← Back to Skills Marketplace
bkennedyshit

Openclaw mneme vision

by Billy Kennedy · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
40
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install mneme-vision
Description
Use local visual memory tools to index and search photos and videos from creator media libraries.
README (SKILL.md)

Visual Memory

Use this skill when the user wants to index, search, organize, or inspect local photo and video libraries.

When the user provides an uploaded photo/video/reel as an attachment, treat it as temporary session context first. Use its local path to answer the current question or run visual similarity search when appropriate. Do not call media_index or otherwise add the attachment to durable visual memory unless the user explicitly asks to add, save, index, catalog, or remember it.

Prefer media_index when the user points at a folder that has not been indexed. Prefer media_search for natural-language searches such as finding shots, finished videos, thumbnails, archive images, or clips matching a description. Prefer media_search_by_image when the user provides an image and wants visually similar items. Use media_describe when the user asks what is in a specific media file.

Use gpu_status before GPU-heavy local tasks when the user is coordinating video work, image generation, upscaling, VLM tagging, or another local model process. Use gpu_release to unload resident Ollama models and hand VRAM to that workflow, and use gpu_reclaim with the returned token when the workflow is done. Use gpu_evacuate only when the user asks to free VRAM immediately without creating a lease.

Return media results as previewable content cards when the host supports rich output. Each result should include:

  • title: filename or human-readable clip name.
  • kind: image, video, audio, or unknown.
  • path: absolute local path, kept available for copy/reveal actions.
  • reason: short explanation for why this media matched.
  • timestamp or time_range: when available for video/audio hits.
  • preview: true when the file can be rendered by the host UI.

Mneme returns neutral media_artifacts.v1 JSON. Preserve the host application's native styling; do not introduce custom colors, cards, gradients, or branding unless the host already provides that UI.

Do not dump long bare paths as the main answer. Put the path behind a Copy path or equivalent action when rich output is available, and show the user the actual image/video/audio preview first. When rich output is not available, use concise Markdown links or a compact table with path values.

Do not invent matches when the tool returns none.

Do not upload local media to a cloud service unless the user explicitly asks for that separate action.

Usage Guidance
Install this only if you are comfortable with a local MCP server indexing selected media folders and temporarily storing uploaded media for session use. Review the external mneme-mcp and OpenClaw plugin packages, and avoid indexing sensitive folders unless you explicitly want them searchable.
Capability Assessment
Purpose & Capability
The skill indexes and searches local photo/video libraries, returns local media paths/previews, and manages GPU/Ollama memory; these capabilities match its stated visual-memory purpose but involve private local media.
Instruction Scope
Runtime instructions limit durable indexing to explicit user requests and say not to upload media to cloud services unless separately requested; README also says uploaded media is saved to a local inbox as temporary session context, but retention details are not specified.
Install Mechanism
The artifact itself contains only markdown and JSON, but installation depends on an external MCP server via mcporter/uvx and an OpenClaw plugin package, so users should trust those external components separately.
Credentials
Local file access, media indexing, preview generation, and GPU memory controls are proportionate for local visual search and creator media workflows.
Persistence & Privilege
The skill can create durable local visual-memory indexes when asked and temporarily store uploaded media locally; no hidden persistence, background worker, credential access, or exfiltration behavior appears in the skill artifacts.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install mneme-vision
  3. After installation, invoke the skill by name or use /mneme-vision
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of mneme-vision skill. - Enables local indexing and search of photo and video libraries. - Supports natural-language and visual similarity search across media. - Handles GPU status and memory management for intensive workflows. - Returns media results as rich content cards when supported. - Ensures strong privacy: does not upload media to cloud unless explicitly requested.
Metadata
Slug mneme-vision
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Openclaw mneme vision?

Use local visual memory tools to index and search photos and videos from creator media libraries. It is an AI Agent Skill for Claude Code / OpenClaw, with 40 downloads so far.

How do I install Openclaw mneme vision?

Run "/install mneme-vision" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Openclaw mneme vision free?

Yes, Openclaw mneme vision is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Openclaw mneme vision support?

Openclaw mneme vision is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Openclaw mneme vision?

It is built and maintained by Billy Kennedy (@bkennedyshit); the current version is v1.0.0.

💬 Comments