Honcho Memory for OpenClaw

Honcho is an external plugin that brings AI-native memory to OpenClaw. By persisting conversations to a dedicated service, it gradually develops models of both users and the agent, offering cross-session context that extends beyond what workspace Markdown files provide.

What it provides

Cross-session memory - every turn's conversation is saved, so context survives session resets, compaction, and channel changes.
User modeling - Honcho keeps a profile for each user (preferences, facts, communication style) and for the agent (personality, learned behaviors).
Semantic search - searches over observations from prior conversations, not just the current session.
Multi-agent awareness - parent agents automatically track spawned sub-agents, with parents added as observers in child sessions.

Available tools

During conversation, Honcho exposes tools the agent can use:

Data retrieval (fast, no LLM call):

Tool	What it does
`honcho_context`	Full user representation across sessions
`honcho_search_conclusions`	Semantic search over stored conclusions
`honcho_search_messages`	Find messages across sessions (filter by sender, date)
`honcho_session`	Current session history and summary

Q&A (LLM-powered):

Tool	What it does
`honcho_ask`	Ask about the user. `depth='quick'` for facts, `'thorough'` for synthesis

Getting started

Get the plugin installed and run setup:

openclaw plugins install @honcho-ai/openclaw-honcho
openclaw honcho setup
openclaw gateway --force

The setup command asks for your API credentials, writes the config, and can optionally migrate existing workspace memory files.

Info

Honcho supports fully local (self-hosted) operation or the managed API at api.honcho.dev. The self-hosted option requires no external dependencies.

Configuration

Configuration lives under plugins.entries["openclaw-honcho"].config:

{
  plugins: {
    entries: {
      "openclaw-honcho": {
        config: {
          apiKey: "your-api-key", // omit for self-hosted
          workspaceId: "openclaw", // memory isolation
          baseUrl: "https://api.honcho.dev",
        },
      },
    },
  },
}

For self-hosted setups, set baseUrl to your local server (like http://localhost:8000) and leave out the API key.

Migrating existing memory

If you've got existing workspace memory files (USER.md, MEMORY.md, IDENTITY.md, memory/), openclaw honcho setup will spot them and offer migration.

Info

Migration won't destroy anything: files get uploaded to Honcho. Originals are left untouched.

How it works

After each AI turn, the conversation gets saved to Honcho. Both user and agent messages are observed, which lets Honcho build and refine its models over time.

During conversation, Honcho tools query the service through OpenClaw's before_prompt_build plugin hook, injecting relevant context before the model sees the prompt.

Honcho vs builtin memory

	Builtin memory	Honcho
Storage	Workspace Markdown files	Dedicated service (local or hosted)
Cross-session	Via memory files	Automatic, built-in
User modeling	Manual (write to MEMORY.md)	Automatic profiles
Search	Vector + keyword (hybrid)	Semantic over observations
Multi-agent	Not tracked	Parent/child awareness
Dependencies	None	Plugin install

Honcho and the builtin memory system can be used side by side. Builtin search keeps local Markdown available alongside Honcho's cross-session memory.

CLI commands

openclaw honcho setup                        # Configure API key and migrate files
openclaw honcho status                       # Check connection status
openclaw honcho ask <question>               # Query Honcho about the user
openclaw honcho search <query> [-k N] [-d D] # Semantic search over memory

Honcho Memory: AI-Native Cross-Session Context for OpenClaw