Give your OpenClaw agents persistent, structured memory across sessions.
BEE hooks into the OpenClaw lifecycle and:
Beliefs live in a SQLite database (vector.db) and persist indefinitely across restarts.
From npm (recommended):
npm install -g @skysphere-labs/openclaw-bee
From GitHub (latest):
npm install -g github:skysphere-labs/openclaw-bee
Add BEE to your extensions in ~/.openclaw/openclaw.json:
{
"extensions": {
"entries": {
"bee": {
"enabled": true,
"config": {
"dbPath": "~/.openclaw/workspace/state/vector.db",
"agentId": "main",
"extractionEnabled": true,
"extractionModel": "anthropic/claude-haiku-4-5",
"maxCoreBeliefs": 10,
"maxActiveBeliefs": 5,
"maxRecalledBeliefs": 5
}
}
}
}
}
openclaw gateway restart
BEE will run its database migration on first start and begin capturing beliefs.
| Option | Default | Description |
|---|---|---|
| -------- | --------- | ------------- |
dbPath | required | Path to your SQLite database |
agentId | "main" | Namespace for belief scoping |
extractionEnabled | true | Enable/disable belief extraction |
extractionModel | "anthropic/claude-haiku-4-5" | Model used for extraction (cheapest works well) |
extractionMinConfidence | 0.55 | Minimum confidence to store a belief (0-1) |
maxCoreBeliefs | 10 | Core beliefs injected into every session |
maxActiveBeliefs | 5 | Recently active beliefs injected |
maxRecalledBeliefs | 5 | Semantically recalled beliefs per query |
maxOutputChars | 2000 | Max chars of belief context injected |
debug | false | Enable verbose logging |
spawnBudgetWarning | 20 | Warn when subagent spawns exceed this threshold |
After restart, ask your agent:
> "How many beliefs do you have?"
Or check directly:
sqlite3 ~/.openclaw/workspace/state/vector.db "SELECT COUNT(*) FROM beliefs"
You should see beliefs accumulate after sessions complete.
For setups with multiple named agents (VECTOR, FORGE, ORACLE, etc.), use different agentId values per agent spawn. BEE scopes beliefs by agentId so each PM has isolated memory.
共 1 个版本