Supermemory Skills
Four Supermemory skills: the version 5 memory API, the CLI, a benchmark for other memory systems and SVG animations
- 116 ★ on the repository
- Last commit
Extended access
Why this level
- The skill steers code toward the Supermemory cloud API, so app users' data goes to `api.supermemory.ai`
- `memorybench` generates an integration and runs a full benchmark, including with paid memory providers
- The `SUPERMEMORY_API_KEY` key sits in environment variables and must never be committed
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/supermemory-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill steers code toward the Supermemory cloud API, so app users' data goes to `api.supermemory.ai`
- `memorybench` generates an integration and runs a full benchmark, including with paid memory providers
- The `SUPERMEMORY_API_KEY` key sits in environment variables and must never be committed
This is third-party code. Review the repository files before installing.
What it does
The supermemoryai/skills repository holds four skills. The `supermemory` skill describes the Supermemory API version 5 and the TypeScript and Python SDKs: namespaces, adding documents, searching memories and chunks, a subject profile, exact call shapes and the legacy names from versions 3 and 4 an agent must not emit. The `supermemory-cli` skill covers the utility from the `supermemory` 5.x package: add and search, profiles, forgetting, API keys, plugins for coding agents and migrating a project to API 5. The `memorybench` skill compares your own memory implementation with Supermemory, Mem0 and Zep: it asks five setup questions, analyzes your code, generates the integration and runs the whole benchmark. The `svg-animations` skill has nothing to do with memory and teaches an agent to make SVG animations: SMIL, CSS, path drawing and shape morphing. In `supermemory/README.md` this skill is described as a setup assistant that asks questions and wires memory into your application by itself.
Who it is for. Developers of AI apps with memory who integrate the Supermemory API and want an agent to write SDK calls without outdated names.
Good fit when
- An app is gaining memory across sessions and the agent should write Supermemory calls on the version 5 schema
- Old code using `containerTag` and `/v3/` paths is being moved to API 5 with the migration command
- Your own memory implementation has to be compared with Supermemory, Mem0 and Zep on the same data
- An interface needs an animated logo or an SVG icon
Not a fit when
- You need a ready memory plugin for Claude Code: it ships separately, as claude-supermemory in the catalog
- The app stays on API versions 3 and 4: the skill covers only the fifth, and the old API shuts down on 31 December 2026
- You need the Supermemory MCP server: this repository holds skills only
Example request
Add long-term memory to the chatbot with Supermemory: one namespace per user, saving the conversation and pulling the profile at the start of a replyLimitations
The repository has no root README, so the author does not describe installation: the `npx skills add supermemoryai/skills` command is generic and finds the SKILL.md files in the folders. API calls need a key in the `SUPERMEMORY_API_KEY` variable. The `supermemory` skill targets version 5, and the Python framework wrappers, by its own account, still run on the old API. The `dreaming` mode forms memories over several minutes by default, so tests need the `instant` option, which spends an extra operation per document.
How to disable. Delete the `supermemory`, `supermemory-cli`, `memorybench` and `svg-animations` skill folders from the agent skills directory. Remove the `SUPERMEMORY_API_KEY` key from your environment variables.
FAQ
How do I install the Supermemory skills?
With `npx skills add supermemoryai/skills`: it finds the four folders holding SKILL.md. The author does not describe installation separately because the repository has no root README.
Which API versions are supported?
Only the fifth. The `supermemory` skill warns that API versions 3 and 4 are deprecated and shut down on 31 December 2026, and tells you to replace the marks of old code, `containerTag` and `/v3/` paths, with `npx supermemory@latest migrate`.
What does `memorybench` do?
It compares your memory with Supermemory, Mem0 and Zep. It asks five setup questions, analyzes your code, generates the integration code, runs the whole benchmark and shows results per system.
Do I need an API key?
Yes, for Supermemory calls: it is set in `SUPERMEMORY_API_KEY`, and requests go to `https://api.supermemory.ai` with an `Authorization: Bearer sm_...` header. The skills themselves install without a key.
Why is there an SVG animation skill in the set?
