← Back to Skills Marketplace
6634
Downloads
7
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install lancedb-memory
Description
Manage and retrieve long-term memories with LanceDB using semantic vector search, category filtering, and detailed metadata storage.
Usage Guidance
Review this skill before installing if you expect memory to be ephemeral or sensitive. It can retain whatever content callers add to memory on disk, uses a fixed local path, and lacks built-in consent, redaction, retention, encryption, confirmation, or recovery controls.
Capability Analysis
Type: OpenClaw Skill
Name: lancedb-memory
Version: 1.0.0
The skill bundle provides LanceDB integration for agent memory management. All files contain Python code for local database operations, including adding, searching, and retrieving memories. While several files use hardcoded absolute paths (e.g., `/Users/prerak/clawd/memory/lancedb` and `sys.path.append('/Users/prerak/clawd/skills/lancedb-memory')`), these paths point to locations within the expected agent's data and skill directories, and do not indicate unauthorized access or malicious intent. There is no evidence of data exfiltration, malicious execution, persistence, or harmful prompt injection attempts.
Capability Assessment
Credentials
Multiple modules instantiate a global database at import time and create /Users/prerak/clawd/memory/lancedb, a hard-coded developer-local path outside the skill directory.
Install Mechanism
No separate installer or remote payload retrieval was found, but the required SKILL.md is executable Python rather than normal skill instructions and depends on local LanceDB/Python environment assumptions.
Instruction Scope
The skill exposes storage and deletion capabilities but provides no clear runtime instructions requiring user opt-in, confirmation, retention limits, or sensitivity filtering before storing arbitrary memory content and metadata.
Persistence & Privilege
Persistent plaintext local memory is central to the purpose, but automatic database creation, arbitrary content storage, direct update/delete methods, and no disclosed purge or recovery controls make the authority under-scoped.
Purpose & Capability
The artifact consistently implements LanceDB-backed long-term memory add, search, update, delete, and stats operations; no network exfiltration, command execution, or credential harvesting was found.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install lancedb-memory - After installation, invoke the skill by name or use
/lancedb-memory - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of LanceDB-memory skill
- Provides a LanceDB-backed long-term memory system with vector search and semantic storage capabilities
- Supports adding, searching, updating, and deleting memory entries with metadata, categories, tags, and importance
- Includes statistics and category management functions for stored memories
- Example usage and main test section included in the code
Metadata
Frequently Asked Questions
What is Lancedb Memory?
Manage and retrieve long-term memories with LanceDB using semantic vector search, category filtering, and detailed metadata storage. It is an AI Agent Skill for Claude Code / OpenClaw, with 6634 downloads so far.
How do I install Lancedb Memory?
Run "/install lancedb-memory" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Lancedb Memory free?
Yes, Lancedb Memory is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Lancedb Memory support?
Lancedb Memory is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Lancedb Memory?
It is built and maintained by pntrivedy (@pntrivedy); the current version is v1.0.0.
More Skills