Skill Detail

Give agents fast searchable memory with Supermemory

Use Supermemory as an agent memory and context layer for ingesting user facts, documents, connectors, and searchable RAG context across assistant workflows.

Integrations & ConnectorsMulti-Framework
Integrations & Connectors Multi-Framework Security Reviewed
⭐ 22.5k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill give-agents-fast-searchable-memory-with-supermemory Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Supermemory account or self-hosted stack; Supermemory API/plugin; agent runtime such as Claude Code, OpenCode, OpenClaw, Hermes, or custom client
Install & setup
Follow the Supermemory docs to create/configure a workspace, connect the API or supported plugin/MCP integration, ingest memory sources, and call memory/search retrieval from the agent workflow.
Author
supermemoryai
Publisher
Vendor Open Source
Last updated
May 8, 2026
Quick brief

This skill helps an operator add persistent memory and retrieval to agent workflows with Supermemory. The system can ingest conversations, facts, documents, web and app connector content, maintain user profiles, and return relevant memory or RAG context for later agent calls.

How it works

What this skill actually does

Invoke it when an assistant needs durable cross-session context, personalized memory, or connector-backed retrieval without building a vector database, chunking pipeline, and profile store from scratch. The boundary is memory ingestion and retrieval for agents through the Supermemory API/plugins; it is not a consumer note-taking app card or a generic database listing.

Inputs and prerequisites: Supermemory account or self-hosted stack; Supermemory API/plugin; agent runtime such as Claude Code, OpenCode, OpenClaw, Hermes, or custom client.

Setup notes: Follow the Supermemory docs to create/configure a workspace, connect the API or supported plugin/MCP integration, ingest memory sources, and call memory/search retrieval from the agent workflow.

Source and verification boundary: use https://docs.supermemory.ai/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.