It sits in the repository beside the others and has no link to memory: the skill teaches an agent to draw SVG icons, logos, loading spinners and path animation. You do not have to install it with the rest.
Discussion
No questions or reviews yet.
Related
SkillsLong-term memory for agents: a remote MCP server, plugins for Claude Code, Cursor and Codex, and an API for your own apps
A Claude Code skill that pulls memory from Memori Cloud before every non-trivial answer and writes new facts back to it
A skill that turns the local bkmr bookmark database into long-term agent memory with hybrid search and five record types
Shared local memory for AI agents: Claude Code, Codex, Cursor and others find the agreements of past sessions in it and record new ones
Long-term memory for AI agents: a skill and the mindmemos command store facts from conversations and recall them in later sessions
Skills keep project memory in a docs/ai folder: short size-capped files, a one-page handoff and a verifier for the install
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Supermemory Skills (this card) | yes | 116 | ||
| Supermemory | yes | OAuth | 31,536 | the remote MCP server, plugins and memory API, while this set only gives instructions to an agent |
| claude-supermemory | yes | 2,799 | a ready memory plugin for Claude Code with automatic search and conversation saving |
README in short
The repository has no root README, and `supermemory/README.md` serves as the introduction. It explains what Supermemory is, lists the TypeScript and Python SDKs, the moments the skill is called automatically and the reference files: quickstart, SDK guide, API reference, integrations and use cases.
README badge
Original SKILL.md
---
name: supermemory
description: Build with the Supermemory v5 API and SDKs (TypeScript `supermemory` 5.x, Python `supermemory` 5.x, `@supermemory/tools` 3.x). Use when an application needs persistent memory across sessions, per-user personalization, a maintained user profile, or semantic search over documents. Covers the namespace-scoped endpoints, exact SDK call shapes, search and ingestion options, typed filters, and the legacy names that must not be emitted.
---
# Supermemory v5
Supermemory stores documents, extracts memories from them, and serves three things back: ranked search results, a maintained profile per subject, and the source chunks. Every call is scoped to one **namespace**: a user id, a project id, or any boundary you want isolated.
This skill documents **v5**. The legacy v3 and v4 API is deprecated and shuts down on December 31, 2026. If you see `containerTag`, `customId`, `/v3/`, or `/v4/` in a codebase, it is on the legacy API; `npx supermemory@latest migrate` launches a coding agent that upgrades it.
## Versions this skill matches
| Client | Version | Install |
| --- | --- | --- |
| TypeScript SDK and CLI | `supermemory` 5.x | `npm i supermemory` |
| Python SDK | `supermemory` 5.x | `pip install -U supermemory` |
| Framework tools (Vercel AI SDK, OpenAI, Mastra, VoltAgent, Claude memory) | `@supermemory/tools` 3.x | `npm i @supermemory/tools supermemory` |
| Python framework wrappers (`supermemory-openai-sdk`, `supermemory-agent-framework`, pipecat, livekit, cartesia) | still on the legacy API | prefer the core Python SDK until they ship a v5 release |
## Core model
- **Namespace**: the isolation boundary. One document lives in exactly one namespace. Never send two namespaces in one request and never infer scope from a document id.
- **Document**: what you add. Text, a URL, or a file. Give it a stable `id` and repeating that `id` appends or diffs into the same document instead of creating a new one. Use it for conversations: one session id, one document.
- **Memory**: a fact extracted from documents. You never write memories directly; you add documents and the engine forms, updates, and versions them.
- **Profile**: the maintained picture of a namespace's subject. `static` facts, `dynamic` recent context, and optional named `buckets`.
- **Chunk**: a piece of source text. Search with `searchMode: "chunks"` for classic RAG over the raw content.
- **Processing**: `add` returns `{ id, status }` and work continues in the background. `system.status` tracks extraction and indexing. `system.dreamingStatus` tracks memory formation and can finish minutes later. With the default `dreaming: "dynamic"`, a new namespace can show zero memories and an empty profile for several minutes. Use `dreaming: "instant"` in quickstarts, tests, and anywhere the next step reads memories right away. `instant` bills one extra operation per document.
## Canonical API surface