Memside

Hub de Continuidade e Memória de IA

Documentação

Memside

Memside is an AI continuity and memory hub for people who work across ChatGPT, Claude, Grok, IDEs, coding agents, and other AI tools that support OAuth, MCP, or API-key connections. It gives you a private place to save reusable context, decisions, operating rules, project notes, and checkpoints so you can move from one AI to another without rebuilding the same background every time.

Use Memside when you want your AI context to survive beyond one chat window. A connected AI tool can retrieve the right memory, continue a project from a checkpoint, follow your saved working preferences, or create new durable context after you approve it. This repository is the public home for Memside integration docs, examples, and support information. It is not a mirror of the private production application source.

Product site: https://www.memside.com

Continuity With Less Repeated Prompting

Memside is built to give AI assistants the right context at the right time: current task state, saved preferences, project notes, checkpoints, and reusable rules. In internal testing and early pilot usage, this helped AI tools stay on track without requiring users to rebuild the same detailed prompt in every new chat or IDE session.

High-level test results:

Context approach	Continuity score
No Context	~45%
Long Context Dump	~84-85%
Memside Context	~96-99%
Very Detailed Manual Prompt	~97-99%

Token savings: in separate context-reuse tests, Memside reduced repeated full-context transfer by 83-91% on representative light, medium, and heavy project datasets.

A very detailed manual prompt means a long prompt where the user includes every important detail by hand: project state, preferences, decisions, references, and next steps. With Memside, the workflow is simpler: ask the AI to save the checkpoint, references, and useful context, then move to a new chat and ask it to continue from that checkpoint using Memside.

Results are based on internal tests and early pilot usage patterns. Performance varies by model, provider, prompt style, and workflow. See Continuity and context results for details.

Connect Memside

Memside supports hosted MCP access for AI tools that can connect to remote MCP servers. MCP gives compatible AI clients a standard way to use Memside as a continuity layer instead of locking your memory into one assistant.

https://api.memside.com/mcp/

If your AI tool supports OAuth for MCP, choose OAuth during setup and sign in with your Memside account. If your tool supports API-key auth instead, create an API key in Memside and use it as a bearer token.

Start here:

Developer Quickstart

Use the path that matches your tool.

Goal	Use	Start here
Connect ChatGPT, Grok, Claude, or another hosted client	OAuth MCP	Client guides
Connect IDEs and coding agents such as VS Code, Copilot, Cursor, Claude Code, Codex, Antigravity, opencode, or a local MCP client	Bearer-header MCP	VS Code guide
Call Memside from scripts or automation	API key	API keys

For a direct API check, create a Memside API key and run:

curl https://api.memside.com/context/startup \
  -H "Authorization: Bearer mem_sk_your_key_here"

For a runnable JavaScript example:

cd examples/javascript
npm run startup

Set MEMSIDE_API_KEY before running examples. See Developer quickstart for the full setup.

JavaScript SDK

Memside publishes a lightweight JavaScript SDK for public API-key workflows:

npm install memside

Basic usage:

import { MemsideClient } from "memside";

const memside = new MemsideClient({
  apiKey: process.env.MEMSIDE_API_KEY
});

const startup = await memside.context.startup();
console.log(startup);

The JavaScript SDK wraps public Memside API routes for startup context, resume context, workspace profile, Memory operations, and Subject organization. See packages/memside for package details.

Python SDK

Memside also publishes a lightweight Python SDK for public API-key workflows:

pip install memside

Basic usage:

from memside import MemsideClient

client = MemsideClient(api_key="mem_sk_your_key_here")

startup = client.context_startup()
print(startup)

The Python SDK wraps the same public Memside API areas as the JavaScript SDK. See packages/python for package details.

MCP Server Setup

Use this hosted MCP server URL in clients that support remote MCP:

https://api.memside.com/mcp/

For ChatGPT, Grok, Claude, and other clients that offer OAuth during MCP setup, choose OAuth and sign in with your Memside account.

For clients that use bearer headers, create a Memside API key and pass it as:

Authorization: Bearer mem_sk_your_memside_api_key

VS Code and GitHub Copilot can use a workspace .vscode/mcp.json file:

{
  "servers": {
    "memside": {
      "type": "http",
      "url": "https://api.memside.com/mcp/",
      "headers": {
        "Authorization": "Bearer mem_sk_your_memside_api_key"
      }
    }
  }
}

Keep real API keys out of shared files. Use local user-level configuration or secret storage when the config is shared with a team.

Detailed setup guides are available for VS Code, GitHub Copilot, ChatGPT, Grok, Claude Code, Cursor, Codex, Antigravity, and opencode.

MCP Registry

This repository includes server.json for the official MCP Registry. It describes Memside as a hosted remote MCP server using Streamable HTTP at:

https://api.memside.com/mcp/

The registry entry is published under:

io.github.memside/memside

See MCP Registry metadata for registry and endpoint checks.

This repository also includes lightweight third-party directory metadata for Glama, Open Plugins, and Cursor plugin discovery. These files point to the same hosted MCP server URL and do not contain credentials.

What You Can Do

With Memside connected, an AI tool can search your saved memories, fetch specific context, create new memories after you approve, update checkpoints, and build compact startup or resume packets. The goal is to keep useful context portable without turning every AI conversation into a long manual setup step.

This is useful when you want to move a project between ChatGPT, Claude, Grok, IDEs, coding agents, or other compatible AI clients. Memside can help the next AI understand what you are building, what decisions were already made, what rules it should follow, and what the next step is.

Memside keeps the normal product boundary intact. Private user data is scoped to the signed-in user, secret memories are excluded from AI-facing MCP and API-key flows, and destructive actions require stronger confirmation.

Key Features

Memside is designed around continuity, selective context retrieval, and user control. The core features are:

Startup and resume context for compact handoffs.
Operating Rules for durable behavior guidance.
User AI Profile for personal working preferences.
AI Skills for reusable instruction packs.
Public, private, and secret memories for practical data boundaries.
MCP and API-key access for connecting multiple AI clients.

API Examples

The examples in this repo use public Memside API surfaces only.

The JavaScript and Python examples use normal HTTP requests against public Memside API surfaces.

The machine-readable OpenAPI document contains only the approved API-key contract. It excludes signed-in application, account, administration, billing, and infrastructure operations.

Public Repo Scope

This repo contains:

setup guides for MCP clients
MCP Registry metadata
third-party MCP directory metadata
Cursor plugin metadata
technical product capability docs
API-key usage examples
developer quickstart and runnable examples
public troubleshooting notes
security and support information
public changelog entries

This repo does not contain:

private Memside application source
secrets or deployment configuration
database or internal operations notes
non-public product architecture

Support

For support, contact support@memside.com or use the support links in the Memside app.

Security reports should follow SECURITY.md.

Copyright and Use

This repository is public documentation, not open-source application code. See LICENSE.md for the repository terms.

Memside and related names, product concepts, documentation, and branding remain the property of their respective owners.