← Back to Skills Marketplace
98
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install self-evolving-memory
Description
Orchestrate the OpenClaw memory system so it actually runs reliably in practice. Use when the task involves capturing user preferences, current task state, c...
Usage Guidance
This skill is coherent and appears to do what it claims: create and manage memory templates and provide routing rules. Before installing or running the setup script, review the templates and scripts (they only copy files and read ~/.openclaw/openclaw.json). Do not run suggested remote install commands (e.g., curl | sh) unless you trust the source; prefer installing embedding backends (like Ollama) via official instructions. Avoid putting API keys or secrets into workspace files; store them in secure config or environment variables per your platform's best practices. If you enable remote embedding providers, verify the remote baseUrl and apiKey targets are trusted. Finally, back up any existing memory files in your workspace before running the setup so nothing is accidentally lost.
Capability Analysis
Type: OpenClaw Skill
Name: self-evolving-memory
Version: 1.0.0
The skill bundle provides a structured framework for managing an AI agent's long-term memory using a layered markdown-based system. The included bash script (scripts/setup.sh) is a standard initialization utility that copies templates and performs local configuration checks, such as verifying the presence of embedding settings in openclaw.json using a safe python3 one-liner. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection; all instructions and code are strictly aligned with the stated purpose of memory orchestration.
Capability Assessment
Purpose & Capability
The skill's name/description (memory orchestration) matches the actual content: templates, routing rules, and a setup script that copies templates and checks embedding config. It does not request unrelated credentials or binaries.
Instruction Scope
SKILL.md and the references confine actions to the user's workspace (creating/templating memory files), reading openclaw.json for memorySearch configuration, and optionally using embedding providers for semantic search. There are no instructions to read arbitrary user files, shell history, or exfiltrate data.
Install Mechanism
There is no install spec; the only executable file is scripts/setup.sh which copies templates and checks configuration (benign). The documentation suggests running external commands to install Ollama (curl | sh) and pulling models; that guidance is optional and carries the usual caution about running remote install scripts.
Credentials
The skill itself requires no environment variables or credentials. Documentation explains how to configure embedding backends which may require API keys (OpenAI or remote Ollama endpoints). Requesting embedding API keys is proportionate to optional embedding features, but users should avoid storing secrets in plain templates or unsecured workspace files.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. It does not modify other skills or system-wide settings beyond copying templates into the user-specified workspace and reading ~/.openclaw/openclaw.json to check config — behavior consistent with its purpose.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install self-evolving-memory - After installation, invoke the skill by name or use
/self-evolving-memory - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Version 1.0.0
- Initial release: introduces a comprehensive orchestration layer for the OpenClaw memory system.
- Defines clear routing, promotion, and hardening rules for handling user preferences, task states, corrections, decisions, and recurring issues across multiple memory layers.
- Includes a first-run setup protocol for initializing and validating required and recommended memory files.
- Provides embedding/vector recall support with detailed configuration examples.
- Establishes hygiene and maintenance workflows for adapting, promoting, and cleaning up memory.
- Lists trigger phrases and concrete guidance on when and how to apply memory orchestration.
Metadata
Frequently Asked Questions
What is self-evolving-memory?
Orchestrate the OpenClaw memory system so it actually runs reliably in practice. Use when the task involves capturing user preferences, current task state, c... It is an AI Agent Skill for Claude Code / OpenClaw, with 98 downloads so far.
How do I install self-evolving-memory?
Run "/install self-evolving-memory" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is self-evolving-memory free?
Yes, self-evolving-memory is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does self-evolving-memory support?
self-evolving-memory is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created self-evolving-memory?
It is built and maintained by HAL-9909 (@hal-9909); the current version is v1.0.0.
More Skills