← Back to Skills Marketplace
118
Downloads
0
Stars
0
Active Installs
7
Versions
Install in OpenClaw
/install smart-memory-zero-dep
Description
Enhanced memory system for agentic workflows. Automatic memory extraction from conversations, memory type classification (preference/project/technical/lesson...
Usage Guidance
This skill appears to do what it says: local memory extraction, tagging, decay, and a session WAL. Before installing or enabling: 1) ensure Python 3.10+ and Bash 4+ are available (metadata omitted these but scripts require them), 2) back up any existing ~/.openclaw/workspace data (scripts will read/modify these files), 3) review/adjust OPENCLAW_WORKSPACE if you want files stored elsewhere, 4) understand the WAL rule (the agent will write remembered text to disk before replying) — if you worry about accidental persistence of secrets, test extraction on non-sensitive sample data and review the regex patterns that block tokens/keys, and 5) if you want to limit risk, disable autonomous invocation for the skill or run it in a sandboxed account until you’re comfortable with behavior.
Capability Analysis
Type: OpenClaw Skill
Name: smart-memory-zero-dep
Version: 1.1.2
The smart-memory-zero-dep skill is a comprehensive local memory management system for OpenClaw agents, implementing a multi-layered storage architecture (Hot RAM, daily logs, and curated long-term facts). The bundle includes several Python and Bash scripts (session_state.py, session_cache.py, memory_decay.py) designed to handle data isolation, temporal archival, and input sanitization. Notably, the scripts include proactive security features such as hard-coded regex filters to prevent the accidental storage of sensitive credentials like API keys (OpenAI, GitHub, ClawHub), passwords, and private keys. All operations are performed locally within the user's workspace or /tmp directory, with no evidence of network exfiltration or malicious execution logic.
Capability Assessment
Purpose & Capability
Overall coherent: name/description (memory extraction, tagging, decay, session cache) matches the included scripts (session_state.py, session_cache.py, extract_memories.sh, classify_memory.py, memory_decay.py, memory_health.sh). Minor inconsistency: registry metadata lists "Required binaries: none" but SKILL.md explicitly requires Python 3.10+ and Bash 4+. Also the package was marked "instruction-only" in install spec but includes multiple executable scripts — this is fine but worth noting as a mismatch between metadata and bundled files.
Instruction Scope
Instructions stay within the stated domain (local writes to ~/.openclaw/workspace and /tmp, no network endpoints). They direct the agent to write WAL entries before responding, run local classification/decay/health scripts, and optionally use the agent's own LLM for higher-quality extraction. Caution: the WAL requirement means the agent will persist extracted text before responding — if extraction misclassifies sensitive text, it may be written locally. The scripts implement regex-based blocking for common key/token patterns, but those checks are heuristic and can miss exotic credential formats.
Install Mechanism
No install spec — scripts are included and run directly. No external downloads or package installs. This is low-risk from an installation perspective (nothing downloaded/executed from remote URLs).
Credentials
The skill requests no secrets or privileged environment variables. SKILL.md documents two optional environment variables (OPENCLAW_WORKSPACE, OPENCLAW_SESSION_ID) used to locate workspace and session cache — these are reasonable and proportional to the functionality.
Persistence & Privilege
The skill writes and modifies files inside a user-local workspace (~/.openclaw/workspace) and /tmp session caches, which is expected for a memory system. always:false (normal). Because the agent is expected to autonomously invoke these scripts (disable-model-invocation: false by default), the skill can autonomously persist data to disk — this is expected for a memory plugin but increases blast radius if the agent is misconfigured or hostile.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install smart-memory-zero-dep - After installation, invoke the skill by name or use
/smart-memory-zero-dep - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.2
UX: wal shortcut alias (--help: 20 chars vs 70), classify --summary for stats-only output, decay --promote-only for quick LESSON promotion, health now shows actionable suggestions
v1.1.1
Extraction: default to keyword mode (zero token cost), LLM mode opt-in only for 20+ turn conversations. Updated extraction_prompt.md with mode comparison table.
v1.1.0
6 upgrades: (1) snapshot/restore for session state persistence, (2) n-gram similarity for CJK/mixed-text classification, (3) LESSON promotion with reference counting, (4) duplicate detection before tagging, (5) auto-extract via --auto flag, (6) expanded Chinese keywords
v1.0.3
Narrow extraction scope: add explicit 'Do NOT Extract' list (credentials, private conversations, speculation, transient state). Clarify sensitive-data regex limitations.
v1.0.2
Security: replace shell scripts with Python (no injection risk), add sensitive data hard-block (API keys, passwords, private keys), input sanitization, path-safe session IDs. Scripts: session_state.sh→session_state.py, session_cache.sh→session_cache.py
v1.0.1
Fix: declare runtime requirements (Bash 4+, Python 3.10+), document env vars (OPENCLAW_WORKSPACE, OPENCLAW_SESSION_ID), add session_state.sh to scripts table, add done/blocker/get to quick reference.
v1.0.0
smart-memory-zero-dep v1.0.0
- Initial release of enhanced memory system for agentic workflows
- Automatic extraction and classification of memory from conversations
- Zero external dependencies; pure shell/Python scripts
- Multi-layer memory design (HOT RAM, daily, curated, archival, session cache)
- Built-in decay/archival and maintenance workflows
- Adopts WAL protocol to prevent context loss in workflow execution
Metadata
Frequently Asked Questions
What is Smart Memory (Zero Dep)?
Enhanced memory system for agentic workflows. Automatic memory extraction from conversations, memory type classification (preference/project/technical/lesson... It is an AI Agent Skill for Claude Code / OpenClaw, with 118 downloads so far.
How do I install Smart Memory (Zero Dep)?
Run "/install smart-memory-zero-dep" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Smart Memory (Zero Dep) free?
Yes, Smart Memory (Zero Dep) is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Smart Memory (Zero Dep) support?
Smart Memory (Zero Dep) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Smart Memory (Zero Dep)?
It is built and maintained by zgjq (@zgjq); the current version is v1.1.2.
More Skills