OpenClaw memory plugin powered by Backboard.io — the world's highest-scoring AI memory system. Gives your AI agent persistent, semantic long-term memory that works across sessions, conversations, and time.
Most AI memory systems forget, hallucinate, or fail at multi-step reasoning over long histories. Backboard's stateful memory architecture is different — it achieved 90.1% overall accuracy on LoCoMo, the industry-standard benchmark for long-term conversational memory, setting the highest public score ever recorded.
| Method | Single-Hop | Multi-Hop | Open Domain | Temporal | Overall |
|---|---|---|---|---|---|
| Backboard | 89.36% | 75.00% | 91.20% | 91.90% | 90.10% |
| Memobase (v0.0.37) | 70.92% | 46.88% | 77.17% | 85.05% | 75.78% |
| Zep | 74.11% | 66.04% | 67.71% | 79.79% | 75.14% |
| Memobase (v0.0.32) | 63.83% | 52.08% | 71.82% | 80.37% | 70.91% |
| Mem0-Graph | 65.71% | 47.19% | 75.71% | 58.13% | 68.44% |
| Mem0 | 67.13% | 51.15% | 72.93% | 55.51% | 66.88% |
| LangMem | 62.23% | 47.92% | 71.12% | 23.43% | 58.10% |
| OpenAI | 63.79% | 42.92% | 62.29% | 21.71% | 52.90% |
Evaluated with GPT-4.1 as the LLM judge under standardized conditions. Full logs, prompts, and verdicts published for reproducibility.
Replication scripts: Backboard-io/Backboard-Locomo-Benchmark
Backboard leads in every category — single-hop recall, multi-hop reasoning, open-domain knowledge, and temporal reasoning. These are the same dimensions measured by LongMemEval (ICLR 2025), which evaluates five core long-term memory abilities: information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention. Backboard's architecture is purpose-built to excel at exactly these tasks.
- 5 agent tools —
memory_search,memory_store,memory_get,memory_list,memory_forget - Auto-recall — relevant memories injected into agent context before each turn
- Auto-capture — key facts stored automatically after each agent turn
- Session + long-term scopes — session-scoped memory (ephemeral) and assistant-scoped memory (persistent)
- Semantic search — vector-based retrieval, no keyword matching
- CLI commands —
openclaw backboard searchandopenclaw backboard stats - Zero-config assistant — auto-creates a Backboard assistant if none is specified
- 2,200+ LLM compatible — works with any model Backboard supports
- OpenClaw gateway installed
- A Backboard.io account and API key
- Node.js 22+
git clone <this-repo> ~/.openclaw/plugins/openclaw-backboard
cd ~/.openclaw/plugins/openclaw-backboard
npm installAdd the plugin to your OpenClaw config (~/.openclaw/openclaw.json):
{
"plugins": {
"load": {
"paths": ["~/.openclaw/plugins/openclaw-backboard"]
},
"entries": {
"openclaw-backboard": {
"enabled": true,
"config": {
"apiKey": "bb_your_api_key_here",
"assistantId": "",
"autoCapture": true,
"autoRecall": true,
"topK": 5
}
}
},
"slots": {
"memory": "openclaw-backboard"
}
}
}| Option | Type | Default | Description |
|---|---|---|---|
apiKey |
string |
(required) | Your Backboard API key |
assistantId |
string |
auto-created | Backboard Assistant ID. Leave empty to auto-create one named "OpenClaw Memory" |
autoCapture |
boolean |
true |
Automatically store conversation context after each agent turn |
autoRecall |
boolean |
true |
Automatically inject relevant memories before each agent turn |
topK |
number |
5 |
Maximum memories returned per search |
./start.shThis clears local cache, installs dependencies, and starts the OpenClaw gateway with the plugin loaded.
The plugin registers five tools that your AI agent can call directly:
Save information to long-term memory.
Agent, please remember that my preferred language is Python and I deploy to AWS.
The agent calls memory_store with the text. Supports optional metadata and a longTerm flag (true for assistant-scoped, false for session-scoped).
Semantic search across stored memories.
What do you remember about my deployment preferences?
Returns ranked results with relevance scores. Supports scope parameter: "session", "long-term", or "all".
List all stored memories. Useful for auditing what the agent knows.
Retrieve a specific memory by ID.
Delete a memory by ID or by search query. Single high-confidence matches are deleted immediately; multiple candidates prompt for clarification.
When autoRecall is enabled, the plugin intercepts every agent turn and:
- Takes the user's prompt
- Searches Backboard for semantically relevant memories
- Injects them into the system context as
<relevant-memories>before the LLM sees the prompt
No tool call needed — the agent simply knows relevant context from prior conversations.
When autoCapture is enabled, the plugin listens for completed agent turns and:
- Extracts the last 10 messages from the conversation
- Stores them in Backboard as a memory, tagged with
source: "auto-capture"and the currentsession_id
This means the agent builds a memory of every conversation automatically.
Inspect and search memories directly from the terminal:
# Search memories
openclaw backboard search "deployment preferences"
openclaw backboard search "favorite color" --limit 10 --scope long-term
# View stats
openclaw backboard statsRun the end-to-end smoke test to verify everything works:
./smoke_test.shThis test:
- Stores a memory via the agent
- Retrieves it via semantic search
- Confirms it in Backboard directly (CLI)
- Checks memory stats
- Deletes the memory via the agent
- Confirms deletion
┌─────────────────────────────────────────────────┐
│ OpenClaw Gateway │
│ │
│ before_agent_start ──► auto-recall (search) │
│ agent_end ──────────► auto-capture (store) │
│ │
│ Tools: memory_search | memory_store | ... │
│ CLI: openclaw backboard search | stats │
└────────────────┬────────────────────────────────┘
│ HTTPS (X-API-Key)
▼
┌─────────────────────────────────────────────────┐
│ Backboard.io API │
│ │
│ /assistants /threads /memories /messages │
│ │
│ Semantic search · Stateful threads │
│ 17,000+ models · Built-in RAG │
└─────────────────────────────────────────────────┘
openclaw-backboard/
├── src/
│ ├── index.ts # Plugin definition, tools, hooks, CLI
│ ├── backboard-client.ts # Thin HTTP client for Backboard REST API
│ └── types.ts # TypeScript interfaces (config, API responses)
├── openclaw.plugin.json # Plugin manifest
├── package.json
├── tsconfig.json
├── start.sh # Gateway launcher
└── smoke_test.sh # End-to-end verification
MIT