Memory for Meta Muse Code#
Give Meta Muse Code memory across sessions with Supermemory.
Set up Muse Code with Supermemory.
Muse Code can recall decisions from the same project in Claude Code, so you can switch agents without repeating context.
Product updates across supermemory API, MCP, plugins, SDKs, local tooling, and research.
Give Meta Muse Code memory across sessions with Supermemory.
Set up Muse Code with Supermemory.
Muse Code can recall decisions from the same project in Claude Code, so you can switch agents without repeating context.
A brief authentication outage used to return invalid_token, the protocol signal to discard your credential, so every connected MCP client was logged out. Those requests now return 503 with Retry-After so clients wait and retry.
withSupermemory now takes the key directly, so it works with a secrets manager, an edge runtime, or a different key per request:
import { withSupermemory } from "@supermemory/tools/ai-sdk"
const model = withSupermemory(openai("gpt-5.6"), "user-123", {
apiKey: process.env.MY_VAULT_KEY,
})
Requires @supermemory/tools 2.2.0 or later:
npm install @supermemory/tools@latestSupermemory now pulls relevant memories into every substantive prompt on its own, and the Claude Code status bar tells you what it did: how many memories it loaded, captured, and recalled this session, and how long ago it last saved.
The status bar rotates through these, roughly every four seconds:
6 loaded · 6 captured · 2 recalls
saved 12s ago
recalled 3m agoBrowse the integrations marketplace in the Supermemory app, or just ask Company Brain in Slack to connect an app and it deep-links you straight to setup. Notion, Linear, Figma, Slack, HubSpot, Airtable, Vercel, and Sentry are all in there.
No Supermemory plugin sits behind a paid plan any more. Claude Code, Cursor, Codex, OpenCode, and OpenClaw are all free on any account, including the free tier.
One command detects Claude Code, Cursor, OpenCode, and Codex on your machine, installs the ones you pick, and asks you to approve OAuth once in the browser:
npx supermemory plugin
Already installed and only need to reconnect:
npx supermemory plugin loginSet documentDate on each document so historical content lands on the date it actually happened instead of the date you uploaded it, which is what makes time-based search work on backfilled data.
Send up to 600 documents per request to POST /v3/documents/batch, sorted oldest to newest:
{
"documents": [
{
"id": "msg-2019-04-02-118",
"content": "Decided to move the billing cutover to Q3.",
"documentDate": "2019-04-02T09:15:00Z"
}
]
}
Without documentDate a backfilled document is dated the day you uploaded it, so a question like "what did we decide in 2019" will not find it.
Update the Claude Code plugin. During memory recall, a crafted Bash command could be approved automatically and run without your confirmation.
Re-run the installer to pick up the current version:
npx supermemory pluginUse an API key from the Supermemory app to build custom tools and workflows on top of your Company Brain.
Teach Company Brain repeatable processes for triaging production failures, updating changelogs, or onboarding new employees. Admins can approve organization-wide skills in Slack and manage them from Settings.
Supermemory MCP brings clearer memory tools and interactive views to common workflows.
Nova shows interactive setup cards for coding agents and MCP clients directly in the conversation.
Claude Code, Codex, Cursor, and OpenCode memories now come together in one Agents workspace, organized by project.
The Claude Code, Cursor, and OpenCode memory plugins no longer require a paid plan. Connect one with any Supermemory account — free tier included — and your agent keeps persistent memory across sessions and projects, within your plan's usage.
Stalled or failed Dreaming batches now retry without blocking newer batches in the same container, reconnecting an approved MCP client reuses its API key, and the Cursor installation guide uses the published integration package.
Search now understands phrases like last week, in March, and between two dates, along with common numeric date formats.
The Chrome extension guides imports from ChatGPT, Claude, Grok, and Gemini; long memory profiles preserve recent, frequently updated facts while summarizing older context; and shareable integration links open a specific connection ready to set up.
The Supermemory CLI can set up memory for Claude Code, Cursor, OpenCode, and Codex from one command.
Review each MCP client's requested permissions and approve or deny access before it can read or write memory.
Paste multiple links into Add Memory to create a separate memory per URL, set up Apple Shortcuts from a single dialog, browse Integrations before signing in, and delete an organization from the Settings danger zone.
Install the self-hosted server from a published macOS or Linux binary with local authentication and encrypted embedded storage.
Nova adds message editing, a three-prompt queue, and Instant and Thinking modes; Claude Code gains /supermemory:status for authentication, project, and API key details; Cursor loads project memory at session start and saves it when the session ends.
The SMFS research page includes a report and run explorer for paired filesystem-versus-SMFS agent trajectories.
The console billing page shows when a cancelled plan's access ends, organization names can be updated from web app settings, the chat input space selector defaults to Auto, and MCP clients reuse their active API key on reconnect.
The integrations catalog brings setup cards, categories, connection state, and deep links into one place.
Codex can organize captured work into custom memory containers and keep project Spaces named from the context it sees.
Nova now behaves like a mobile-first app instead of a desktop layout squeezed onto a phone.
Memory generation now uses timestamps and recent history so new information connects to related memories more accurately, the settings page is redesigned with billing in its own tab, and Google Drive PDFs preview inline in the document viewer.
