# supermemory

Guides agents on building with the Supermemory v5 API and SDKs. Helps add persistent memory, semantic chunk search, and user profiles to apps.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 903 installs · ★ 113
- Author: supermemoryai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/supermemoryai/skills/tree/HEAD/supermemory/SKILL.md
- Updated: 2026-10-14
- HTML: https://affpapa.org/en/nevibecode/skills/supermemory

## What it does

This skill gives coding assistants exact specifications for Supermemory v5 across TypeScript and Python SDKs. All storage and retrieval operations are isolated within a single namespace. Instead of managing memory facts by hand, you submit text, files, or URLs under a stable identifier. The background engine parses the content, creates searchable chunks, and maintains a profile for each subject.

Background ingestion requires care during testing. The default dynamic dreaming mode can take minutes to process new records, leaving the profile empty right after creation. Switching to instant dreaming fixes this for automated tests, though it bills one extra operation per document. The skill also enforces v5 patterns, filtering out obsolete parameters like containerTag from older releases.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add supermemoryai/skills --skill supermemory -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/supermemory/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/supermemory/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add supermemoryai/skills --skill supermemory -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/supermemory/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add supermemoryai/skills --skill supermemory -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/supermemory/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install supermemoryai/skills supermemory
```

2. **Manually: put the files in place**
- File: `.github/skills/supermemory/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add supermemoryai/skills --skill supermemory -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/supermemoryai/skills --path supermemory
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/supermemory/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add supermemoryai/skills --skill supermemory -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/supermemoryai/skills/tree/HEAD/supermemory/SKILL.md

## When to use it
- persist user context across chat sessions using Supermemory v5
- run semantic searches over document chunks
- maintain user profile buckets from unstructured notes
- migrate legacy code away from deprecated v3 and v4 parameters

## Example prompts
- Write a TypeScript function to add a document with instant dreaming in namespace user_alex.
- Show how to search memory chunks for a specific user profile using Python SDK v5.
- Check this codebase for legacy Supermemory containerTag references and update them to v5.

## Similar
- [memory-lancedb-pro](https://affpapa.org/en/nevibecode/skills/memory-lancedb-pro.md) — skill · 643 installs
- [memory-engineering](https://affpapa.org/en/nevibecode/skills/memory-engineering.md) — skill · 29 installs
- [agent-memory-systems](https://affpapa.org/en/nevibecode/skills/sickn33-agent-memory-systems.md) — skill · 2000 installs
- [phoenix-evals](https://affpapa.org/en/nevibecode/skills/phoenix-evals.md) — skill · 1000 installs
- [memory-search](https://affpapa.org/en/nevibecode/skills/ruvnet-memory-search.md) — skill · 750 installs
- [langchain-orchestration](https://affpapa.org/en/nevibecode/skills/langchain-orchestration.md) — skill · 451 installs

## Other versions with the same name
- [supermemory · supermemoryai](https://affpapa.org/en/nevibecode/skills/supermemoryai-supermemory.md) — 548 installs

From the same set: [supermemoryai/skills](https://affpapa.org/en/nevibecode/by/supermemoryai/skills.md) — 3 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md