Cognee

Cognee is an open-source AI memory and knowledge graph platform that enables developers to build persistent, structured memory for AI agents and LLM applications. The platform provides a REST API and Python/TypeScript SDKs for ingesting documents and data from 28+ sources, processing them through a six-stage ECL (Extract, Cognify, Load) pipeline, and storing the resulting entities and relationships in a hybrid graph-vector-relational store. Developers can query the knowledge graph using 13+ search modes including semantic graph completion, RAG completion, and temporal search. Cognee is available as a managed cloud service on AWS, GCP, and Azure, or as a self-hosted deployment via Docker, Modal, Railway, Fly.io, and Render.

Cognee publishes 7 APIs on the APIs.io network, including agents API, cognify API, data API, and 4 more. Tagged areas include AI, Memory, Knowledge Graph, RAG, and Agents.

The Cognee catalog on APIs.io includes 1 JSON-LD context and 1 Spectral governance ruleset.

Cognee’s developer surface includes authentication, documentation, engineering blog, pricing, and 15 more developer resources.

🌐 Visit website 📡 Source on GitHub

46.8/100 developing ▬ flat Agent 41/100 agent ready Full breakdown ↓
scored 2026-07-28 · rubric v0.6

AccessFreemiumSelf serve⚡ Free to try

7 APIs

AIMemoryKnowledge GraphRAGAgentsGraph DatabaseVector SearchLLMOpen Source

Kin Score

Kin Score How this is scored →
scored 2026-07-28 · rubric v0.6

Composite quality — 46.8/100 · developing

Contract Quality 16.1 / 25

Developer Ergonomics 4.3 / 20

Commercial Clarity 10.0 / 20

Operational Transparency 0.7 / 13

Governance 8.3 / 12

Discoverability 7.4 / 10

Agent readiness — 41/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/cognee: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 7

Individual APIs this provider publishes, each with its own machine-readable definition.

Rate Limits 1

Documented rate limits and quota policies.

Cognee Rate Limits

0 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

JSON Schema 2

Standalone JSON Schema definitions for this provider's data models.

Cognee Dataset

5 properties

JSON SCHEMA

Cognee Search Payload

12 properties

JSON SCHEMA

Examples 1

Example request and response payloads for these APIs.

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

Design & Contract 2

Pagination, idempotency, versioning, errors, and events

Vocabulary

Vocabulary

JSONLDContext

JSONLDContext

Build 2

SDKs, sample code, and the tooling you integrate with

GitHubOrg

GitHubOrg

GitHubRepository

GitHubRepository

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 2

Status, limits, changes, and where to get help

Discord

Discord

RateLimits

RateLimits

Commercial 4

Pricing, plans, and the legal terms of use

Pricing

CostCalculator

Plans

FinOps

Company 4

The organization behind the API

Website

Website

LinkedIn

Blog

Blog

Blog

Blog

Other 1

Properties that don't map to a standard resource type

Source (apis.yml)

aid: cognee
name: Cognee
description: 'Cognee is an open-source AI memory and knowledge graph platform that enables developers to build persistent,
  structured memory for AI agents and LLM applications. The platform provides a REST API and Python/TypeScript SDKs for ingesting
  documents and data from 28+ sources, processing them through a six-stage ECL (Extract, Cognify, Load) pipeline, and storing
  the resulting entities and relationships in a hybrid graph-vector-relational store. Developers can query the knowledge graph
  using 13+ search modes including semantic graph completion, RAG completion, and temporal search. Cognee is available as
  a managed cloud service on AWS, GCP, and Azure, or as a self-hosted deployment via Docker, Modal, Railway, Fly.io, and Render.

