cortex.

A shared memory for your team & agents

Your team’s
hive mind.
With governance.

Every decision, connected. Every lesson, remembered. Shared understanding for your people and AI agents — with your team in control.

Context, recovered

“Why did we build it this way?”

Found the decision. Linked the implementation. Your next engineer starts here.

Decision → implementation → lesson

THE TEAMMATE THAT NEVER FORGETSSCROLL TO DISCOVER ↓

Your tools. One shared context.

Claude CodeCursorCodexGitHub Copilot MCP clients

The Cortex platform

A little less repetition.
A lot more collective intelligence.

Your tools create the context. Cortex turns it into knowledge your people and agents can build on.

GitHub + code memory

Your codebase. With a memory.

Connect a repository to a project. The CocoIndex-powered indexer turns code into searchable memories, so your next agent starts with the implementation in context.

Illustrative workflow
acme / payments main
01 async function retryPayment() {02 const attempts = 203 // The why belongs with the code.04 }
Retry boundary → provider timeoutImplementation linked to the decision

Code indexing requires the connected indexer service.

Background agents

The work happens. Context follows.

Bind a connected source to a project. New activity becomes draft memories, ready for owner review or your configured auto-merge policy.

Illustrative workflow
#engineering Source connected
“Let’s cap retries at two. The provider
times out after the third attempt.”
Payment retry policySource attached · awaiting review
Draft

Dreams

Wake up to connected knowledge.

Schedule a review of shared memories. Dreams updates useful links and flags possible duplicates for you to review.

Illustrative workflow
Connections found. Context restored.

Digests

Catch up without the archaeology.

Get a weekly digest of what changed and what your agents learned. Decisions, discoveries, and project updates in one readable briefing.

Illustrative workflow
Your week in context Weekly briefing
  • 01 The retry policy changed
  • 02 A deployment lesson worth keeping
  • 03 What the team learned next
Less catching up. More moving forward.

Chat

Ask the team. Even after hours.

Ask Cortex about your memories and connected tools. Follow the sources, recover the reasoning, and carry the answer into your next task.

Illustrative workflow

Why do we retry twice?

The provider times out on attempt three.
The team capped retries to avoid duplicate charges.
↗ Payment retry policy
The answer. And the reasoning behind it.

Governance + graph

Shared knowledge. Earned trust.

Keep drafts private until review. Approve what belongs, explore how it connects, and keep each project inside its own access boundaries.

Illustrative workflow
Your team sets the boundaries.
Private draftOwner review Shared

Integrations

Different tools.
Shared understanding.

The decision in Slack. The change in GitHub. The thinking in your docs. Bring it all into orbit around your team.

Connect your workspace
ONE CONNECTED WORKSPACE
01 / Capture02 / Review03 / Recall
Knowledge in motion.

One team. Every tool. A shared starting point.

You choose the accounts. Project membership controls access to shared memories.

02 / From lost to connected

Someone leaves.
The knowledge stays.

It's 2 a.m. An incident hits the system your teammate built. Cortex gives you a place to find their reasoning, the known edge cases, and the decisions behind the code.

Connect your first agent
CORTEX / SHARED CONTEXT

ILLUSTRATIVE WORKFLOW

Why does checkout retry twice?

01

Recall the decision

Payment retries · architecture

02

Follow the relationship

Provider timeout · known edge case

03

Move forward with context

The reasoning is still here.

Honest comparison

Cortex vs. the field.

Capture, connect, review, and recall. See how the whole workflow compares, from the first source to the next teammate.

CapabilityCortexTurnstoneAlmanacGlenSupermemoryMem0
Built aroundGoverned team memoryLocal AI workspaceAlways-on agentAgent learning layerMemory & context APIMemory API
Connected work context5 app integrationsApps, browser & filesApps & company wikiSessions, apps & docsConnectors & syncAPI & integrations
Background captureSources → project draftsContinuous brain updatesSelf-updating wikiContinuous captureExtraction pipelineFact extraction
GitHub repository → code memoriesCocoIndex indexer¹Agent-backed code context
Chat with your work contextBuilt-in chatBuilt-in workspaceApp, Slack & iMessageWeb app & Slack
Scheduled link review + duplicate reportsDreams
Weekly team memory briefingDigests
Draft → merge request → shared memoryOwner / policy review

Based on linked public product pages, reviewed September 15, 2026. A dash means this specific workflow was not documented, not that the product cannot support it. Features and plan availability vary. ¹ Requires the connected code-indexer service.

Pricing

Flat per seat, no surprise invoice.

One workspace for your team's context. Choose the plan that fits how you work, with hosted infrastructure taken care of.

Team

Early access

$20/ seat / mo

We run the infra, backups, and embeddings. You just invite your team.

  • Full MCP tool set + REST API + web UI
  • Flat per-seat price — no per-token or per-query metering
  • Hybrid FTS + pgvector search, draft/merge review, chat, integrations
  • Automatic backups + managed pgvector search
  • Email support
Start trial

Org

$100/ seat / mo

For teams that want personalized digests and higher usage ceilings on top of everything in Team.

  • Everything in Team
  • Personalized weekly digest per member
  • Higher included usage allowance
  • Priority support
Talk to us

License

Custom

For orgs that need single-tenant, isolated infrastructure but still want a contract, an SLA, and a phone number to call.

  • Single-tenant deployment on your own cloud
  • SSO/SAML + audit log
  • Dedicated SLA
  • Annual contract, volume seat pricing
  • Priority roadmap input
Book a call

Built on trust

Shared knowledge.
Clear boundaries.

Your team's memory deserves the same care as the work that created it.

Access follows membership

Organizations and projects define who can access each memory. Your team works inside its own boundaries.

Review before sharing

Enable approval on a project so member contributions stay drafts until an owner reviews them.

Deployment that fits

Start with hosted Cortex. The License plan offers a single-tenant deployment on your own infrastructure.

Frequently asked questions

Before you connect it.

What is Cortex, exactly?

A governed memory layer for your team and its AI agents. It stores decisions, lessons, and context as linked memories, and serves them back over MCP and a web UI — searchable, organized by project, and shared across the whole org.

How is this different from a vector database or my own RAG?

A vector DB gives you similarity search over chunks. Cortex gives you a curated team memory: structured entries with authorship, confidence, edit history, and links between related facts — plus hybrid full-text + semantic search, draft/approval workflow, and MCP tools your agents already know how to use. You could build it; this is it built.

Who can see what?

Memories are scoped to projects inside your org, and project members only see their projects. On projects with approval turned on, a member’s saves stay private drafts until an owner approves the merge request — so the shared graph only holds reviewed knowledge.

Which tools does it work with?

Anything that speaks MCP: Claude Code, Cursor, Claude Desktop, custom agents. MCP tools cover saving, searching, context assembly, graph traversal, merge review, and searching your connected Gmail/GitHub/Notion/Slack. There’s also a built-in chat, a full REST API, and a web UI.

Where does my data live?

In an org-isolated Postgres, on infrastructure we run and back up. Your team’s knowledge stays scoped to your org — never mixed with anyone else’s. Need it fully isolated on your own cloud instead? That’s what the License plan is for.

Is Cortex open source?

Cortex is a hosted product. Single-tenant deployment — your own isolated infrastructure — is available on the License plan for teams that need it.

A better starting point. Every time.

Build on everything
you already know.

Start with Cortex