
add/replace/remove edits applied atomically against the final character
budget, so a single call can free space and add entries even when an add
alone would overflow.session_search — FTS5-backed, no aux-LLM, effectively free. One
tool, three modes inferred from which args are set: discovery (query),
scroll (session_id + around_message_id), browse (no args).grok-composer-2.5-fast coding model.OpenAgents runs natively on Windows (PowerShell, cmd, Windows Terminal, git-bash mintty, VS Code integrated terminal). Most of it just works, but a handful of differences between Win32 and POSIX have bitten us — document new ones here as you hit them so the next person (or the next session) doesn't rediscover them from scratch.
Alt+Enter doesn't insert a newline — Windows Terminal (and mintty) grab it
for fullscreen before prompt_toolkit sees it. Use Ctrl+Enter instead (the
CLI binds it to newline on Windows; raw Ctrl+J does the same, harmlessly).
To inspect how your terminal reports a keystroke, run
python scripts/keystroke_diagnostic.py from the repo root.
HTTP 400 "No models provided" on first run — config.yaml was saved with
a UTF-8 BOM (Notepad does this). Re-save as UTF-8 without BOM;
hermes config edit writes correctly.
execute_code / SandboxWinError 10106 from the sandbox child process — it can't create an
AF_INET socket. Root cause is usually Hermes's env scrubber dropping
SYSTEMROOT/WINDIR/COMSPEC (Python's socket needs SYSTEMROOT to find
mswsock.dll), not a broken Winsock LSP. The _WINDOWS_ESSENTIAL_ENV_VARS
allowlist in tools/code_execution_tool.py covers it; if you still hit it,
echo os.environ inside an execute_code block to confirm SYSTEMROOT is set.
scripts/run_tests.sh is POSIX-only (expects .venv/bin/activate); the
Hermes-installed venv/Scripts/ has no pip/pytest (stripped for size).
Install pytest into a system Python and run directly with -n 0
(pyproject.toml's addopts already sets -n):
"/c/Program Files/Python311/python" -m pip install --user pytest pytest-xdist pyyaml
export PYTHONPATH="$(pwd)"
"/c/Program Files/Python311/python" -m pytest tests/foo/test_bar.py -v --tb=short -n 0
(POSIX-only tests need skip guards — see the cross-platform guard list in the Contributor section below.)
Line endings. Git may warn LF will be replaced by CRLF. Cosmetic — the
repo's .gitattributes normalizes. Don't let editors auto-convert committed
POSIX-newline files to CRLF.
Forward slashes work almost everywhere. C:/Users/... is accepted by
every OpenAgents tool and most Windows APIs. Prefer forward slashes in code
and logs — avoids shell-escaping backslashes in bash.
stt.enabled: true in config.yamlpip install faster-whisper or set API key/restart. In CLI: exit and relaunch.hermes tools — check if toolset is enabled for your platform.env)/reset after enabling toolshermes doctor — check config and dependencieshermes auth — re-authenticate OAuth providers (or hermes auth add <provider>).env has the right API keygh auth login tokens do NOT work for Copilot API. You must use the Copilot-specific OAuth device code flow via hermes model → GitHub Copilot./reset starts a new session with updated toolset/restart. In CLI: exit and relaunch.hermes skills list — verify installedhermes skills config — check platform enablement/skill name or hermes -s nameCheck logs first:
grep -i "failed to send\|error" ~/.openagents/logs/gateway.log | tail -20
Common gateway problems:
sudo loginctl enable-linger $USERsystemd=true in /etc/wsl.conf for systemd services to work. Without it, gateway falls back to nohup (dies when session closes).systemctl --user reset-failed openagents-gatewaymessage.channels event. Without it, the bot ignores public channels.Alt+Enter newline, WinError 10106, UTF-8 BOM config, test suite, line endings): see the dedicated Windows-Specific Quirks section above.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>
| 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 | ~/.openagents/logs/gateway.log |
| Session files | hermes sessions browse (reads state.db) |
| Source code | ~/.openagents/openagents/ |
For occasional contributors and PR authors. Full developer docs: https://openagents.nousresearch.com/docs/developer-guide/
openagents/
├── run_agent.py # AIAgent — core conversation loop
├── model_tools.py # Tool discovery and dispatch
├── toolsets.py # Toolset definitions
├── cli.py # Interactive CLI (HermesCLI)
├── openagents_state.py # SQLite session store
├── agent/ # Prompt builder, context compression, memory, model routing, credential pooling, skill dispatch
├── openagents_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/ # Extensive pytest suite (run via scripts/run_tests.sh)
└── website/ # Docusaurus docs site
Config: ~/.openagents/config.yaml (settings), ~/.openagents/.env (API keys) — both under $OPENAGENTS_HOME when it is set.
