← Back to Skills Marketplace
30673
Downloads
32
Stars
464
Active Installs
1
Versions
Install in OpenClaw
/install agent-memory
Description
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
Usage Guidance
Install only if you want an agent to keep local cross-session memory. Do not store API keys, passwords, financial details, confidential business data, or unnecessary personal information. Review or delete the SQLite database periodically, and consider a separate custom database path for different projects or users.
Capability Analysis
Type: OpenClaw Skill
Name: agent-memory
Version: 1.0.0
The OpenClaw AgentMemory skill bundle is a self-contained, SQLite-based persistent memory system for AI agents. All code and documentation are aligned with its stated purpose of storing facts, lessons, and entities. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts against the analyzing agent. The skill uses standard Python libraries, manages its database in a user-specific directory (`~/.agent-memory/memory.db`), and explicitly states 'No external dependencies' in `requirements.txt`, indicating a low supply chain risk.
Capability Assessment
Purpose & Capability
The storage and recall features match the stated persistent-memory purpose, including facts, lessons, entities, search, deletion, cleanup, and export. Stored content may include user or relationship details, so users need data-handling discipline.
Instruction Scope
The skill suggests adding a session-start and session-end memory protocol to agent instructions. This is disclosed and purpose-aligned, but it can influence future sessions through saved memories.
Install Mechanism
No install script, package install hook, external dependency, or obfuscated setup behavior was found. requirements.txt states that it uses only the Python standard library.
Credentials
The default database path is ~/.agent-memory/memory.db, with custom-path and in-memory options. Local persistence is proportionate to the purpose, and the artifacts do not show credential access, broad file indexing, or network transmission.
Persistence & Privilege
Persistence is explicit and central to the skill. It creates a local SQLite database and provides user-callable deletion and cleanup methods, with no evidence of background daemons, privilege escalation, or hidden persistence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-memory - After installation, invoke the skill by name or use
/agent-memory - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - SQLite-backed persistent memory for AI agents
Metadata
Frequently Asked Questions
What is Agent Memory?
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions. It is an AI Agent Skill for Claude Code / OpenClaw, with 30673 downloads so far.
How do I install Agent Memory?
Run "/install agent-memory" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Memory free?
Yes, Agent Memory is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Agent Memory support?
Agent Memory is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Memory?
It is built and maintained by Dennis (@dennis-da-menace); the current version is v1.0.0.
More Skills