Integrations

CortexDB ships 31 integration recipes and 16 managed data connectors across the AI ecosystem. Every integration recipe is a thin adapter on top of the Python and TypeScript SDKs — copy, paste, swap in your scope, ship. Data connectors are managed sync workers that ingest from third-party systems into CortexDB on a schedule.

The 6 inference backend pages are deployment guides for self-hosted and enterprise CortexDB instances. They configure the model router used by /v1/answer and the Understanding synthesizer; they are listed separately and excluded from the integration count.

---

Agent frameworks

22 frameworks. Every page is a self-contained recipe: a memory adapter, a retriever class, or a tool wrapper that talks to CortexDB via V1Client. Pick one or compose several — the SDK doesn't care.

Orchestration

6 workflow + scheduling platforms.

No-code platforms

3 visual-builder / hosted-tool platforms.

Inference backends

6 inference backends. These pages are server-side deployment guides — they configure which model CortexDB's internal /v1/answer route and Understanding synthesizer call. They are not user-facing on the SaaS / free tier (where the synthesizer model is fixed to Claude Opus 4.6). Use these if you self-host or run an enterprise deployment.

Data connectors

16 third-party systems. Connectors run as managed sync workers on CortexDB's infrastructure — point them at your Slack workspace / GitHub org / Jira project once and they continuously ingest into your scope as conversation / document experiences. Available on Starter and up; the worker is provisioned via your account dashboard.

---

Not in this list?

The Python, TypeScript, and REST interfaces work everywhere fetch does. If you have a framework, orchestrator, or pipeline that isn't listed, drop into Discord — and if it's a connector you'd like CortexDB to operate as a managed sync worker, contact sales.