Tool overview
Cognee is listed under AI Infrastructure & MLOps AI tools.
What is Cognee?
Cognee converts documents and application data into persistent, queryable agent memory. Teams can use the open-source engine locally or Cognee Cloud with APIs, MCP integrations, workspaces, and usage-based token processing.
Best for
Teams building agents that need persistent organizational memory
Who is it for?
Decision note
Rebuilt from the original export under the complete V412/V411 factual-source-verification workflow. Preview only. Apply remains blocked until Failures = 0, Warnings = 0, Unmapped = 0, Missing = 0; explicit clears are reviewed; image import is disabled or V380 accepts the asset; a representative WordPress edit screen is compared with the export and proposed row; and a post-Apply zero-change Preview succeeds.
Key features
Persistent structured agent memory
Open-source local and self-hosted engine
Cloud API with unlimited calls
Claude Code, Codex, and MCP integrations
Use cases
Give coding agents durable memory
Build GraphRAG and semantic search
Create internal copilots with context
Serve memory to customer-facing agents
Pros
- Free forever cloud tier
- Apache-2.0 open-source engine
- Local, self-hosted, and BYO-cloud paths
Limitations
Entity resolution and retrieval require testing on real data.
Teams remain responsible for permissions, deletion, and source governance.
Pricing details
Billing options
Pricing note
Free includes one workspace, 1M tokens, unlimited users, and unlimited API calls. Standard is $2.50 per 1M processed tokens plus $5 per additional workspace. Enterprise supports BYO cloud and SLAs.
Supported languages
- English
Integrations
Claude Code
Codex
MCP
Slack
Notion
Google Drive
Please log in to join the discussion.