← Back to Skills Marketplace
claw-mem: Three-Tier Memory
by
Peter Cheng
· GitHub ↗
· v2.0.1
· MIT-0
78
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install opensourceclaw-claw-mem
Description
Three-Tier Memory System for OpenClaw. Store and recall memories across sessions with Episodic, Semantic, and Procedural layers. BM25 + Heuristic retrieval.
README (SKILL.md)
claw-mem: Three-Tier Memory System
Local-first memory system with three memory layers and intelligent retrieval.
Prerequisites
pip install git+https://github.com/opensourceclaw/claw-mem.git
Quick Start
Search Memory
python3 {baseDir}/scripts/search.py "project deadlines" --limit 10
Store Memory
python3 {baseDir}/scripts/store.py "User preference" --category preference
Start Bridge (for OpenClaw integration)
python3 {baseDir}/scripts/bridge.py --workspace ~/.openclaw/workspace
Memory Layers
| Layer | Purpose | Example |
|---|---|---|
| Episodic | Event sequences | Session context |
| Semantic | Knowledge facts | User preferences |
| Procedural | Rules | Best practices |
Retrieval Modes
| Mode | Description | Use Case |
|---|---|---|
keyword |
Simple keyword match | Quick lookup |
bm25 |
BM25 ranking | Relevance ranking |
hybrid |
BM25 + Keyword | Balanced retrieval |
enhanced_smart |
Full pipeline | Best quality |
Set mode via environment:
export CLAW_MEM_SEARCH_MODE=enhanced_smart
Configuration
OpenClaw config (openclaw.config.json):
{
"plugins": {
"slots": {
"memory": "claw-mem"
},
"claw-mem": {
"config": {
"workspaceDir": "~/.openclaw/workspace",
"autoRecall": true,
"autoCapture": true,
"topK": 10
}
}
}
}
Performance
| Operation | Latency |
|---|---|
| Initialize | ~4ms |
| Store | ~8ms |
| Search | ~5ms |
| Average | ~6ms |
Advanced
See references for detailed documentation:
- Architecture - Three-tier design
- Retrieval - Search algorithms
Usage Guidance
This skill appears coherent for a local memory plugin, but take the following precautions before installing: 1) Review the upstream GitHub repo (https://github.com/opensourceclaw/claw-mem) because pip install from a git URL runs code from that repository during install. 2) Install into an isolated environment (virtualenv) to limit impact. 3) Be aware it persists data to ~/.openclaw/workspace (SQLite files) — avoid storing sensitive secrets there and consider its autoCapture/autoRecall settings. 4) If you need stronger assurance, inspect the full claw_mem package source (especially any network code or RPC bridge implementation) before running the bridge. Otherwise the package and included scripts are proportionate to the stated purpose.
Capability Analysis
Type: OpenClaw Skill
Name: opensourceclaw-claw-mem
Version: 2.0.1
The claw-mem skill bundle provides a legitimate three-tier memory system (Episodic, Semantic, Procedural) for OpenClaw agents. The scripts (bridge.py, search.py, store.py) and documentation (SKILL.md, architecture.md) are consistent with the stated purpose of local-first memory management using SQLite, and no indicators of data exfiltration, malicious execution, or prompt injection were found.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, and the three scripts all align: they implement a local memory system, rely on a Python package named 'claw_mem', and operate on a workspace directory. No unrelated credentials, binaries, or system-wide config are requested.
Instruction Scope
Runtime instructions limit actions to installing the package, running the provided scripts, and configuring a workspace path and a search-mode env var. The SKILL.md does not instruct reading unrelated files, harvesting environment secrets, or posting data to third-party endpoints.
Install Mechanism
The README recommends pip installing directly from the GitHub repository (git+https://github.com/opensourceclaw/claw-mem.git). That is a common and expected install path but it does execute code from that remote repository at install-time — review the upstream repository before running pip install.
Credentials
No required environment variables or credentials are declared. Only a search-mode env var (CLAW_MEM_SEARCH_MODE) is suggested, and the scripts use a local workspace path (~/.openclaw/workspace) for SQLite persistence. No disproportionate secret access is requested.
Persistence & Privilege
Skill is not forced always-on and does not request elevated system privileges. It will read/write local SQLite DBs in the specified workspace (episodic.db, semantic.db, procedural.db) which is expected for a memory plugin. Note: the default config in SKILL.md enables autoCapture/autoRecall, which means the plugin will persist conversation data if enabled.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install opensourceclaw-claw-mem - After installation, invoke the skill by name or use
/opensourceclaw-claw-mem - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.1
- Improved SKILL.md for clarity and conciseness
- Updated installation instructions to use git+https URL
- Simplified descriptions of memory layers and retrieval modes
- Removed mention of the 'entity' and 'heuristic' retrieval modes
- Updated example commands for consistency
v2.0.0
claw-mem 2.0.0 introduces a three-tier memory system and enhanced retrieval features for OpenClaw agents.
- Adds Episodic, Semantic, and Procedural memory layers for structured fact, event, and rule storage.
- Supports versatile retrieval modes: keyword, BM25, hybrid, entity, heuristic, and enhanced_smart.
- Enables local, session-persistent memory storage with fast performance (average latency ~6ms).
- Simplifies configuration and OpenClaw integration via dedicated scripts and example configs.
- Provides clear documentation for setup, memory layers, retrieval, and advanced usage.
Metadata
Frequently Asked Questions
What is claw-mem: Three-Tier Memory?
Three-Tier Memory System for OpenClaw. Store and recall memories across sessions with Episodic, Semantic, and Procedural layers. BM25 + Heuristic retrieval. It is an AI Agent Skill for Claude Code / OpenClaw, with 78 downloads so far.
How do I install claw-mem: Three-Tier Memory?
Run "/install opensourceclaw-claw-mem" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is claw-mem: Three-Tier Memory free?
Yes, claw-mem: Three-Tier Memory is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does claw-mem: Three-Tier Memory support?
claw-mem: Three-Tier Memory is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created claw-mem: Three-Tier Memory?
It is built and maintained by Peter Cheng (@petercheng); the current version is v2.0.1.
More Skills