skills.rest
zester4
zester4COMMUNITY
Explore all skills by this author →
GitHub

supermemory

Integrate persistent memory, user profiles, and semantic search into AI agents via the Supermemory API.

2|1|Updated Jun 9, 2026
Search Tags:#knowledge graph#semantic search#personalization#rag#ai agents#memory#user profiles
One-click install
npx skills add https://github.com/zester4/zilmate --skill supermemory-zester4
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: supermemory
Source: https://github.com/zester4/zilmate/tree/main/.agents/skills/supermemory
Command: npx skills add https://github.com/zester4/zilmate --skill supermemory-zester4

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires supermemory, and includes references (resource) components.

What problem does it solve? AI applications are stateless by default and forget user context between sessions, forcing developers to build custom memory pipelines. This Skill guides agents to add persistent memory, personalization, and semantic retrieval to chatbots and assistants using the Supermemory API and SDKs. ## Core Features & Use Cases - Memory API & User Profiles: Store conversations with add() and retrieve static plus dynamic user facts with profile() to personalize every response. - Semantic & Hybrid RAG Search: Search documents, PDFs, images, and URLs with search.memories() using semantic or hybrid modes, metadata filters, and relevance thresholds. - Knowledge Graph Architecture: Automatically builds relationships (updates, extends, derives) between memories so knowledge evolves over time. - Use Case: A developer building a customer support chatbot uses container tags per customer, stores each ticket interaction, and retrieves full history before generating replies so the agent recalls past issues and resolutions. ## Quick Start Ask the agent to add long-term memory to your chatbot using Supermemory with your API key from console.supermemory.ai.

Frequently Asked Questions about supermemory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add long-term memory to an AI chatbot?▼

Use the Supermemory SDK: call profile() with the user's containerTag before generating a response to retrieve context, then call add() after the conversation to store new memories. This retrieve-enrich-store loop gives the chatbot persistent recall across sessions.

What is the difference between Supermemory and a vector database?▼

Vector databases provide raw similarity search, while Supermemory is an end-to-end memory layer with automatic chunking, embedding, relationship building (updates, extends, derives), and generated user profiles. It requires no manual pipeline construction.

Does Supermemory support Python and TypeScript?▼

Yes, Supermemory provides native SDKs for both: install with npm install supermemory for TypeScript/JavaScript or pip install supermemory for Python, including an AsyncSupermemory client. Other languages can use the REST API directly.

How do I isolate memory between users in a multi-tenant app?▼

Use container tags as isolation boundaries, such as user_123 for per-user memory or org_acme for shared organization knowledge. Searches and profiles only return memories within the specified containerTag, preventing cross-tenant data access.

Why is my Supermemory search returning no results?▼

Common causes are a threshold set too high, a mismatched containerTag between add() and search calls, or content still processing. Lower the threshold toward 0.3, verify tag consistency, and wait 1-2 minutes for PDFs or 5-10 minutes for videos.

Related Skills

Explore More Software Engineering Skills→
UniquecreteUniquecrete

supermemory

Stores and retrieves long-term agent memory via Supermemory's knowledge-graph API.

Community
Intermediate
copilot-ldcopilot-ld
1

libagent

Orchestrate LLM completions, memory windows, and tool calls for conversational AI workflows.

Official
Advanced
WingedGuardianWingedGuardian
90

user_evaluate

Evaluate content relevance using four lenses and user memory context.

Community
Advanced
mefardalesmefardales

vector-databases

Integrate vector databases for semantic search and RAG pipelines.

Community
Advanced