OpenClaw integration

Drop-in upgrade for OpenClaw memory.

OpenClaw's built-in memory is fine for getting started, but it lacks semantic search, entity tracking, lifecycle management, and multi-agent isolation. @remnic/plugin-openclaw is a thin adapter that replaces the memory slot with the Remnic engine — all data still stays on your disk as plain markdown.

Quick install Package on npm Quick start

Install

# 1. Install the plugin package
openclaw plugins install @remnic/plugin-openclaw --pin

# 2. Wire up the memory slot automatically
remnic openclaw install

# 3. Restart the gateway
launchctl kickstart -k gui/$(id -u)/ai.openclaw.gateway
# or on Linux:
systemctl restart openclaw-gateway

# 4. Verify
remnic doctor

remnic openclaw install writes plugins.entries["openclaw-remnic"] and plugins.slots.memory = "openclaw-remnic" to ~/.openclaw/openclaw.json. OpenClaw gates memory plugins on the slots.memory key — without it, hooks never fire.

Prefer conversation? Tell any OpenClaw agent: "Install the @remnic/plugin-openclaw plugin and configure it as my memory system." It will run the install, update openclaw.json, and restart the gateway for you.

Verify the hooks are firing

After restart, the gateway log should contain:

[remnic] gateway_start fired — Remnic memory plugin is active
  id=openclaw-engram, memoryDir=~/.openclaw/workspace/memory/local

On macOS:

grep "gateway_start fired" ~/.openclaw/logs/gateway.log

If the line is missing, run remnic doctor. Each failing check includes a remediation hint pointing at remnic openclaw install.

Why replace default memory?

Hybrid search

BM25 + vector + reranking. Six pluggable backends. Find the right memory by meaning, not keyword.

Entity graph

Tracks people, projects, tools, and relationships as structured entities. Causal and timeline queries.

Lifecycle management

Active → validated → stale → archived. Old memories drop out of recall automatically.

Namespaces

Multi-agent isolation with explicit principals. Shared context for agents that should see the same memory.

Governance

Review queues, shadow/apply modes, reversible transitions. Trust-zone promotion workflow.

Lossless Context Management

Proactive session archive + hierarchical summary DAG. Context never dies when the window compacts.

Config essentials

{
  "plugins": {
    "allow": ["openclaw-remnic"],
    "slots": { "memory": "openclaw-remnic" },
    "entries": {
      "openclaw-remnic": {
        "enabled": true,
        "config": {
          // Option 1: OpenAI for extraction
          "openaiApiKey": "${OPENAI_API_KEY}"

          // Option 2: local LLM (Ollama, LM Studio)
          // "localLlmEnabled": true,
          // "localLlmUrl": "http://localhost:1234/v1",
          // "localLlmModel": "qwen2.5-32b-instruct"

          // Option 3: gateway model chain
          // "modelSource": "gateway",
          // "gatewayAgentId": "engram-llm",
          // "fastGatewayAgentId": "engram-llm-fast"
        }
      }
    }
  }
}

The full config reference has 90+ settings covering search backends, capture modes, namespaces, governance, and Memory OS features. See docs/config-reference.md.

Gateway model source (recommended)

With modelSource: "gateway", Remnic routes every LLM call — extraction, consolidation, reranking — through an OpenClaw agent persona's model chain instead of its own config. Define personas in openclaw.json → agents.list[] with a primary model and fallbacks[] array. Remnic tries each in order until one succeeds. Build multi-provider chains like Fireworks → local LLM → cloud OpenAI.

Install Remnic Quick install guide Back home