minds-eye
v1.0.0Remember and retrieve visual content from conversations. Use when: (1) user sends an image, photo, chart, diagram, or screenshot and wants it saved/remembere...
⭐ 1· 218·0 current·0 all-time
byTianyu Jiang@horisky
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (remember & retrieve visual content) matches the included scripts and instructions: analyze images via a vision-capable model, capture website screenshots, store images and metadata in ~/.multimodal-memory, and provide search/list utilities. Required binary (python3) and optional Playwright dependency are reasonable for this functionality.
Instruction Scope
Instructions correctly direct the agent to use the provided scripts (analyze.py, capture_url.py, store.py, search.py, list.py). The skill intentionally reads OpenClaw config (~/.openclaw/openclaw.json) and ~/.openclaw/.env and will ask for absolute image file paths when needed. These behaviors are consistent with the purpose but do grant the skill the ability to read arbitrary files the agent is instructed to analyze (those files will be base64-encoded and sent to the configured model provider).
Install Mechanism
This is an instruction-and-script skill with no installer; requirements.txt lists Playwright only. One-time pip install of Playwright (recommended by the SKILL.md) is the only external package installation suggested. There are no downloads from unknown URLs or archives that would raise high install risk.
Credentials
The skill does not require unusual environment variables, but it will look for an API key in ~/.openclaw/openclaw.json, ~/.openclaw/.env, or the OPENAI_API_KEY env var to call a vision-capable model. This is proportional to its function. Users should be aware that any image provided (or any file path supplied and read) will be uploaded to the configured API provider.
Persistence & Privilege
The skill stores data under the user's home directory (~/.multimodal-memory/) and updates a memory.md file; this is expected for a local memory capability. It does not request always:true and does not modify other skills or system-wide agent configuration.
Assessment
This skill appears to do what it says: it analyzes images by sending them to the configured vision-capable model and stores copies and metadata under ~/.multimodal-memory/. Before installing, verify which provider/API key the skill will use (check ~/.openclaw/openclaw.json and your OPENAI_API_KEY). Do not supply file paths to sensitive local files (password screenshots, private keys, etc.), because any image file you point the skill to will be read and uploaded to the API. If you plan to capture websites, note Playwright (or headless Chrome) will load remote pages locally to take screenshots — that can execute page JS. Consider using a separate/limited account or running this skill in an isolated environment if you need to limit exposure, and review or rotate API keys regularly. Finally, inspect ~/.multimodal-memory/ if you want to audit stored images and memory.md summaries or remove them when no longer needed.Like a lobster shell, security has layers — review code before you run it.
latestvk970p52exdssjav0n8q360nbe582axd8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧠 Clawdis
OSmacOS · Linux
Binspython3