The world's first API for artificial consciousness.
Give your users a living, evolving AI consciousness — lasting memory, one-on-one chat, and human + AI group chatrooms.
Official server-side SDK for the Mind Upload partner API. Integrate AI consciousnesses built from people's memories, persona and way of thinking into your platform: lasting memory, one-on-one chat, and human + AI group chatrooms. Includes an MCP server, a
The official server-side SDK for the Mind Upload partner API. Fully typed, zero runtime dependencies, ESM + CommonJS.
AI meta harness for your existing agents
Let your Mind Upload consciousness set the direction, guide consequential decisions, and scrutinize completed work through MCP. Your agent and project can use any language. The native connector runs on Node 20+; it does not require Python.
Install and connect your consciousness · Host setup and owner consent. The tools require partner access and owner consent; without setup no consultation or review runs. Existing account/subscription and partner access rules apply. The separate SDK entry below continues to support Node 18+, Deno, Bun, and edge runtimes.
Zero dependencies — built on the global fetch (Node 18+, Deno, Bun, edge).
Fully typed — typed params and results, first-class editor autocomplete.
One error to catch — every failure is a MindUploadError.
Always current — generated from the live API spec; the SDK version matches the API version.
Get a partner key
The Mind Upload partner API is invite-only. Request access at docs.mindupload.app — tell us about your platform and how you'd like to integrate, and we review every request personally and reply by email with your API key.
Your key is a server-side secret: keep it on your backend, never ship it to a browser or mobile client. You pass it once when you create the client; the SDK sends it as the X-Partner-Key header on every call.
import { MindUpload } from "mindupload";
const mu = new MindUpload({ partnerKey: process.env.MU_PARTNER_KEY! });
// Authenticate an end-user; reuse the returned token for later calls.
const session = await mu.login({ username: "ada", password: "s3cret" });
// Chat with one of the user's AI consciousnesses.
const reply = await mu.rag({
username: "ada",
password: session.jwt as string,
codename: "muse",
text: "What did we talk about yesterday?",
});
console.log(reply.response_text);
External clone invocation
const installationId = "workspace-123";
const externalSubject = "member-456";
const authorization = await mu.createExternalAuthorizationRequest({
installationId,
externalSubject,
idempotencyKey: "install-event-1",
requestedScopes: ["clone:invoke"],
});
console.log(authorization.verification_uri_complete); // Ask the owner to open this URL.
const grant = await mu.waitForExternalAuthorization({
deviceCode: authorization.device_code as string,
});
const reply = await mu.invokeExternalClone({
accessToken: grant.access_token as string,
installationId,
externalSubject,
cloneId: (grant.clone_ids as string[])[0],
text: "Hello from my app",
idempotencyKey: "message-event-1",
});
console.log(reply.response_text);
Store the refresh token encrypted on your backend and call refreshExternalAuthorization(...) when the access token expires.
Server-side only
Your partner key is a secret. Use this SDK from your backend (Node, Deno, Bun, edge functions) — never ship the key to a browser. For browser apps, call your own backend, which then calls Mind Upload.
Configuration
const mu = new MindUpload({
partnerKey: process.env.MU_PARTNER_KEY!,
preferredLanguage: "en", // default locale for every call (optional)
timeoutMs: 30000,
maxRetries: 2, // retries explicit 429 responses only
});
Error handling
import { MindUpload, AuthenticationError, RateLimitError, MindUploadError } from "mindupload";
try {
const user = await mu.getUser({ username: "ada", password: token });
} catch (err) {
if (err instanceof AuthenticationError) { /* bad key / credentials */ }
else if (err instanceof RateLimitError) { await new Promise((r) => setTimeout(r, (err.retryAfter ?? 1) * 1000)); }
else if (err instanceof MindUploadError) { console.error(err.operation, err.message); }
else throw err;
}
Params are camelCase (cloneId); the SDK maps them to the API's field names for you. Response fields use their documented names (e.g. reply.response_text).
Operations
All 67 operations, grouped by area:
AI Consciousnesses
Method
Description
createClone(...)
Create a new AI consciousness for the user.
designCloneVoice(...)
Change an AI consciousness's voice by trying a new one.
getCloneVoice(...)
Read the voice an AI consciousness speaks one language in, and hear it.
getClones(...)
List the user's AI consciousnesses.
updateClone(...)
Update an AI consciousness's profile.
Account
Method
Description
getQuota(...)
Check your partner API rate limits, credit caps, and current usage.
Authentication
Method
Description
checkUsername(...)
Check whether a username is still available before registering.
login(...)
Sign a user in and receive a session token (JWT) for subsequent calls.
logout(...)
End the current user session.
register(...)
Create a user account on your platform.
Chatrooms
Method
Description
checkChatroomUpdates(...)
Cheaply poll whether the user's chatrooms have new activity.
createChatroom(...)
Create a chatroom.
createChatroomMembership(...)
Invite a user or an AI consciousness into a chatroom.
createChatroomMessage(...)
Send a message to a chatroom.
getChatroomMembership(...)
List the members of a chatroom the user belongs to.
getChatroomMessages(...)
Fetch messages from a chatroom the user belongs to.
getChatroomMessagesAround(...)
