← Back to Skills Marketplace
325
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install memori-extension
Description
Memory augmentation and LLM call interception using the Memori Python library with optional Zhipu API integration.
Usage Guidance
This skill appears coherent, but follow these precautions before enabling external features: 1) Test in local-only mode by leaving ZHIPUAI_API_KEY unset—this keeps all work on your machine. 2) Review the Memori and zhipuai packages (origin, maintainers) before pip installing. 3) If you do supply ZHIPUAI_API_KEY, understand that full conversation text (including system prompts and assistant responses) may be transmitted to Zhipu's servers. 4) Protect the local database and tech_terms file with appropriate file permissions and backups; the skill can append terms to the configured file. 5) If you need higher assurance, run the skill in a sandbox environment and inspect traffic to confirm only intended API calls occur.
Capability Analysis
Type: OpenClaw Skill
Name: memori-extension
Version: 1.0.2
The skill is transparent about its operations, explicitly detailing local file read/write (SQLite database, tech terms file) and optional external API calls to Zhipu AI if an API key is provided. The `SKILL.md` and `README.md` provide clear security and privacy notices, warning users about data transmission if the Zhipu AI API is enabled. The Python code (`memori_extension.py`) implements these features as described, only making external calls when `ZHIPUAI_API_KEY` is set. There is no evidence of intentional malicious behavior such as unauthorized data exfiltration, credential theft, backdoors, or prompt injection designed to subvert the agent's purpose. All risky capabilities are clearly documented and opt-in.
Capability Assessment
Purpose & Capability
Name/description match the implementation: the bundle wraps the Memori Python library for local memory operations and exposes an optional Zhipu client that is only activated when ZHIPUAI_API_KEY is set. Required binaries (python3) and the declared Python dependency (memori) are appropriate.
Instruction Scope
SKILL.md and the code explicitly describe file reads/writes (local SQLite DB and optional tech terms file) and clearly document that conversation text is sent to Zhipu only if the ZHIPUAI_API_KEY env var is provided. The code also persists added tech terms when persist=True. There are no instructions to read unrelated system files or to exfiltrate secrets beyond the controlled Zhipu API call.
Install Mechanism
This is an instruction-only skill with included Python wrapper code; installation is via pip for memori (and optionally zhipuai). No downloads from untrusted URLs or extract/install steps are present in the manifest.
Credentials
No required credentials are declared. The only sensitive environment variable is ZHIPUAI_API_KEY (optional) which directly maps to the optional external augmentation feature. Other environment variables control local file paths and terms and are proportionate to the functionality.
Persistence & Privilege
The skill does not request always:true or other elevated persistence. It reads/writes its own local DB and optional config file; it does not modify other skills or global agent configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install memori-extension - After installation, invoke the skill by name or use
/memori-extension - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
**Security & privacy information added for file/database operations and external API calls.**
- Added a comprehensive "Security & Privacy Notice" section, detailing data flow, local file/database usage, and when/what is sent to external APIs.
- Documented all supported environment variables, clarifying privacy impact of each.
- Provided explicit recommendations for safe use and cautions regarding enabling Zhipu API integration.
- Clarified local-only operation (no external data transmission) unless API keys are provided.
- Highlighted file/database access patterns and best practices for privacy-conscious deployments.
v1.0.1
- Renamed the skill and module from "memori-zhipu" to "memori-extension".
- Added detailed documentation on optional Zhipu API integration and corresponding environment variables.
- Introduced configuration options for customizing technical terms via environment variables or a separate config file.
- Updated metadata and file structure to reflect new naming and environment variable requirements.
- Expanded usage instructions and configuration examples for enhanced clarity.
v1.0.0
- Initial release of the memori-extension skill.
- Provides memory augmentation and LLM call interception using the Memori Python library.
- Includes APIs for searching, storing, and augmenting memory, as well as an LLM interception utility.
- Requires the memori Python package (install via pip).
- Optional integration with Zhipu API for enhanced augmentation.
- Licensed under Apache License Version 2.0.
Metadata
Frequently Asked Questions
What is memori-extension?
Memory augmentation and LLM call interception using the Memori Python library with optional Zhipu API integration. It is an AI Agent Skill for Claude Code / OpenClaw, with 325 downloads so far.
How do I install memori-extension?
Run "/install memori-extension" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is memori-extension free?
Yes, memori-extension is completely free (open-source). You can download, install and use it at no cost.
Which platforms does memori-extension support?
memori-extension is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created memori-extension?
It is built and maintained by ian-at (@ian-at); the current version is v1.0.2.
More Skills