memory
Memory Skill
Persistent key-value storage for agent memory. Store important information and recall it later.
When to Use
✅ USE this skill when:
- "Remember that my favorite color is blue"
- "What did I tell you about my project?"
- "Forget my preferences"
- "What do you know about X?"
- Storing user preferences for later recall
- Saving context across conversations
When NOT to Use
❌ DON'T use this skill when:
- Temporary storage during a single session → use variables
- Large data storage → use file system
- Sensitive data → use secure storage
Storage Location
Memory is stored in ~/.agent-memory/memory.json as a JSON file.
Commands
Store Information
{baseDir}/memory.sh store "project_name" "My Cool Project"
{baseDir}/memory.sh store "preferences" '{"theme": "dark", "language": "en"}'
{baseDir}/memory.sh store --category "work" "company" "Acme Corp"
Recall Information
{baseDir}/memory.sh recall "project_name"
{baseDir}/memory.sh recall --all
{baseDir}/memory.sh recall --category "work"
{baseDir}/memory.sh search "project"
Forget Information
{baseDir}/memory.sh forget "project_name"
{baseDir}/memory.sh forget --category "work"
{baseDir}/memory.sh forget --all
List Categories
{baseDir}/memory.sh categories
{baseDir}/memory.sh stats
Categories
Organize memory by category:
personal- Personal preferences and infowork- Work-related informationprojects- Project detailscontext- Conversation context- Custom categories as needed
Examples
Store user preference:
{baseDir}/memory.sh store --category "personal" "timezone" "America/New_York"
Recall specific value:
{baseDir}/memory.sh recall "timezone"
# Output: America/New_York
Search for related keys:
{baseDir}/memory.sh search "project"
# Output: project_name, project_status, project_url
Get all memory for a category:
{baseDir}/memory.sh recall --category "work"
# Output: {"company": "Acme Corp", "role": "Developer"}
Notes
- Memory persists across sessions in a JSON file
- Values can be simple strings or JSON objects
- Categories help organize related memories
- Use
--allflag carefully (affects all stored data)
More from winsorllc/upgraded-carnival
vector-memory
Vector-based semantic memory using embeddings for intelligent recall. Store and search memories by meaning rather than keywords. Use when you need semantic search, similar document retrieval, or context-aware memory.
131model-router
Route requests between different LLM providers and models. Configure routing rules, fallback providers, and model-specific parameters inspired by ZeroClaw and OpenClaw model routing systems.
63rss-monitor
Monitor RSS/Atom feeds and blogs for new content using feedparser.
59rss-reader
Read and parse RSS/Atom feeds. Use when: user wants to subscribe to feeds, get latest articles, or monitor news sources.
54video-frames
Production-grade video frame extraction with thumbnail grids, GIF creation, and batch frame processing. Includes intelligent quality presets, progress tracking, and comprehensive error handling.
39elevenlabs-tts
Convert text to speech using ElevenLabs API. Use when you need to generate voice audio for messages, narrations, or accessibility.
25