OpenClaw with Cognee Cloud

Register Cognee Cloud as OpenClaw’s memory provider with multi-scope recall.

Give your OpenClaw agents Cognee-backed memory sourced from your Cognee Cloud tenant. The plugin indexes your Markdown memory files, recalls relevant context before each run, and searches the knowledge graph built from past sessions with natural language — with optional multi-scope routing (company / user / agent).

1. Install the plugin

openclaw plugins install @cognee/cognee-openclaw@2026.9.22

Or install locally for development:

cd integrations/openclaw
npm install && npm run build
openclaw plugins install --link .

2. Run setup

openclaw cognee setup              # Cognee only (replaces built-in memory)
openclaw cognee setup --hybrid     # keep built-in memory enabled in config

3. Connect to Cognee Cloud

Cognee Cloud tenants serve the same /api/v1/* API as a self-hosted server, so connecting is just the default config pointed at your tenant URL with an API key. Edit ~/.openclaw/openclaw.json:

{
  "plugins": {
    "entries": {
      "cognee-openclaw": {
        "enabled": true,
        "hooks": {
          "allowPromptInjection": true,
          "allowConversationAccess": true
        },
        "config": {
          "baseUrl": "https://your-tenant.aws.cognee.ai",
          "apiKey": "${COGNEE_API_KEY}",
          "datasetName": "my-project"
        }
      }
    }
  }
}

COGNEE_API_KEY is mandatory for a cloud tenant — cloud tenants expose no login route, so there’s nothing to auto-mint. Set it in the environment the gateway process starts from (a daemonized gateway doesn’t see exports from your current shell), using a key from the API Keys page:

export COGNEE_API_KEY="<your-api-key>"

allowConversationAccess: true is the one that is strictly required: OpenClaw withholds the conversation hooks (llm_output, agent_end) from installed plugins without it, so Q&A session capture and post-run file sync are silently skipped. allowPromptInjection gates the prompt-injection hooks (before_prompt_build) that carry recall; it defaults to allowed, but openclaw cognee setup writes it explicitly because it also signals hook startup intent. Restart the gateway after changing either: openclaw gateway stop && openclaw gateway start.

Leave mode at its default — do not set mode: "cloud". That mode switches every request to a legacy path scheme without the /api/v1 prefix, which current tenants don’t serve. All operations — file sync, updates, recall, session capture, and improve — work against Cloud through the standard /api/v1/* paths.

4. Verify

openclaw cognee health     # verify Cognee API connectivity
openclaw cognee status     # files indexed, dataset info, per-scope breakdown

A healthy status shows the dataset ID, indexed file count, and a recent last-sync timestamp.

Multi-scope memory

Enable multi-scope mode by setting any scope-specific dataset name; memory files are routed to the right dataset by path:

Scope	Purpose	Example files
Company	Shared knowledge across all users/agents	memory/company/policies.md
User	Per-user preferences, feedback, corrections	memory/user/preferences.md
Agent	Per-agent learned behaviors, tool outputs	memory/tools.md, MEMORY.md

See the full integration guide for the complete config, search types, and CLI reference.

---

Full integration guide

Multi-scope config, search types, and troubleshooting

OpenClaw Docs

Learn about OpenClaw’s memory system