Integrations

OpenClaw

Persistent cross-session memory for OpenClaw. Replaces MEMORY.md with a structured knowledge graph that actually scales.

Why Waystone + OpenClaw

OpenClaw's built-in MEMORY.md convention is a flat file that grows without bound — it gets stuffed into every session regardless of relevance, becomes expensive and noisy as it grows, and eventually gets truncated. Waystone replaces it with a graph-based memory store:

• Retrieves only what's relevant to the current task — not everything you've ever noted
• Scales to thousands of facts without context bloat
• Retires superseded facts automatically — no manual cleanup when decisions change
• Persists across projects with full export/import portability

Token savings compared to a naive MEMORY.md approach: typically 60–80% fewer context tokens per session on a well-established project — exact savings depend on project age and query specificity. Waystone's benchmark data is available under benchmarks/ in the repo.

1. Install Waystone

# CLI in early access — request at unbidden.ai

Verify the install:

waystone --version

2. Add to openclaw.json

In your OpenClaw config file (openclaw.json), add an mcpServers block:

{
  "mcpServers": {
    "waystone": {
      "command": "waystone",
      "args": ["mcp-serve"],
      "env": {
        "WAYSTONE_PROJECT": "my-project"
      }
    }
  }
}

Replace my-project with the name you want for this project's memory store. Waystone will create it automatically the first time it's accessed.

Restart OpenClaw. You should see waystone_query, waystone_extract, waystone_stats, and waystone_list_projects in the available tools.

3. Update your agent instructions

Replace your existing MEMORY.md instructions in your OpenClaw system prompt or config with:

## Memory (Waystone)
At the start of each session, call waystone_query with a brief description of
the current task. This retrieves relevant decisions, constraints, and context
from prior sessions — only what's relevant, not everything.

After completing significant work or at the end of a session, call
waystone_extract with a summary of what was built, decided, or changed.
Waystone will structure and store the facts automatically.

Do not write to MEMORY.md. Use waystone_query and waystone_extract instead.

4. Migrate existing MEMORY.md (optional)

If you have an existing MEMORY.md, import it into Waystone before your next session:

waystone init my-project
waystone extract my-project MEMORY.md

Waystone will parse the file, extract structured facts, and merge them into the project graph. After this, you can leave MEMORY.md in place as a historical artifact or delete it — Waystone won't touch it either way.

To verify the import worked:

waystone show my-project

How it works in practice

Once configured, your OpenClaw sessions follow this pattern automatically:

1. Session start: OpenClaw calls waystone_query with the task description. Waystone returns the 10–25 most relevant facts from the project's history.
2. During the session: You work normally. OpenClaw may call waystone_query again as the task evolves.
3. Session end: OpenClaw calls waystone_extract with a summary. Waystone extracts structured facts, detects which supersede prior decisions, and updates the graph.

The graph grows across sessions. Each session starts with a sharp, relevant slice of accumulated project memory rather than a flat growing file.

Hosted API (optional)

By default, Waystone runs locally — the memory store is a SQLite file in ~/.waystone/. For cross-machine sync or team access, switch to the hosted API:

{
  "mcpServers": {
    "waystone": {
      "command": "waystone",
      "args": ["mcp-serve"],
      "env": {
        "WAYSTONE_PROJECT": "my-project",
        "WAYSTONE_API_KEY": "your-api-key",
        "WAYSTONE_REMOTE_URL": "https://api.waystone.unbidden.ai"
      }
    }
  }
}

Get an API key from the Pro or Team plan. Local mode is free and has no rate limits.

Troubleshooting