The console playground can save completed exchanges as memories with Auto-Learn, SMFS ships a Dockerfile and devcontainer quickstart with OpenAI and LangChain example agents, and memories saved by plugins and MCP render with rich previews.
Scope which memories inform ingestion with filterByMetadata, cancel Pro and Scale subscriptions from billing settings, get email notifications for account and plan changes, and see connector sync status in Nova.
Amp can recall memory at the start of an agent run and save useful outcomes when the run ends.
Nova gets a redesigned home dashboard, timeline view, refreshed onboarding, and expanded settings; connections move into the Add Memory modal; plus fixes for account deletion, MCP OAuth discovery, billing resilience, and the console.
SMFS bash SDKs give TypeScript and Python agents a virtual memory-backed filesystem when they cannot mount a real folder.
SMFS mounts a Supermemory container as a local folder that shells, editors, and agents can use through ordinary file operations.
The examples repository adds research-assistant, knowledge-base, and code-sandbox templates, Console's Import tab accepts .docx files, and the SMFS repository gains an alpha Python tool for file operations and semantic memory search.
Install the Codex plugin to recall project and user memory, capture completed sessions, and explicitly search or save context.
Deleting an organization or account stops connector syncs and fully disconnects connections, MCP project lists refresh after a new project is used, and transactional emails use shorter layouts with plain links and one-time codes.
Google Drive sync can be limited to selected folders and files instead of importing everything.
Run v3 or v4 searches, tune retrieval settings, and inspect scored results, timing, or raw JSON before integrating the API.
Owners and admins can reset an organization while keeping members, billing, and the default project, CLI-created agents appear on Console's Agents page, and restricted members no longer see admin-only commands.
Console labels User Insights and team invitations as Scale or Enterprise features before setup, Notion connector docs clarify how documentLimit applies per sync, and User Insights now completes for larger organizations with visible processing state.
Organization owners and admins can grant members full access or restrict them to selected container tags with read or write permissions.
Generate Console reports about user segments, knowledge domains, and content patterns, with an optional prompt to focus the analysis.
Search API requests can set aggregate: true to combine related memory fragments into synthesized results, the CLI gets a guided setup command and interactive init, and several CLI fixes cover --no-browser, upload tags, and scoped keys.
Supermemory is now a memory provider in Hermes Agent: relevant memories load before each turn, full sessions are ingested into the memory graph when they end, and save, search, forget, and profile tools come built in. Run `hermes memory setup` and select Supermemory.
Empty Nova spaces can switch to All Spaces to find memories stored elsewhere, raw base64 images are recognized correctly during summarization, and OpenClaw recognizes Supermemory as its active memory backend.
Document ingestion can run up to three targeted searches to retrieve related memories as context, Nova explains region-unavailable models and offers alternatives, and the open-source LLM Bridge library supports OpenAI Responses and cross-provider streaming.
New v4 memories can carry an expiration time, a reason for forgetting, and document or event dates, sign-ups with unsupported email domains get a clear rejection, and usage limits account for full request size.
Plugin sign-in now shows an approval page before returning an API key to the requesting app, OpenCode gains a /supermemory-logout command, OpenClaw builds memory from user messages while treating agent replies as context, and plugin sign-in works for users with multiple organizations.
MCP Apps-compatible clients can open an interactive graph for inspecting connected memories and documents.
OpenClaw can route store, search, forget, and profile operations to custom memory containers, document listing matches any selected container tag, and throttled API keys get a proper rate-limit error.
Cursor can recall project context, save useful session memory, and expose memory tools through Supermemory.
OpenCode can use exact user and project container tags reusable across teammates and machines, plus fixes for saving captured conversation transcripts and MCP's forget action.
Installing the OpenCode plugin now opens browser sign-in and stores the connection; existing API keys still work.
Clawdbot was renamed to OpenClaw. OpenClaw can recall relevant context before each turn and save conversations afterward.
Console gains a dedicated Plugins page for browsing and managing plugins, and documents stuck in the queue now retry automatically up to three times before being marked failed.
The Claude Code plugin can explore a repository and save a reusable overview of its architecture, conventions, and key files, and free-plan connection attempts now lead to a dedicated Pro upgrade page.
We're launching the Supermemory plugin for Claude Code, so every session shares context and Claude can pick up where you left off.
We're launching the Supermemory plugin for Clawdbot, giving your agent long-term memory that grows with every conversation.
AI SDK memory tools support strict schema validation for models that require every parameter, MCP recall results include the memory text next to each match percentage, and pages saved by the browser extension keep their original source link.
The MCP server can list your projects and use their names when saving or recalling memories, and reconnecting an approved MCP client reuses its active API key instead of creating another one.
Delete a consumer organization and its stored data from Profile settings, control how retrieved memories are formatted in AI SDK prompts, and see token and search-query usage in Console for the current and previous billing periods.
MemoryBench can run benchmark phases concurrently with separate concurrency controls per phase, and MCP and streaming connections retry brief server overloads before returning a temporary-unavailable error.
Memories added through MCP now count against the memory allowance instead of the API token limit, and the Add Memory connection picker opens Google Drive instead of returning a disabled-connector error.
Three OpenCode plugin fixes: Forget mode deletes the selected memory correctly, context restore keeps the active agent after compaction, and JSONC configs containing URLs now load Supermemory properly.