Hooks are small scripts that run inside the Gateway when agent events fire: commands like /new, /reset, /stop, session compaction, gateway lifecycle, and message flow. They are discovered from directories and managed with openclaw hooks. The Gateway loads internal hooks only after you enable hooks or configure at least one hook entry, hook pack, legacy handler, or extra hook directory.
There are two kinds of hooks in OpenClaw:
- Internal hooks (this page): run inside the Gateway when agent events fire.
- Webhooks: external HTTP endpoints that let other systems trigger work in OpenClaw. See Webhooks.
Hooks can also be bundled inside plugins. openclaw hooks list shows both standalone hooks and plugin-managed hooks (displayed as plugin:<id>).
Choose the right surface
OpenClaw has several extension surfaces that look similar but solve different problems:
| If you want to… | Use… | Why |
|---|
Save a snapshot on /new, log /reset, call an external API after message:sent, or add coarse operator automation | Internal hooks (HOOK.md, this page) | File-based hooks are meant for operator-managed side effects and command/lifecycle automation |
| Rewrite prompts, block tools, cancel outbound messages, or add ordered middleware/policy | Typed plugin hooks via api.on(...) | Typed hooks have explicit contracts, priorities, merge rules, and block/cancel semantics |
| Add telemetry-only export or observability | Diagnostic events | Observability is a separate event bus, not a policy hook surface |
Quick start
# List available hooks
openclaw hooks list
# Enable a hook
openclaw hooks enable session-memory
# Check hook status
openclaw hooks check
# Get detailed information
openclaw hooks info session-memory
Event types
Hooks subscribe to a specific key from this table, or to a bare family name
(command, session, agent, gateway, message) to receive every action
in that family. OpenClaw core emits nothing else, so any other name is almost
always a typo that leaves the hook silently dead (only a plugin emitting a
custom event could fire it). The hook loader logs a warning for such names
(for example command:nwe), and openclaw hooks info <name> flags them, so a
hook that never runs is diagnosable.
| Event | When it fires |
|---|
command:new | /new command issued |
command:reset | /reset command issued |
command:stop | /stop command issued |
command | Any command event (general listener) |
session:compact:before | Before compaction summarizes history |
session:compact:after | After compaction completes |
session:patch | When session properties are modified |
agent:bootstrap | Before workspace bootstrap files are injected |
gateway:startup | After channels start and hooks are loaded |
gateway:shutdown | When gateway shutdown begins |
gateway:pre-restart | Before an expected gateway restart |
message:received | Inbound message from any channel |
message:transcribed | After audio transcription completes |
message:preprocessed | After media and link preprocessing completes or is skipped |
message:sent | Outbound send attempted (context.success has the result) |
Writing hooks
Hook structure
Each hook is a directory containing two files:
my-hook/
├── HOOK.md # Metadata + documentation
└── handler.ts # Handler implementation
handler.ts, handler.js, index.ts, or index.js.
---
name: my-hook
description: "Short description of what this hook does"
metadata:
{ "openclaw": { "emoji": "🔗", "events": ["command:new"], "requires": { "bins": ["node"] } } }
---
# My Hook
Detailed documentation goes here.
metadata.openclaw):
| Field | Description |
|---|
emoji | Display emoji for CLI |
events | Array of events to listen for |
export | Named export to use (defaults to "default") |
os | Required platforms (e.g., ["darwin", "linux"]) |
requires | Required bins, anyBins, env, or config paths |
always | Bypass eligibility checks (boolean) |
hookKey | Config key override (defaults to the hook name) |
homepage | Docs URL shown by openclaw hooks info |
install | Installation methods |
Handler implementation
const handler = async (event) => {
if (event.type !== "command" || event.action !== "new") {
return;
}
console.log(`[my-hook] New command triggered`);
// Your logic here
// Optionally send a reply on replyable surfaces
event.messages.push("Hook executed!");
};
export default handler;
type, action, sessionKey, timestamp, messages, and context (event-specific data). Typed plugin hook contexts for agent and tool hooks can also include trace, a read-only W3C-compatible diagnostic trace context that plugins may pass into structured logs for OTEL correlation.
Strings pushed to event.messages are delivered back to the chat only for
command:new and command:reset (routed as a reply to the originating
conversation) and for session:compact:before / session:compact:after
(sent as compaction status notices). All other events, including
command:stop, message:*, agent:bootstrap, session:patch, and
gateway:*, ignore pushed messages.
