Compatibility
Verification
Tags
memsearch — OpenClaw Plugin
Automatic persistent memory for OpenClaw. Every conversation turn is summarized and indexed — your next session picks up where you left off.
Prerequisites
- OpenClaw >= 2026.3.22 (2026.4+ recommended for full CLI support)
- Python 3.10+
Install
From ClawHub (recommended)
# 1. Install memsearch
uv tool install "memsearch[onnx]"
# 2. Install the plugin from ClawHub
openclaw plugins install --force clawhub:memsearch
# 3. Allow memsearch to read conversation turns and inject recall context
openclaw config set plugins.entries.memsearch.hooks.allowConversationAccess true
openclaw config set plugins.entries.memsearch.hooks.allowPromptInjection true
# 4. Restart the gateway
openclaw gateway restart
From Source (development)
# 1. Install memsearch
uv tool install "memsearch[onnx]"
# 2. Clone the repo and install the plugin
git clone https://github.com/zilliztech/memsearch.git
cd memsearch
openclaw plugins install --force ./plugins/openclaw
# 3. Allow memsearch to read conversation turns and inject recall context
openclaw config set plugins.entries.memsearch.hooks.allowConversationAccess true
openclaw config set plugins.entries.memsearch.hooks.allowPromptInjection true
# 4. Restart the gateway
openclaw gateway restart
Usage
Start a TUI session as normal:
openclaw tui
What happens automatically
| When | What |
|---|---|
| Agent starts | Recent memories injected as context |
| Each turn ends | Conversation summarized (bullet-points) and saved to daily .md |
| LLM needs history | Calls memory_search / memory_get / memory_transcript tools |
Recall memories
Two ways to trigger:
/memory-recall what was the caching strategy we chose?
Or just ask naturally — the LLM auto-invokes memory tools when it senses the question needs history:
We discussed caching strategies before, what did we decide?
Three-layer progressive recall
The plugin registers three tools the LLM uses progressively:
memory_search— Semantic search across past memories. Always starts here.memory_get— Expand a chunk to see the full markdown section with context.memory_transcript— Parse the original session transcript for exact dialogue.
The LLM decides how deep to go based on the question — simple recall uses only L1, detailed questions go to L2/L3.
Multi-agent isolation
Each OpenClaw agent stores memory independently under its own workspace:
~/.openclaw/workspace/.memsearch/memory/ ← main agent
~/.openclaw/workspace-work/.memsearch/memory/ ← work agent
Collection names are derived from the workspace path, so agents with different workspaces have isolated memories. When an agent's workspace points to a project directory used by other platforms, memories are automatically shared across platforms.
Shared memory across projects
Set MEMSEARCH_DIR to a fixed path to share a single memory store across all agents and projects:
export MEMSEARCH_DIR=~/.memsearch
openclaw tui
When MEMSEARCH_DIR is set:
- All agents write memories to that directory regardless of their workspace path.
- The collection name is derived from
MEMSEARCH_DIRinstead of the workspace path, so all agents share the same index.
Configuration
Works out of the box with zero configuration (ONNX embedding, no API key needed).
Optional settings via openclaw plugins config memsearch:
| Setting | Default | Description |
|---|---|---|
provider | onnx | Embedding provider (onnx, openai, google, voyage, jina, mistral, ollama) |
autoCapture | true | Auto-capture conversation summaries after each turn |
autoRecall | true | Auto-inject recent memories at agent start |
To override only the OpenClaw native capture summarization model:
memsearch config set plugins.openclaw.summarize.model qwen3-coder
To use a memsearch-managed API provider instead:
memsearch config set llm.providers.openai.type openai
memsearch config set llm.providers.openai.model gpt-5-mini
memsearch config set llm.providers.openai.api_key env:OPENAI_API_KEY
memsearch config set plugins.openclaw.summarize.provider openai
Leave plugins.openclaw.summarize.provider empty or set it to native to keep the default OpenClaw agent model. This setting does not fall back to llm.model.
Memory files
Each agent's memory is stored as plain markdown:
# 2026-03-25
## Session 14:47
### 14:47
<!-- session:UUID transcript:~/.openclaw/agents/main/sessions/UUID.jsonl -->
- User asked about the memsearch architecture.
- OpenClaw explained core components: chunker, scanner, embedder, MilvusStore.
These files are human-readable, editable, and version-controllable. Milvus is a derived index that can be rebuilt anytime.
Uninstall
openclaw plugins uninstall memsearch
openclaw gateway restart
Uninstalling the plugin does not delete memory files in .memsearch/memory/.