Skip to content

Install Cortex

View as Markdown

Cortex lets your agents preserve and reuse what they learn from your work. You do not need to write Modules or fill a knowledge base before starting.

Open guided setup (new tab) and choose Ask my agent to help, or give your agent the complete installation guide:

Help me set up Cortex for this agent using this guide. Handle the setup you can, and guide me through sign-in and any permissions only I can complete.

The guide below is also available if you prefer to follow the steps yourself. After setup, continue your normal work; the agent maintains useful knowledge as it learns from your decisions and corrections.

Choose your agent

To use Cortex in your browser, see Use the Cortex web app.

Before you start

Read the Workspace pricing FAQ.

Cloud pricing lists OAuth as included at no additional charge. See Cloud pricing for current rates. Any applicable data-transfer charges depend on active Cloud meters.

You need access to an Account that can use Cortex. An Account is the shared space that owns your knowledge and controls access. Create an Account (new tab) or sign in to an existing Account (new tab). The Try Cortex button opens account creation in a new tab so this guide stays open. Use the same Account in your agent and the Cortex web app. Signing in to the website does not connect the agent.

Check whether Cortex already works in the agent before installing anything. Ask it to list the Modules it can access. A successful Cortex call, including an empty list, confirms the connection. If that works, check the instructions and tool settings below without creating another connection.

CLI access

Use this path when your agent can execute shell commands. If the Socra CLI is absent, run the installer for your operating system.

For macOS or Linux:

Bash
curl -fsSL https://cli.socra.cloud/install.sh | sh

For Windows, run this in PowerShell:

PowerShell
irm https://cli.socra.cloud/install.ps1 | iex

Open a new terminal. Add the Cortex commands:

Bash
socra install cortex

Sign in and select your Account in the browser that opens:

Bash
socra account login

Wait for the terminal to confirm sign-in. If you selected the wrong Account, run socra account switch. Then verify access:

Bash
socra cortex module list

Ask the agent to run that command itself. A returned list, including an empty list, confirms CLI access. A successful CLI call does not prove that a separate MCP connection works.

CLI installation does not add persistent agent instructions. You can add the suggested instructions to your host's persistent instructions, preserving existing text. Alternatively, tell the agent when to use Cortex as you work. Do not run socra cortex setup for CLI-only access; that command configures detected coding-agent plugins.

If you saved instructions, start a new agent conversation and ask:

Text
Run socra cortex map to list the Modules I can access (an empty list is valid). Separately, report whether this new conversation received persistent Cortex guidance and what it requires. Do not change anything.

Check both the command result and the agent's report about its guidance. If instructions are missing, check where they were saved and whether that location applies to this conversation. If you skipped instructions, CLI access can still work; report the guidance as skipped.

Suggested instructions

The connection gives your agent tools. These instructions teach it how to use them: when to retrieve knowledge, which specifics to preserve from conversation and work, and how to keep Modules and their dependencies current. This is why setup includes guidance as well as sign-in. You can adapt it to how you work; no repeated reminder to document each decision is needed.

To adapt the instructions to how you work, ask your agent:

markdown
Adapt https://workspace.socra.com/docs/cortex/instructions.md to how I already work, and help me save the result in my agent’s persistent instructions.
Text
Cortex helps people and teams stop repeating themselves to their AI. It keeps their preferences, requirements, decisions, and reasons in a single source of truth that agents can retrieve across conversations and tools.

Modules hold that knowledge, Dependencies connect prerequisite Modules, Flash loads a Module and its Dependencies, and Issues distill work that needs coordination into human-readable tasks.

Before executing a task, Flash its narrowest relevant Module(s). Flash known targets directly; otherwise prefer Search. Use Map only when Search leaves subjects or relationships unclear. Reuse a successful Flash while the required knowledge remains available in context. Retrieve missing knowledge again when needed.

When conversation or work reveals preferences, requirements, decisions, or other specific knowledge, update the relevant Modules or create missing ones. Preserve the knowledge and its reasons and keep Dependencies consistent. Briefly name the affected Modules and explain what changed and why.

The Codex and Grok Build plugins deliver Cortex guidance through the socra-cortex skill. These packages have no SessionStart hook. The Claude Code, Cursor, and GitHub Copilot CLI plugins deliver guidance through a session-start hook. ChatGPT’s plugin, CLI-only access, and direct MCP connections require saving instructions separately alongside your existing persistent instructions. The guide for your agent shows where to save them. If your agent cannot save them itself, it should show you the text and the steps to save it.

Choose your review preference

The supplied guidance tells the agent to maintain useful knowledge and briefly explain its changes. You can customize that behavior. For example:

  • Automatic maintenance: “Keep our Cortex knowledge current as we work, within the material and access I have authorized. Tell me what changed and why.”
  • Review first: “Recommend changes to Cortex Modules and their dependencies, but show me the proposed change and wait for approval before saving it.”

Ask your agent to save the preference alongside your existing persistent instructions so it applies in future sessions. You can change it later. This changes who reviews knowledge updates; it does not make you responsible for writing them.

Your host's tool confirmations and Cortex's access permissions are separate controls. Instructions guide behavior, while those controls enforce what a tool can do. Keep any approval requirements you want for publication, deployment or other actions. See the security model.

After installation

The connection is verified when the configured agent makes a real Cortex call and receives a result. A new Account can return an empty list. An access error or a response without a call is not verification.

Keep working with your agent. It can preserve useful knowledge from the next task or from existing material you authorize it to inspect. The quickstart shows that ordinary-work flow. Installation does not require creating a Module.

Complete guide for agents

Open the complete installation guide as Markdown to give your agent all supported paths in one document.

See also