Core Docs

Start here with shared AI context.

Core keeps the context behind a team's work connected across files, decisions, people, projects, and the AI tools they already use. Use these docs to connect one AI tool, organize the first useful records, start one recurring workflow, invite teammates when ready, and troubleshoot setup.

First 30 minutes Connect your first AI tool

StartChoose ChatGPT or Claude

Core prepares the right setup path.

ConnectOpen the AI app

Review the prepared connection and approve it.

More waysDeveloper and local tools

Use a focused guide when you need one.

After setupWork normally

Agents read and write useful context.

PrivacyPrivate by default

Shared spaces are intentional.

Docs navigatorConnect once, then keep working.

Start with ChatGPT or Claude, or choose a focused guide for another tool.

Start with the path that matches your next step

Docs are the product manual. Guides are applied workflow education. Use docs when you need setup, product concepts, access, or troubleshooting details.

What is Core?Understand the product before setup. Your first 30 minutes in CoreCreate a useful starting point without reorganizing everything. Connect your first AI toolUse Core with the agent or MCP-compatible tool you already use. Use Core with MCP-compatible toolsUnderstand the remote MCP endpoint and app-specific setup paths. Organize files, people, work, and decisionsBuild the company context AI needs. Start with one recurring workflowMake context useful before expanding scope. Invite teammates and manage accessShare context deliberately when a workflow becomes collaborative. Troubleshooting and supportFix MCP, auth, reload, and setup issues.

Connect ChatGPT or Claude

During onboarding, Core prepares a personalized connection and opens the right place in your AI app. Approve the connection there, then continue onboarding while Core confirms it in the background.

ChatGPT

Copy address and open ChatGPTCore copies your prepared address and opens Plugins. Turn on Developer mode, add Core with Server URL and OAuth, then approve it.

Claude

Open Claude setupCore opens Claude with the connector name and address filled in. Add it once for the same account across web, Desktop, and mobile.

What changes after Core is connected

Setup is meant to be a one-time step. After that, Core should fade into the background while your work compounds.

01Choose the app

Start with ChatGPT or Claude, or open More ways to connect for a developer tool.

02Connect Core

Use Core's prepared setup action and approve the connection.

03Start normal work

The agent can read visible context before work begins.

04Preserve useful output

Decisions, tasks, files, and checkpoints remain available for the next run.

Your context survives.
Important decisions, checkpoints, and working notes do not disappear when a chat ends.
Your work stays yours.
Private work defaults to your personal Core space. Shared spaces are opt-in and permissioned.
Your agents get smarter together.
The next agent can pick up useful context from the last one instead of rebuilding the world from scratch.
Collaboration stays controlled.
Invite people to Spaces when a project, class, company, or client needs shared context.

More ways to connect

Use a focused guide for Codex, Claude Code, Cursor, VS Code, Windsurf, Hermes, OpenCode, and other compatible developer or local tools.

Guided terminal setup

Use the CLI helper

The installer asks which tool you use, opens Core signup or login, and applies the setup when the tool supports it.

npx -y @gradien/core-agent-setup

Manual fallback

Use the standard Core address

Use this only when an app-specific guide asks for a remote server address outside onboarding. During onboarding, keep the complete personalized address Core gives you.

Name: Core
Authentication: OAuth

https://core.gradien.ai/mcp/continuity

Developer and local guides

Each tool has its own settings, sign-in behavior, and reload rules. Use these after choosing More ways to connect.

How to work after setup

Keep asking for normal work. Core is useful because it lets context travel quietly with the work, not because you have to remember a new ritual.

Pick up the project where we left off.
Remember this decision for future work.
Review this against the direction I have been shaping.
Draft the next version and keep the working notes private.
Create a Space for this project and invite a collaborator when I am ready.

Explicit Core requests are still useful when you want precision: search prior decisions, save a private checkpoint, or create a Space for a team.

Privacy and collaboration

Core starts as a user product. Personal work belongs in your private cloud space by default. Collaboration appears through Spaces you create or join.

Agents can search material you are allowed to see.
Agents should only change shared or team material when you explicitly ask.
Space owners can invite people and choose read or write permissions.
A user can belong to many Spaces, such as a company, class, client project, or team.

Reference

Use these when setting up custom harnesses or debugging a connector.

Core setup guideRendered setup guide for agents and humans. TroubleshootingRecovery steps for OAuth, reload, and connector issues. Full agent-readable contextComplete public Core product and setup context. OAuth protected resource metadataDiscovery metadata for remote MCP clients.

What Is Core Plain-language explanation of Core. Why Core Matters Why personal agent memory and controlled shared context matter. How To Use Core Daily operating loop for external agents. Core FAQ Frequently asked product and setup questions.