Documentation Index
Fetch the complete documentation index at: https://docs.wednesdayai.dev/llms.txt
Use this file to discover all available pages before exploring further.
Hooks catalogue
WednesdayAI ships four bundled hooks. They are auto-discovered from dist/hooks/bundled/ and managed via the CLI.
openclaw hooks list # show all hooks with enabled/disabled status
openclaw hooks enable <name>
openclaw hooks disable <name>
openclaw hooks info <name> # requirements, config, current status
openclaw hooks check # verify all enabled hooks can load
During onboarding (openclaw onboard), the wizard prompts you to enable recommended hooks.
session-memory
Saves session context to the agent workspace when you issue /new or /reset. Useful for giving the agent a memory of previous sessions.
| Property | Value |
|---|
| Event | command:new |
| Writes to | ~/.openclaw/workspace/memory/ (default) |
| Emoji | 💾 |
Enable:
openclaw hooks enable session-memory
What it does: when a session resets, saves a structured summary of the session to the workspace memory directory. On the next session start, the agent can read this file if memory search tools are configured.
Injects additional files from configured glob/path patterns into the agent workspace when it bootstraps. Used to inject custom context files, templates, or system prompts that should always be available to the agent.
| Property | Value |
|---|
| Event | agent:bootstrap |
| Reads from | Configured glob patterns |
| Emoji | 📎 |
Enable:
openclaw hooks enable bootstrap-extra-files
Configure paths in ~/.openclaw/openclaw.json:
{
hooks: {
internal: {
entries: {
"bootstrap-extra-files": {
enabled: true,
config: {
patterns: ["~/.openclaw/context/*.md", "~/.openclaw/context/*.txt"],
},
},
},
},
},
}
command-logger
Logs all command events to a local log file. Provides an audit trail of every /command sent to the gateway.
| Property | Value |
|---|
| Event | All command:* events |
| Writes to | ~/.openclaw/logs/commands.log |
| Emoji | 📝 |
Enable:
openclaw hooks enable command-logger
Log format (JSONL, one entry per line):
{"timestamp":"2026-05-27T12:34:56.789Z","event":"command:new","sessionKey":"agent:main:whatsapp:dm:+15555550123","agentId":"main"}
boot-md
Runs BOOT.md from the agent workspace when the gateway starts. Useful for injecting startup instructions or running an initialization checklist.
| Property | Value |
|---|
| Event | gateway:start |
| Reads from | <workspace>/BOOT.md |
| Emoji | 🚀 |
| Requires | Internal hooks enabled: hooks.internal.enabled: true |
Enable:
openclaw hooks enable boot-md
Hook discovery order
Hooks are discovered in this order (highest precedence first):
<workspace>/hooks/ — per-agent hooks
~/.openclaw/hooks/ — user-installed shared hooks
<openclaw>/dist/hooks/bundled/ — bundled hooks (this catalogue)
A hook in a higher-precedence directory overrides one with the same name in a lower-precedence directory.
Installing custom hooks
openclaw hooks install ./path/to/my-hook
openclaw hooks install @wednesdayai/my-hook-pack
Dependencies are installed with npm install --ignore-scripts. Keep hook dependencies to pure JS/TS packages with no postinstall build steps.
Writing a hook
See Hooks for the full hook authoring guide, including the HookContext type, all available events, and HOOK.md frontmatter format.