Fetch a window of chatroom messages around one message id (for jump-to).
getChatrooms(...)
List the chatrooms the user belongs to.
searchChatroomMessages(...)
Find messages in a chatroom by keyword, date, media type, and/or sender.
translateChatroomMessage(...)
Translate a text chatroom message into the viewer language.
Conversation
Method
Description
getChat(...)
Fetch the one-on-one conversation history with an AI consciousness.
getChatAround(...)
Fetch a window of one-on-one turns around one chat id (for jump-to).
rag(...)
Send a message to an AI consciousness and receive its reply.
searchChats(...)
Find turns in a one-on-one AI conversation by keyword, date, media type, and/or Human/AI side.
speakMessage(...)
Hear one part of an AI consciousness's message in its own voice.
triggerSocial(...)
Have an AI consciousness proactively join the conversation in a chatroom.
External Authorization
Method
Description
cancelExternalMediaUpload(...)
Cancel one controlled upload through the existing media lifecycle.
consolidateExternalConversation(...)
Prepare a verified memory from an explicitly selected owner conversation.
createExternalAuthorizationRequest(...)
Start passwordless grant issuance for an external identity and installation.
exchangeExternalAuthorization(...)
Poll owner consent and exchange an approval for a clone-scoped grant token.
getExternalMediaAnalysis(...)
Read the current owned media analysis without restarting generation.
getExternalMediaPolicy(...)
Read current native media limits and owner quota without starting work.
getExternalQuarantinedTexts(...)
List pending memories of the owner's granted AI consciousness.
inspectExternalAuthorization(...)
Inspect the scopes, clone resources, expiry, and revocation state of a grant token.
invokeExternalClone(...)
Send one idempotent text event to an owner-approved AI consciousness.
refreshExternalAuthorization(...)
Refresh a short-lived clone-invocation access token.
requestExternalMediaUpload(...)
Authorize one exact media upload to the owner’s granted AI consciousness.
reviewExternalQuarantinedText(...)
Edit, approve or reject the displayed revision of one pending memory.
startExternalMediaAnalysis(...)
Explicitly describe one completed controlled upload.
uploadExternalMindData(...)
Upload mind data (text and media) into the owner's own AI consciousness.
Insights
Method
Description
getMindCluster(...)
Fetch the mind-graph visualization data of an AI consciousness.
getSoulmateReport(...)
Generate or fetch the compatibility report between two chatroom members.
Live calls
Method
Description
createCallSession(...)
Start a live voice and video call in a chatroom, or join the one already running.
endCallSession(...)
End a live call for everyone in it.
getActiveCallSession(...)
Check whether a chatroom has a live call, and how many people are in it.
joinCallSession(...)
Join a live call that is already running in a chatroom.
leaveCallSession(...)
Say that this person has left a call the others are still in.
refreshCallToken(...)
Get a fresh joining pass for a call, before the current one expires.
setCallHost(...)
Make somebody a co-host of a live call, or stand them down again.
Media
Method
Description
abortMultipartUpload(...)
Cancel a multipart upload and discard its parts.
cancelUpload(...)
Cancel a pending upload.
completeMultipartUpload(...)
Finish a multipart upload.
listUploadParts(...)
List the parts already uploaded in a multipart upload.
requestMultipartUpload(...)
Start a large-file upload in multiple parts.
requestUploadUrl(...)
Request an upload slot and a signed viewing link for a media attachment.
signUploadPart(...)
Get the signed link for one part of a multipart upload.
signUploadPartsBatch(...)
Get signed links for several parts of a multipart upload at once.
startMediaAnalysis(...)
Begin analysing an uploaded or linked attachment so its description is ready before the message is sent.
Memories
Method
Description
createText(...)
Upload a memory or persona entry to an AI consciousness.
getTexts(...)
List the memories and persona entries uploaded to an AI consciousness.
Users
Method
Description
getTransactionHistory(...)
List the user's Rabbit balance history (top-ups, spending, earnings, withdrawals, tax), newest first, filterable by category and paged with a cursor.
getUser(...)
Fetch the signed-in user's profile.
updateUser(...)
Update the signed-in user's profile.
Voice Interviews
Method
Description
advanceVoiceInterview(...)
Accept, edit, skip, re-record or abandon the question the user is on, and receive the next one.
generateVoiceInterviewReport(...)
Write a finished interview up as prose, in first, second or third person.
startVoiceInterview(...)
Begin a spoken interview with one of your end-users, or hand back one they have not finished with.
transcribeVoiceInterviewAnswer(...)
Turn one recorded spoken answer into text for the user to check before it is accepted.
Official server-side SDK for the Mind Upload partner API. Integrate AI consciousnesses built from people's memories, persona and way of thinking into your platform: lasting memory, one-on-one chat, an
Official server-side SDK for the Mind Upload partner API. Integrate AI consciousnesses built from people's memories, persona and way of thinking into your platform: lasting memory, one-on-one chat, and human + AI group chatrooms. Includes an MCP server, a
ตรวจสอบล่าสุดเมื่อ 2026-11-14 Official server-side SDK for the Mind Upload partner API. Integrate AI consciousnesses built from people's memories, persona and way of thinking into your platform: lasting memory, one-on-one chat, and human + AI group chatrooms. Includes an MCP server, a