Integrations

Everything you already run,
writing to one memory.

55 frameworks, orchestrators, platforms and data sources. Each one is a documented path into the same store — not 55 separate memories.

55 integrations

Connectors

CortexDB ingests from the tools you already run.

Slack

Continuously ingest Slack messages into CortexDB as experiences.

GitHub

Ingest GitHub pull requests, issues, and commits into CortexDB.

GitLab

Ingest GitLab merge requests, issues, commits, pipelines, and releases into CortexDB.

Jira

Ingest Jira issues, comments, sprints, and status changes into CortexDB.

Linear

Ingest Linear issues, comments, projects, and cycles into CortexDB.

Confluence

Ingest Confluence pages, blog posts, and updates into CortexDB.

Notion

Ingest Notion pages, database entries, and comments into CortexDB.

Google Workspace

Unified connector for Gmail, Google Drive, and Google Calendar.

Microsoft Teams

Ingest Microsoft Teams channel messages, threaded replies, and 1:1/group chats into CortexDB.

Discord

Ingest Discord messages, threads, and forum posts into CortexDB.

Salesforce

Ingest Salesforce Cases, Opportunities, Accounts, Tasks, Chatter, and Notes into CortexDB.

HubSpot

Ingest HubSpot Contacts, Companies, Deals, Tickets, and Engagements into CortexDB.

Zendesk

Ingest Zendesk tickets, comments, and Help Center articles into CortexDB.

Intercom

Ingest Intercom conversations, replies, articles, and contacts into CortexDB.

ServiceNow

Ingest ServiceNow incidents, change requests, problems, knowledge articles, and tasks into CortexDB.

Freshdesk

Ingest Freshdesk tickets, replies, private notes, and attachments into CortexDB.

PagerDuty

Ingest PagerDuty incidents, alerts, and notes into CortexDB.

tl;dv

Ingest tl;dv meeting recordings and speaker-segmented transcripts into CortexDB.

Agent frameworks

Your agent framework calls CortexDB.

LangChain

Use CortexDB as a long-term memory provider for LangChain agents.

LangGraph

Add persistent memory to LangGraph agents and workflows.

LlamaIndex

Use CortexDB as a memory store for LlamaIndex agents and query engines.

CrewAI

Add long-term memory to CrewAI agents and crews.

AG2

Add persistent memory to AG2 agents (successor to AutoGen).

AutoGen

Add persistent memory to Microsoft AutoGen agents.

Agno

Add persistent memory to Agno agents.

DSPy

Use CortexDB as a retriever and persistent memory in DSPy programs.

Smolagents

Add long-term memory to HuggingFace Smolagents.

CAMEL-AI

Add long-term memory to CAMEL-AI agents.

PydanticAI

Add persistent memory to PydanticAI agents with the cortexdb v1 SDK.

Mastra

Give Mastra agents long-term memory with CortexDB tools.

OpenAI Agents SDK

Wire CortexDB long-term memory into the OpenAI Agents SDK.

Google ADK

Add persistent memory to Google Agent Development Kit agents.

Letta

Use CortexDB as durable long-term memory alongside Letta (formerly MemGPT) agents.

BeeAI

Add long-term memory to IBM BeeAI Framework agents.

NeMo Guardrails

Wire CortexDB recall and capture into NVIDIA NeMo Guardrails as registered actions.

Instructor

Store Instructor-extracted structured outputs in CortexDB as typed experiences.

ControlFlow

Add persistent memory to ControlFlow tasks and agents.

Eliza OS

Give Eliza OS agents durable cross-session memory.

Hermes

Use CortexDB as a long-term memory provider for NousResearch Hermes agents.

OpenClaw

Give OpenClaw — Claude-powered desktop agents — durable memory across machines and sessions.

Orchestration

Scheduled and event-driven memory pipelines.

Temporal

Capture and recall CortexDB experiences from Temporal workflows + activities.

n8n

Call /v1/experience and /v1/recall from n8n workflows via HTTP nodes.

Prefect

Wrap CortexDB ingest in Prefect tasks for scheduled and event-driven memory pipelines.

Airflow

Wrap CortexDB ingest in Airflow PythonOperator tasks.

Zapier

Push experiences into CortexDB from any of Zapier's 6,000+ apps using Webhooks by Zapier.

Make.com

Push experiences into CortexDB from Make.com (formerly Integromat) scenarios.

No-code platforms

Capture and recall from visual builders.

Vercel AI SDK

Add persistent memory to Vercel AI SDK chat apps.

Flowise

Use Custom HTTP nodes in Flowise to capture and recall via CortexDB.

Dify

Capture and recall via HTTP nodes inside Dify AI workflows.

Inference backends

Where /v1/answer and embeddings run.

Ollama

Use a locally-hosted Ollama model as the answer model and entity-extraction LLM for CortexDB.

Groq

Route /v1/answer through Groq's LPU-accelerated models for sub-second responses.

Together AI

Route /v1/answer + embeddings through Together AI's open-model platform.

Fireworks AI

Route /v1/answer through Fireworks AI's optimized open-model inference.

vLLM

Route /v1/answer through a self-hosted vLLM server.

DeepInfra

Route /v1/answer through DeepInfra's serverless open-model inference.

Every entry links to its documentation. Setup for Me copies a prompt you can paste straight into your coding agent — it reads the page and wires it up.

Full documentation ↗