Two files. Auto-discovery imports any tools/*.py with a top-level
registry.register() call, but a tool is only exposed to an agent once
its name appears in a toolset.
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. Wire it into a toolset in toolsets.py — add the name to
_HERMES_CORE_TOOLS (every platform) or to a specific toolset.
All handlers must return JSON strings. Use get_openagents_home() for paths,
never hardcode ~/.openagents. For custom/local-only tools, write a plugin in
~/.openagents/plugins/ instead of editing core — see the developer docs.
CommandDef to COMMAND_REGISTRY in openagents_cli/commands.pycli.py → process_command()gateway/run.pyAll consumers (help text, autocomplete, Telegram menu, Slack mapping) derive from the central registry automatically.
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
Use the canonical runner — it enforces CI-parity (hermetic env, unset credentials, TZ=UTC, xdist workers, per-test subprocess isolation):
scripts/run_tests.sh # full suite
scripts/run_tests.sh tests/tools/ # one directory
scripts/run_tests.sh tests/tools/test_x.py # one file
scripts/run_tests.sh -v --tb=long # pass-through pytest flags
OPENAGENTS_HOME to temp dirs — never touch real ~/.openagents/..venv, then venv, then the shared worktree venv.Cross-platform test guards: tests using POSIX-only syscalls need a skip marker. Common ones already in the codebase:
@pytest.mark.skipif(sys.platform == "win32", reason="Symlinks require elevated privileges on Windows") (see tests/cron/test_cron_script.py)@pytest.mark.skipif(sys.platform.startswith("win"), reason="POSIX mode bits not enforced on Windows") (see tests/openagents_cli/test_auth_toctou_file_modes.py)signal.SIGALRM → Unix-only (see tests/conftest.py::_enforce_test_timeout)@pytest.mark.skipif(sys.platform != "win32", reason="Windows-specific regression")Monkeypatching sys.platform is not enough when the code under test also calls platform.system() / platform.release() / platform.mac_ver(). Those functions re-read the real OS independently, so a test that sets sys.platform = "linux" on a Windows runner will still see platform.system() == "Windows" and route through the Windows branch. Patch all three together:
monkeypatch.setattr(sys, "platform", "linux")
monkeypatch.setattr(platform, "system", lambda: "Linux")
monkeypatch.setattr(platform, "release", lambda: "6.8.0-generic")
See tests/agent/test_prompt_builder.py::TestEnvironmentHints for a worked example.
Factual host/backend guidance (OS, $HOME, cwd, terminal backend, shell)
is emitted by agent/prompt_builder.py::build_environment_hints(). The key
invariant for prompt authors: with a remote terminal backend
(docker, singularity, modal, daytona, ssh, managed_modal), host info is
suppressed and every file tool runs inside the backend container — the
prompt must never describe the host the agent can't touch.
type: concise subject line
Optional body.
Types: fix:, feat:, refactor:, docs:, chore:
get_openagents_home() from openagents_constants for all paths (profile-safe)config.yaml, secrets go in .envcheck_fn so they only appear when requirements are met