Skip to main content
Cognee works seamlessly with AI Agent frameworks and popular tools in the AI ecosystem. These integrations help you observe, evaluate, use your AI Memory.
All integrations are designed to be lightweight and easy to configure, requiring minimal setup to get started.

​
Observability & Monitoring

Track performance, debug issues, and monitor your knowledge graph operations in production.

OpenTelemetry

Vendor-neutral observabilityExport OTEL traces, metrics, and logs for Cognee’s memory operations to any OTLP-compatible backend (Grafana, Jaeger, Dash0, Dynatrace, and more).

Keywords AI

LLM application tracingSpan-level tracing across tasks and workflows with minimal code using Cognee’s observe abstraction.

​
Evaluation & Testing

Measure and improve the quality of your knowledge graph outputs with comprehensive evaluation frameworks.

Built-in Evaluation Framework

Benchmark retrieval qualityRun standard multi-hop QA benchmarks, compare search strategies, and inspect results in an interactive dashboard — no third-party service required.

DeepEval

Comprehensive RAG evaluationRun QA & RAG metrics including Contextual Relevancy, Precision/Recall, and Coverage using LLM-as-a-judge workflows.

​
Cloud LLM Providers

Connect to enterprise-grade LLM services through Cognee’s flexible integration layer.

AWS Bedrock

Enterprise LLM accessUse AWS Bedrock models including Claude, Nova/Titan, GPT-OSS, and others through Cognee’s native Bedrock provider. LiteLLM proxy setup is optional.

​
Data Ingestion

Scrape, extract, and ingest web content directly into Cognee’s knowledge graph.

GitHub

Org repositories to code graphInstall a GitHub App into an org and index every covered repository into one github_<org> dataset, kept fresh by webhooks and searchable with SearchType.CODE.

Linear

Workspace issues + an agent that answersInstall Cognee as a Linear agent: @mention it or delegate an issue and it answers from memory, while the workspace’s issues sync into one linear_<workspace> dataset via webhooks.

Google Drive

Drive files to knowledge graphConnect a personal or Workspace Google account over OAuth, pick the folders and shared drives to cover, and sync them into one google_drive_<account> dataset on demand.

ScrapeGraphAI

Web scraping to knowledge graphScrape URLs with natural language prompts and ingest the results directly into cognee.

Gmail

Inbox to knowledge graphConnect a mailbox over read-only OAuth, pick the labels to cover, and sync matching messages into one gmail_<account> dataset with incremental updates and forget-on-delete. Bundled with the SDK via cognee[gmail].

Google Calendar

Calendar events to knowledge graphConnect a calendar account over read-only OAuth, list the calendars to cover explicitly, and sync their events into one google_calendar_<account> dataset with incremental updates and forget-on-delete. Bundled with the SDK via cognee[google-calendar].

​
Agent Frameworks

Build stateful AI agents with persistent semantic memory that endures across sessions.

LangGraph

add_tool / search_tool for create_agent—no manual state management.

Haystack

CogneeWriter and CogneeRetriever components for pipelines and agents.

Google ADK

Native LongRunningFunctionTool for async-first Gemini agents.

CrewAI

Shared crew memory via add_tool and search_tool.

Strands

cognee_tools() exposing remember and recall (cognee v1.0).

Hermes Agent

Drop-in memory provider plugin—no code required.

Band

Wrap any Band adapter in CogneeMemoryAdapter — rooms become memory.

Vellum

Persistent memory for Vellum agents with the Cognee plugin.

OpenAI Agent SDK

Native function_tool pattern with agent handoffs support.

OpenClaw

Multi-scope auto-index and recall for your personal AI agent.

​
Coding Agents

Give your terminal coding agents persistent memory with the Cognee plugin—no code, no pip install. It hooks into the agent’s lifecycle to capture and recall memory automatically.

Claude Code

claude plugin install cognee-memory@cognee — memory across every session.

Codex

codex plugin add cognee@cognee — memory across every session.

Pi

pi install npm:@kerryhatcher/pi-cognee — community extension with SDK and MCP modes.

Docker Sandboxes

sbx run claude --kit ./cognee-memory — a mixin kit that stacks memory onto any sandboxed agent.

​
No-Code & Low-Code

Build memory pipelines visually—no Python required.

n8n

No-code memory workflows with all n8n integrations.

Dify

Cognee memory tools for Dify apps and workflows (Cloud or self-hosted).

​
Team Chat

Query and grow your memory without leaving a conversation.

Slack

Ask with /cognee-ask, save with /cognee-remember or the Remember this shortcut, import channel history with /cognee-import, and link your account — or run the standalone channel-memory bot that answers @cognee with cited source messages.

​
Agent IDEs & Development Tools

Integrate Cognee directly into your development workflow with MCP-compatible tools and AI assistants.

MCP Integrations

Cursor

AI-powered code editor integration

Continue

VS Code AI assistant plugin

Claude Code via MCP

Anthropic’s Claude integration

Cline

VS Code AI coding extension

Codex via MCP

OpenAI coding agent with MCP support
Cognee’s Model Context Protocol (MCP) adapter enables seamless integration with AI assistants, providing direct access to your knowledge graphs for in-context assistance.

​
Contributing Integrations

Don’t see your favorite tool? Cognee is open and extensible—help us grow the ecosystem!
All community database integrations are maintained in the cognee-community repository, keeping the core Cognee package lean while providing extensibility.