Event context highlights
Command events (command:new, command:reset): context.sessionEntry, context.previousSessionEntry, context.commandSource, context.senderId, context.workspaceDir, context.cfg.
Command events (command:stop): context.sessionEntry, context.sessionId, context.commandSource, context.senderId.
Message events (message:received): context.from, context.content, context.channelId, context.metadata (provider-specific data including senderId, senderName, guildId). context.content prefers a nonblank command body for command-like messages, then falls back to the raw inbound body and generic body; it does not include agent-only enrichment such as thread history or link summaries.
Message events (message:sent): context.to, context.content, context.success, context.channelId, plus context.error when sending failed.
Message events (message:transcribed): context.transcript, context.from, context.channelId, context.mediaPath.
Message events (message:preprocessed): context.bodyForAgent (final enriched body), context.from, context.channelId.
Bootstrap events (agent:bootstrap): context.bootstrapFiles (mutable array), context.agentId.
Session patch events (session:patch): context.sessionEntry, context.patch (only changed fields), context.cfg. Only privileged clients can trigger patch events; the context is a clone, so handlers cannot mutate the live session entry.
Compaction events: session:compact:before includes messageCount, tokenCount. session:compact:after adds compactedCount, summaryLength, tokensBefore, tokensAfter.
command:stop observes the user issuing /stop; it is cancellation/command
lifecycle, not an agent-finalization gate. Plugins that need to inspect a
natural final answer and ask the agent for one more pass should use the typed
plugin hook before_agent_finalize instead. See Plugin hooks.
Gateway lifecycle events: gateway:shutdown includes reason and restartExpectedMs and fires when gateway shutdown begins. gateway:pre-restart includes the same context but only fires when shutdown is part of an expected restart and a finite restartExpectedMs value is supplied. During shutdown, each lifecycle hook wait is best-effort and bounded so shutdown continues if a handler stalls. The default wait budget is 5 seconds for gateway:shutdown and 10 seconds for gateway:pre-restart.
Use gateway:pre-restart for short restart notices while channels are still available:
import { execFile } from "node:child_process";
import { promisify } from "node:util";
const execFileAsync = promisify(execFile);
export default async function handler(event) {
if (event.type !== "gateway" || event.action !== "pre-restart") {
return;
}
const restartInSeconds = Math.ceil(event.context.restartExpectedMs / 1000);
await execFileAsync("openclaw", [
"system",
"event",
"--mode",
"now",
"--text",
`Gateway restarting in ~${restartInSeconds}s (${event.context.reason}). Checkpoint now.`,
]);
}
gateway:shutdown (or gateway:pre-restart) event and the rest of the shutdown sequence, the gateway also fires a typed session_end plugin hook for every session that was still active when the process stopped. The event’s reason is shutdown for a plain SIGTERM/SIGINT stop and restart when the close was scheduled as part of an expected restart. This drain is bounded so a slow session_end handler cannot block process exit, and sessions that have already been finalized through replace / reset / delete / compaction are skipped to avoid double-firing.
Hook discovery
Hooks are discovered from four sources:
- Bundled hooks: shipped with OpenClaw
- Plugin hooks: bundled inside installed plugins; can override bundled hooks with the same name
- Managed hooks:
~/.openclaw/hooks/ (user-installed, shared across workspaces); can override bundled and plugin hooks. Extra directories from hooks.internal.load.extraDirs share this precedence.
- Workspace hooks:
<workspace>/hooks/ (per-agent, disabled by default until explicitly enabled)
Workspace hooks can add new hook names but cannot override bundled, managed, or plugin-provided hooks with the same name.
The Gateway skips internal hook discovery on startup until internal hooks are configured. Enable a bundled or managed hook with openclaw hooks enable <name>, install a hook pack, or set hooks.internal.enabled=true to opt in. When you enable one named hook, the Gateway loads only that hook’s handler; hooks.internal.enabled=true, extra hook directories, and legacy handlers opt into broad discovery.
Hook packs
Hook packs are npm packages that export hooks via openclaw.hooks in package.json. Install with:
openclaw plugins install <path-or-spec>
openclaw hooks install and openclaw hooks update commands are deprecated aliases for openclaw plugins install / openclaw plugins update.
