CortexDB Docs
Self-Hosting

Self-Hosting

Running CortexDB yourself is the recommended path — the same server the cloud runs, on your own infrastructure. Start here.

Self-hosting is the recommended way to run CortexDB. The server you run yourself is the same one the cloud runs — the identical cortexdb/cortexdb image, the identical v1 API. Hosting it yourself means:

  • Your data stays in your infrastructure — memory, embeddings, and blobs never leave your network.
  • No per-token or per-seat cost — you pay only for the compute you run and the model APIs you choose to wire in (or none, if you run models locally).
  • Full control — pick your embedding and answer models, your storage backend, your auth and compliance posture.
  • One binary — a single Rust process; single-node handles ~10M events on commodity hardware.

Start here

Five minutes to a running server

The Self-Hosting Quickstart takes you from nothing to a stored-and- recalled memory with one docker run. It's the recommended starting point for everyone.

The self-hosting path

  1. Quickstartdocker run, point at localhost:3141, first write + recall.
  2. Defaults & prerequisites — what runs out of the box (content-only: capture, BM25 + vector recall, blob extraction) vs what's opt-in (Facts/Beliefs/ Understanding, the knowledge graph, cross-encoder rerank, and /v1/answer), and how to turn each on.
  3. Configuration — how config resolves (defaults → cortex.toml → env → CLI), and the ~100 CORTEX_* knobs.
  4. Profiles & Presets — copy-paste configs for common shapes, including a full Enterprise profile.

Wire in the pieces you need

Operate it

Self-hosted vs Cloud

Both run the same server and the same v1 API — you move between them by changing one base URL, so this is a deployment choice, not a product choice.

Self-hosted (recommended)Managed cloud
Where data livesYour infrastructure — memory, embeddings, blobs never leave your networkCortexDB's infrastructure
Model API keysYours; you choose the providers (or run models locally, no external calls)Managed for you
Cost modelYour compute + whatever model APIs you wire in (or $0 with local models)Tiered subscription
Who runs itYou (one Docker container; single-node handles ~10M events)CortexDB
Upgrades / opsYou pull new images and run backupsHandled for you
AuthYou set CORTEX_API_KEY (or your OIDC/IdP)Provisioned tokens
Best whenData residency, cost control, air-gapped or regulated environments, full controlYou'd rather not operate a server and want zero ops

Not sure? Start self-hosted with the Quickstart — it's five minutes and nothing leaves your machine — and switch the base URL to the cloud later if operating the server isn't worth it for you.

Connectors, self-hosted

Every one of the 18 connectors runs against your own instance with the cortexdb-sync CLI — no dashboard required. Point it at http://localhost:3141 and it ingests Slack, GitHub, Jira, and the rest into your scopes.

Moving between self-hosted and cloud

The API, SDKs, and connectors are identical — point them at http://localhost:3141 (self-hosted) or https://api-v1.cortexdb.ai (managed cloud) by changing one base URL.

On this page