Skip to main content

​
Cognee API Reference

Welcome to the Cognee API documentation. This comprehensive reference covers all endpoints for building, managing, and querying your memory using Cognee’s powerful platform.

​
Getting Started

Before using the API, you need to choose how to run Cognee. You have two main options:

Cogwit (Cloud)

Managed Cloud PlatformProduction-ready, fully managed service with automatic scaling and enterprise features.

Local Docker Setup

Self-Hosted DevelopmentRun Cognee locally using Docker for development, testing, and custom deployments.

​
Setup Options

  • Cogwit Cloud
  • Local Docker
Managed Service - Recommended for Production
  1. Sign up at platform.cognee.ai
  2. Create API Key in your dashboard
  3. Start using the API immediately
# Base URL for Cogwit
BASE_URL="https://api.cognee.ai"

# Authentication
curl -H "X-Api-Key: YOUR-API-KEY" \
     -H "Content-Type: application/json" \
     $BASE_URL/api/health
Cogwit provides enterprise-grade infrastructure with automatic scaling, managed databases, and 24/7 monitoring.

​
API Base URLs

Production (Cogwit)

https://api.cognee.ai
Authentication: X-Api-Key header Rate Limits: Based on your subscription plan Availability: 99.9% uptime SLA
http://localhost:8000
Authentication: Optional (can be disabled for local development) Rate Limits: None Availability: Depends on your local setup

​
Authentication

  • Cogwit Cloud
  • Local Docker
API Key AuthenticationAll requests require an API key in the header:
X-Api-Key: YOUR-API-KEY
Content-Type: application/json
Get your API key from the Cogwit dashboard.

​
Core API Endpoints

The Cognee API provides endpoints for the complete knowledge graph lifecycle:

Data Ingestion

POST /api/addAdd text, documents, or structured data to your knowledge base.

Knowledge Processing

POST /api/cognifyTransform raw data into structured knowledge graphs with entities and relationships.

Semantic Search

POST /api/searchQuery your knowledge graph using natural language or structured queries.

Data Management

DELETE /api/deleteRemove specific data items or entire datasets from your knowledge base.

​
API Features

Choose from different search modes based on your needs:
  • GRAPH_COMPLETION: LLM-powered responses with graph context
  • CHUNKS: Raw text segments matching your query
  • SUMMARIES: Pre-generated hierarchical summaries
  • INSIGHTS: Structured entity relationships
  • CODE: Code-specific search with syntax understanding
Support for various input formats locally and strings on cogwit:
  • Text: Raw text strings, documents, articles
  • Structured: JSON, CSV, XML data
  • Code: Source code files and repositories
  • URLs: Web pages and online content

​
Quick Example

Here’s a complete example using the API: 
import requests

# Configuration
BASE_URL = "http://localhost:8000"  # or https://api.cognee.ai for Cogwit
API_KEY = "your-api-key"  # only for Cogwit

headers = {
    "Content-Type": "application/json",
    "X-Api-Key": API_KEY  # only for Cogwit
}

# 1. Add data
add_response = requests.post(
    f"{BASE_URL}/api/add",
    json={"data": "AI is transforming how we work and live."},
    headers=headers
)

# 2. Process into knowledge graph
cognify_response = requests.post(
    f"{BASE_URL}/api/cognify",
    json={"datasets": ["main_dataset"]},
    headers=headers
)

# 3. Search the knowledge graph
search_response = requests.post(
    f"{BASE_URL}/api/search",
    json={
        "query": "What is AI?",
        "search_type": "GRAPH_COMPLETION"
    },
    headers=headers
)

print(search_response.json())

​
Interactive API Explorer

OpenAPI Specification

Try the API interactivelyAll endpoints below are automatically generated from our OpenAPI specification, providing interactive examples and real-time testing capabilities.

​
Error Handling

All API endpoints return standard HTTP status codes:
  • 200: Success
  • 400: Bad Request - Invalid parameters
  • 401: Unauthorized - Invalid or missing API key
  • 404: Not Found - Resource doesn’t exist
  • 429: Too Many Requests - Rate limit exceeded
  • 500: Internal Server Error - Server-side error
Always implement proper error handling in your applications to gracefully handle API failures and rate limits.

​
Next Steps

Explore Endpoints

API DocumentationBrowse all available endpoints with interactive examples below.

Community Support

Get HelpJoin our Discord community for support and discussions.
⌘I