A background service that distills raw OpenClaw conversation logs into structured, theme-based, and searchable Markdown memory cards.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install auto-memory-distiller
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 auto-memory-distiller 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 Auto-Memory-Distiller?
Auto-Memory-Distiller is a sophisticated background utility designed to solve the problem of information fragmentation in AI interactions. As a specialized component of the Openclaw Skills ecosystem, it silently monitors your conversation streams and incrementally converts disordered JSONL records into a structured long-term knowledge base. It leverages Large Language Models to synthesize messy dialogues into categorized Markdown files, ensuring that valuable insights are preserved and easily retrievable for future sessions.
By focusing on incremental processing and topic aggregation, this skill ensures that your AI agent evolves with a coherent understanding of your projects and preferences. It bridges the gap between ephemeral chat history and a permanent, high-quality knowledge repository, making it an indispensable asset for developers who rely on Openclaw Skills for complex workflows.
Auto-Memory-Distiller Use Cases
- Automating the creation of a personal knowledge base from daily AI coding sessions.
- Cleaning and redacting sensitive data like API keys and credentials from local logs.
- Organizing fragmented technical discussions into cohesive, topic-based documentation.
- Maintaining a traceable history of decisions and insights with direct links to original chat sources.
How Auto-Memory-Distiller Works
- The skill identifies the current read state using a local cursor file to find new conversation entries.
- It extracts incremental data from JSONL logs, ensuring no redundant Token consumption.
- The system scans existing memory cards to determine if new insights belong to established topics.
- An LLM-powered engine synthesizes the new content, merging it into existing files or creating new thematic cards.
- Physical file paths and line pointers are appended to every memory entry for full traceability.
- The state cursor is updated to mark the newly processed lines as complete.
Auto-Memory-Distiller Setup
To integrate this tool into your collection of Openclaw Skills, first install the necessary Python dependencies:
pip install google-genai python-dotenv
Next, configure your Gemini API Key. You can add this to your system environment variables or place it in your workspace configuration file located at ~/.openclaw/workspace/.env:
GEMINI_API_KEY=your_gemini_api_key_here
Finally, run the script manually or schedule it via crontab for periodic background distillation:
python ~/.openclaw/workspace/skills/auto-distiller/distiller.py
Auto-Memory-Distiller Data Schema & Taxonomy
The skill manages data within the standard workspace directory using the following structure:
| File/Path | Purpose |
|---|---|
distiller.py |
The core execution logic for memory processing. |
state.json |
Automatically generated file tracking the session cursor (line numbers). |
memory/topics/*.md |
The structured output directory where topic-based Markdown cards are stored. |
Each Markdown card includes a header, the distilled knowledge, and a source pointer indicating the original file path and line number of the conversation.
Auto-Memory-Distiller Advanced Features
- Incremental Processing: Uses a state cursor to process only new logs, significantly reducing API costs.
- Intelligent Topic Merging: Prevents knowledge fragmentation by appending new data to relevant existing documents.
- Automated Safety Redaction: Automatically filters out API keys, secrets, and noisy system error logs using LLM analysis.
- Source Traceability: Maintains a strict record of where every piece of knowledge originated for easy verification.
SKILL.md
Loading
Related Openclaw Skills
Cloudflare DNS Management Skill
A powerful tool for programmatically managing Cloudflare DNS records to automate domain configuration and email authentication.
Time Clawshine
An automated, restic-powered backup system that provides hourly incremental snapshots for your OpenClaw instance to prevent data loss or agent errors.
Bible Research
A specialized AI agent for in-depth Bible study and scriptural research using a structured, context-aware methodology.
HK IPO Research Assistant
A comprehensive real-time data aggregator and analysis tool for Hong Kong Stock Exchange (HKEX) Initial Public Offerings.
Task Supervisor
A self-supervising manager for long-running AI agent tasks with progress tracking and periodic reporting.
Clawd Modifier
A creative customization toolkit for personalizing the Claude Code mascot's appearance and color schemes within your terminal.
Featured*
