← Back to Skills Marketplace
463
Downloads
0
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install memory-distiller
Description
OpenClaw's subconscious. Automatically distills conversation insights, corrections, and preferences into durable memory. The agent that learns from every ses...
Usage Guidance
This skill appears to do what it claims: automatically detect corrections/preferences/insights and append structured entries to the agent's memory files. Before installing, consider: (1) Silent writes — auto-recording happens without notifying the user; ensure you're comfortable with the agent persisting conversation fragments. (2) Privacy enforcement — the SKILL.md prohibits storing secrets, but there's no code to enforce that; verify your runtime enforces the privacy filter or audit what actually gets written. (3) Review and retention — decide how to review, edit, and delete auto-learned memory entries so accidental or sensitive data can be removed. If those concerns are acceptable and your agent runtime provides appropriate filesystem and privacy protections, the skill is coherent with its stated purpose.
Capability Analysis
Type: OpenClaw Skill
Name: memory-distiller
Version: 1.0.1
The 'memory-distiller' skill is designed to enhance the OpenClaw agent's learning by automatically distilling conversation insights, corrections, and preferences into durable memory files (`MEMORY.md`, `USER.md`, `memory/YYYY-MM-DD.md`). The `SKILL.md` instructions clearly define its purpose, trigger conditions, and a 'Quality Gate' to filter out irrelevant information. Crucially, it includes a 'Privacy Filter' that explicitly forbids the agent from writing sensitive data (passwords, tokens, PII) to any memory file, even if prompted by the user. There are no instructions for data exfiltration, malicious execution, persistence, or any other harmful behaviors. The installation command `npx clawhub@latest install memory-distiller` is standard for OpenClaw skills. All analyzed files align with a benign, helpful learning enhancement for the agent.
Capability Assessment
Purpose & Capability
Name/description promise (automatic distillation of conversation into durable memory) aligns with the instructions: scan messages for triggers, apply four quality gates, and write to MEMORY.md, memory/YYYY-MM-DD.md, and USER.md. No unrelated binaries, credentials, or install steps are requested.
Instruction Scope
Instructions explicitly direct scanning every user message for trigger words and writing entries to persistent memory files. This is within the stated purpose, but the behaviour includes silent auto-writes (no user notification on auto-trigger) and relies on the agent following the written 'Privacy Filter' rules — there is no enforcement code in the package (it's instruction-only), so accidental capture of sensitive material depends on accurate implementation by the agent runtime.
Install Mechanism
Instruction-only skill with no install spec and no code files. Lowest-risk install footprint — nothing is downloaded or written by an install step in the skill package.
Credentials
The skill requires no environment variables, credentials, or special config paths. It does reference writing to standard project memory files (MEMORY.md, memory/YYYY-MM-DD.md, USER.md), which is proportionate to a memory-distillation feature. The manifest does not declare file paths explicitly — this is typical for instruction-only skills that rely on the agent's existing memory facility.
Persistence & Privilege
The skill persists changes to agent memory files (durable effect across sessions), which is expected for its purpose. It does not set always: true. However, its default behavior to write silently on auto-trigger may be surprising to users and has privacy implications because persisted memory will influence future agent behavior.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install memory-distiller - After installation, invoke the skill by name or use
/memory-distiller - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
memory-distiller v1.0.1
- Introduces automatic distillation of conversation insights, corrections, and preferences into persistent memory for OpenClaw agents.
- Scans user messages for actionable signals (corrections, preferences, insights, explicit "remember" cues) and creates durable memory entries if quality standards are met.
- Implements a four-part quality gate (durability, generality, novelty, actionability) to ensure retention of valuable, reusable knowledge only.
- Organizes distilled memories into structured files (`MEMORY.md`, `memory/YYYY-MM-DD.md`, `USER.md`) using a clear, timestamped format.
- Performs all recording silently unless explicitly instructed, ensuring a non-intrusive user experience.
- Includes built-in privacy and duplication safeguards to avoid storing sensitive or redundant data.
Metadata
Frequently Asked Questions
What is Memory Distiller?
OpenClaw's subconscious. Automatically distills conversation insights, corrections, and preferences into durable memory. The agent that learns from every ses... It is an AI Agent Skill for Claude Code / OpenClaw, with 463 downloads so far.
How do I install Memory Distiller?
Run "/install memory-distiller" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Memory Distiller free?
Yes, Memory Distiller is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Memory Distiller support?
Memory Distiller is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Memory Distiller?
It is built and maintained by zcyynl (@zcyynl); the current version is v1.0.1.
More Skills