← Back to Skills Marketplace
anderotxoa

MemPalace

by anderotxoa · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
127
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install mempalace-ander
Description
Integración con MemPalace para gestión de memoria semántica persistente. Use when you need to search, add, or query memories stored in a MemPalace palace. Su...
Usage Guidance
This skill appears coherent with its stated purpose, but before installing: (1) ensure you trust the mempalace package that will be imported at /root/.openclaw/workspace/mempalace (inspect its code if present), (2) confirm chromadb and any Python deps are installed in the runtime environment, and (3) be aware the scripts read/write the local directory (~/.mempalace/palace or a custom --palace-path). If you are unsure, run these scripts in an isolated environment (container or VM) and inspect the mempalace package to ensure it doesn't perform unexpected network/exfiltration actions.
Capability Analysis
Type: OpenClaw Skill Name: mempalace-ander Version: 1.0.0 The MemPalace skill is a legitimate semantic memory management system using ChromaDB. The scripts (add_memory.py, search.py, kg_query.py, status.py) provide standard functionality for storing, searching, and querying structured and unstructured data locally in ~/.mempalace/palace, with no evidence of data exfiltration, malicious execution, or prompt injection.
Capability Tags
crypto
Capability Assessment
Purpose & Capability
Name/description describe semantic memory management and the shipped scripts implement search, add, status, and KG queries against a ChromaDB-backed 'palace' — the requested capabilities align with the stated purpose.
Instruction Scope
SKILL.md and the scripts restrict actions to a local palace path (default ~/.mempalace/palace) and to ChromaDB operations. One repeated pattern: scripts insert '/root/.openclaw/workspace/mempalace' into sys.path to import a mempalace package that is not included in the bundle; this is a fragile dependency but not itself a sign of malicious behavior.
Install Mechanism
No install spec (instruction-only + scripts). The scripts rely on external Python packages (chromadb and a mempalace package) but do not install them. This is low risk but means the runtime environment must already provide these dependencies.
Credentials
The skill declares no environment variables, credentials, or config paths. The scripts operate on a local path and accept a --palace-path override; there are no requests for unrelated secrets or external service keys.
Persistence & Privilege
always is false and the skill does not attempt to modify other skills or global agent settings. It reads and writes local ChromaDB storage (expected for its function).
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install mempalace-ander
  3. After installation, invoke the skill by name or use /mempalace-ander
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Integración con MemPalace para gestión de memoria semántica persistente en OpenClaw
Metadata
Slug mempalace-ander
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is MemPalace?

Integración con MemPalace para gestión de memoria semántica persistente. Use when you need to search, add, or query memories stored in a MemPalace palace. Su... It is an AI Agent Skill for Claude Code / OpenClaw, with 127 downloads so far.

How do I install MemPalace?

Run "/install mempalace-ander" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is MemPalace free?

Yes, MemPalace is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does MemPalace support?

MemPalace is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created MemPalace?

It is built and maintained by anderotxoa (@anderotxoa); the current version is v1.0.0.

💬 Comments