  '
type: Index
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Freemium · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/cognee.png
url: https://raw.githubusercontent.com/api-evangelist/cognee/refs/heads/main/apis.yml
created: '2026-06-12'
modified: '2026-06-12'
specificationVersion: '0.19'
tags:
- AI
- Memory
- Knowledge Graph
- RAG
- Agents
- Graph Database
- Vector Search
- LLM
- Open Source
apis:
- aid: cognee:cognee-agents-api
  name: Cognee agents API
  description: AI agent identity management
  humanURL: https://docs.cognee.ai/api-reference/introduction
  baseURL: https://api.cognee.ai
  tags:
  - agents
  properties:
  - type: OpenAPI
    url: openapi/cognee-agents-api-openapi.yml
  - type: Documentation
    url: https://docs.cognee.ai/api-reference/introduction
  - type: SwaggerUI
    url: https://api.cognee.ai/docs
- aid: cognee:cognee-cognify-api
  name: Cognee cognify API
  description: Knowledge graph construction pipeline
  humanURL: https://docs.cognee.ai/api-reference/introduction
  baseURL: https://api.cognee.ai
  tags:
  - cognify
  properties:
  - type: OpenAPI
    url: openapi/cognee-cognify-api-openapi.yml
  - type: Documentation
    url: https://docs.cognee.ai/api-reference/introduction
  - type: SwaggerUI
    url: https://api.cognee.ai/docs
- aid: cognee:cognee-data-api
  name: Cognee data API
  description: Data ingestion and deletion operations
  humanURL: https://docs.cognee.ai/api-reference/introduction
  baseURL: https://api.cognee.ai
  tags:
  - data
  properties:
  - type: OpenAPI
    url: openapi/cognee-data-api-openapi.yml
  - type: Documentation
    url: https://docs.cognee.ai/api-reference/introduction
  - type: SwaggerUI
    url: https://api.cognee.ai/docs
- aid: cognee:cognee-datasets-api
  name: Cognee datasets API
  description: Dataset management and introspection
  humanURL: https://docs.cognee.ai/api-reference/introduction
  baseURL: https://api.cognee.ai
  tags:
  - datasets
  properties:
  - type: OpenAPI
    url: openapi/cognee-datasets-api-openapi.yml
  - type: Documentation
    url: https://docs.cognee.ai/api-reference/introduction
  - type: SwaggerUI
    url: https://api.cognee.ai/docs
- aid: cognee:cognee-health-api
  name: Cognee health API
  description: Service health probes
  humanURL: https://docs.cognee.ai/api-reference/introduction
  baseURL: https://api.cognee.ai
  tags:
  - health
  properties:
  - type: OpenAPI
    url: openapi/cognee-health-api-openapi.yml
  - type: Documentation
    url: https://docs.cognee.ai/api-reference/introduction
  - type: SwaggerUI
    url: https://api.cognee.ai/docs
- aid: cognee:cognee-search-api
  name: Cognee search API
  description: Semantic and graph search queries
  humanURL: https://docs.cognee.ai/api-reference/introduction
  baseURL: https://api.cognee.ai
  tags:
  - search
  properties:
  - type: OpenAPI
    url: openapi/cognee-search-api-openapi.yml
  - type: Documentation
    url: https://docs.cognee.ai/api-reference/introduction
  - type: SwaggerUI
    url: https://api.cognee.ai/docs
- aid: cognee:cognee-settings-api
  name: Cognee settings API
  description: System configuration (LLM and vector DB)
  humanURL: https://docs.cognee.ai/api-reference/introduction
  baseURL: https://api.cognee.ai
  tags:
  - settings
  properties:
  - type: OpenAPI
    url: openapi/cognee-settings-api-openapi.yml
  - type: Documentation
    url: https://docs.cognee.ai/api-reference/introduction
  - type: SwaggerUI
    url: https://api.cognee.ai/docs
common:
- type: AgenticAccess
  url: agentic-access/cognee-agentic-access.yml
- type: DomainSecurity
  url: security/cognee-domain-security.yml
- type: Authentication
  url: authentication/cognee-authentication.yml
- type: Website
  url: https://www.cognee.ai/
- type: Documentation
  url: https://docs.cognee.ai/
- type: GitHubOrg
  url: https://github.com/topoteretes
- type: GitHubRepository
  url: https://github.com/topoteretes/cognee
- type: LinkedIn
  url: https://www.linkedin.com/company/cognee-ai
- type: Blog
  url: https://www.cognee.ai/blog
- type: Pricing
  url: https://www.cognee.ai/pricing
- type: CostCalculator
  url: https://www.cognee.ai/cost-calculator
- type: X
  url: https://x.com/cognee_
- type: Discord
  url: https://discord.gg/m63hxKsp4p
- type: Plans
  url: plans/cognee-plans-pricing.yml
- type: RateLimits
  url: rate-limits/cognee-rate-limits.yml
- type: FinOps
  url: finops/cognee-finops.yml
- type: Vocabulary
  url: vocabulary/cognee-vocabulary.yml
- type: JSONLDContext
  url: json-ld/cognee-context.jsonld
- type: Blog
  url: blogs/blogs.json
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com