Bundled hooks
| Hook | Events | What it does |
|---|
| session-memory | command:new, command:reset | Saves session context to <workspace>/memory/ |
| bootstrap-extra-files | agent:bootstrap | Injects additional bootstrap files from glob patterns |
| command-logger | command | Logs all commands to ~/.openclaw/logs/commands.log |
| compaction-notifier | session:compact:before, session:compact:after | Sends visible chat notices when session compaction starts/ends |
| boot-md | gateway:startup | Runs BOOT.md when the gateway starts |
openclaw hooks enable <hook-name>
session-memory details
Extracts the last user/assistant messages (default 15, configurable with hooks.internal.entries.session-memory.messages) and saves them to <workspace>/memory/YYYY-MM-DD-HHMM.md using the host local date. Memory capture runs in the background so /new and /reset acknowledgements are not delayed by transcript reads or optional slug generation. Set hooks.internal.entries.session-memory.llmSlug: true to generate descriptive filename slugs with the configured model (falls back to timestamp slugs when unavailable). Requires workspace.dir to be configured.
{
"hooks": {
"internal": {
"entries": {
"bootstrap-extra-files": {
"enabled": true,
"paths": ["packages/*/AGENTS.md", "packages/*/TOOLS.md"]
}
}
}
}
}
patterns and files are accepted as aliases of paths. Paths resolve relative to the workspace and must stay inside it. Only recognized bootstrap basenames are loaded (AGENTS.md, SOUL.md, TOOLS.md, IDENTITY.md, USER.md, HEARTBEAT.md, BOOTSTRAP.md, MEMORY.md).
command-logger details
Logs every slash command as a JSON line (timestamp, action, session key, sender ID, source) to ~/.openclaw/logs/commands.log.
compaction-notifier details
Sends short status messages into the current conversation when OpenClaw starts and finishes compacting the session transcript. This makes long turns less confusing on chat surfaces because the user can see that the assistant is summarizing context and will continue after compaction.
boot-md details
Runs BOOT.md at gateway startup for each configured agent scope, if the file exists in that agent’s resolved workspace.
Plugin hooks
Plugins can register typed hooks through the Plugin SDK for deeper integration:
intercepting tool calls, modifying prompts, controlling message flow, and more.
Use plugin hooks when you need before_tool_call, before_agent_reply,
before_install, or other in-process lifecycle hooks.
Plugin-managed internal hooks are different: they participate in this page’s
coarse command/lifecycle event system and show up in openclaw hooks list as
plugin:<id>. Use those for side effects and compatibility with hook packs, not
for ordered middleware or policy gates.
For the complete plugin hook reference, see Plugin hooks.
Configuration
{
"hooks": {
"internal": {
"enabled": true,
"entries": {
"session-memory": { "enabled": true },
"command-logger": { "enabled": false }
}
}
}
}
requires.env eligibility checks (alongside the process environment), and handlers can read them from their hook config entry:
{
"hooks": {
"internal": {
"entries": {
"my-hook": {
"enabled": true,
"env": { "MY_CUSTOM_VAR": "value" }
}
}
}
}
}
{
"hooks": {
"internal": {
"load": {
"extraDirs": ["/path/to/more/hooks"]
}
}
}
}
The legacy hooks.internal.handlers array config format is still supported for backwards compatibility, but new hooks should use the discovery-based system.
CLI reference
# List all hooks (add --eligible, --verbose, or --json)
openclaw hooks list
# Show detailed info about a hook
openclaw hooks info <hook-name>
# Show eligibility summary
openclaw hooks check
# Enable/disable
openclaw hooks enable <hook-name>
openclaw hooks disable <hook-name>
Best practices
- Keep handlers fast. Hooks run during command processing. Fire-and-forget heavy work with
void processInBackground(event).
- Handle errors gracefully. Wrap risky operations in try/catch; do not throw so other handlers can run.
- Filter events early. Return immediately if the event type/action is not relevant.
- Use specific event keys. Prefer
"events": ["command:new"] over "events": ["command"] to reduce overhead.
Troubleshooting
Hook not discovered
# Verify directory structure
ls -la ~/.openclaw/hooks/my-hook/
# Should show: HOOK.md, handler.ts
# List all discovered hooks
openclaw hooks list
Hook not eligible
openclaw hooks info my-hook
Hook not executing
- Verify the hook is enabled:
openclaw hooks list
- Restart your gateway process so hooks reload.
- Check gateway logs:
openclaw logs --follow | grep -i hook
