A local-first, audit-friendly memory store plugin for OpenClaw that provides explicit control over documentation capture and semantic search.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-memory-docs
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-memory-docs using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenClaw Memory Docs?
OpenClaw Memory Docs is a powerful Gateway plugin designed for developers who require high-fidelity, documentation-grade memory within their AI agent environment. Unlike general memory systems that capture every interaction, this tool focuses on explicit, intentional storage, making it ideal for project documentation, long-lived technical notes, and architectural decisions. By integrating with Openclaw Skills, it ensures that your most important project context is preserved in a local, deterministic, and searchable format.
Privacy and security are central to the design. The plugin features a local embedding engine for semantic search without external service calls and includes automatic redaction for sensitive information like API keys and private tokens. This makes OpenClaw Memory Docs a reliable choice for professional environments where data sovereignty and security are non-negotiable.
OpenClaw Memory Docs Use Cases
- Creating a searchable repository of architectural decisions and technical debt notes during development sessions.
- Organizing project-specific knowledge using tags and project metadata for quick retrieval via Openclaw Skills.
- Maintaining a secure, redacted record of API endpoint details and backend configurations.
- Syncing AI-generated documentation with Git repositories using the markdown export and import functionality.
How OpenClaw Memory Docs Works
- Users explicitly capture information using specific commands like /remember-doc, ensuring only relevant data is stored.
- The plugin processes the text through a redaction engine to identify and mask secrets such as tokens or private keys.
- Content is stored locally in a JSONL file, maintaining a flat-file database that is easy to audit and backup.
- A local embedder generates vector representations of the stored text, allowing for semantic similarity searches rather than just keyword matching.
- AI agents or users can retrieve information using the search tool or commands, filtering by project or tags to find precise context.
- For long-term preservation, data can be exported into individual Markdown files with YAML frontmatter for version control.
OpenClaw Memory Docs Setup
To get started with this plugin in your environment, you can install it via ClawHub:
clawhub install openclaw-memory-docs
For developers looking to run the plugin locally or contribute, use the following commands:
openclaw plugins install -l ~/.openclaw/workspace/openclaw-memory-docs
openclaw gateway restart
OpenClaw Memory Docs Data Schema & Taxonomy
The plugin uses a structured approach to manage documentation, alternating between JSONL for active storage and Markdown for exports. Data is organized according to the following schema:
| Field | Type | Description |
|---|---|---|
id |
String | Unique identifier for the memory record |
text |
String | The documentation content (redacted if enabled) |
tags |
Array | Custom labels for filtering and organization |
project |
String | The specific project association for the entry |
createdAt |
Timestamp | Date and time the record was created |
Exported files are named using the YYYY-MM-DD_<shortid>.md format to ensure they remain sorted and merge-friendly in git-based Openclaw Skills workflows.
OpenClaw Memory Docs Advanced Features
- Semantic search tool
docs_memory_searchfor direct integration into agentic workflows and automated research. - Automatic redaction of sensitive data patterns including API keys, tokens, and private key blocks to prevent data leaks.
- Git-friendly Markdown export/import that preserves all metadata in YAML frontmatter for seamless documentation portability.
- Configurable embedding dimensions (default 256) to optimize the balance between search accuracy and local resource usage.
- Multi-tag and project-based filtering to manage large-scale documentation across different workstreams.
SKILL.md
Loading
Related Openclaw Skills
Openclaw Memory Core
A high-performance utility library providing privacy-first redaction, local JSONL storage, and offline text embeddings for AI memory management.
Openclaw INWX
A comprehensive automation plugin for managing the INWX domain registrar lifecycle, including DNS, registration, and DNSSEC within the Openclaw Skills ecosystem.
openclaw-help
A security-first plugin that adds a customizable /help command to your agent while keeping private workflows and shortcuts safe from public repositories.
Openclaw GPU Bridge
A high-performance bridge for offloading BERTScore and embedding calculations to remote GPU infrastructure.
OpenClaw Model Failover Plugin
A gateway-level plugin that automatically switches to fallback LLM models when primary APIs hit rate limits or encounter quota errors.
OpenClaw Ops (Elvatis)
A comprehensive operational toolkit for managing, monitoring, and validating OpenClaw deployments and configurations.
METADATA
Featured*
