Open source memory for agents

Open Source Memory
Platform for Agents

Capture context, turn it into graph memory, and let every agent recall it across sessions. Start local with open source, then scale on Cognee Cloud.

Start building View GitHub

Works withClaude Code Codex Skill MCP OpenClaw

5M+SDK runs/month#1GitHub Repository 17.1kGitHub Stars

Loved by engineers from

Try it for free

How it works

Capture, model, and recall. One memory layer for your agents.

01Capture

Connect the context your agents miss

Use one source or all: files, warehouses, vector stores, APIs, and chat logs. Cognee handles parsing, chunking, embedding, and provenance.

SnowflakePostgres.pdfTicketsRESTSlack

02Model

Turn raw data into graph memory

Cognee extracts entities, relationships, and domain rules so agents search by meaning, not just nearest chunks. Permissions and recall tuning stay with the memory layer.

EntitiesRelationsOntologiesPermissionsFeedback

$ cognee.remember(documents)

03Recall

Serve memory to every agent

Claude Code, LangGraph, OpenClaw, MCP-compatible clients, and custom runtimes can read and write the same durable memory across sessions.

Claude CodeLangGraphOpenClawMCPCustom

In production

From an AI chatbot to agentic research memory at Bayer.

Get Case-Study for free

What cognee does

Everything agents need after the prompt window ends.

Capture context with provenance

Turn documents, tickets, transcripts, product data, and research papers into cited memory your agents can inspect and reuse.

Read the case studies

Connect facts into working memory

Entities, relationships, ontologies, and feedback become a graph that gets sharper as people and agents use it.

Read the Knowunity story

Use one memory layer across your stack

Run locally, connect through MCP, or plug into Claude Code and LangGraph. Your sources stay where they are; Cognee gives agents a shared memory surface.

Browse integrations

What teams build

Build in minutes. Grow into a production memory platform.

015 minutes · Local

Start with local memory for coding agents

Install Cognee, connect your agent, and give it durable project context without standing up new infrastructure.

Best forSolo devs - agent hackers

Run quickstart →$ pip install cognee

021 day · Connect

Connect the data your agents should know

Use adapters and `cognee.remember()` to turn warehouses, docs, chats, and APIs into one recallable memory layer.

Best forData + platform teams

See connectors →docs.cognee.ai/integrations

031 week · Production

Ship agents that understand your domain

Put Cognee behind customer-facing agents so they can retrieve cited facts, follow domain rules, and improve from real usage.

Best forProduct engineers - vertical agents

Read the Knowunity case →

Use Cognee with

Any agent. One memory API.

First-party integrations for Claude Code, Cursor, LangGraph, OpenClaw, and more, plus an MCP server so compatible agents can read and write Cognee memory without custom glue.

CustomiseCustom ontologies CustomiseCustom data model GovernPermissions control

Skill

+ build your own

Pricing

Build locally for free. Scale when your agents do.

Free

For developers exploring Cognee

Free

Build and run memory workflows with tasks and pipelines
Auto-generate knowledge structures from your data
Integrated evaluations
More than 28 data sources supported
Community support

View on GitHub

Developer

For individual developers working with Cognee

$35/per month

1,000 documents or 1 GB of data included

Everything in Free, plus...

1 user
Fully hosted on AWS, GCP, and Azure
Comprehensive API endpoints
Automated scaling and parallel processing
Automatic updates
10,000 API calls included

Top-up packs+ 1,000 docs (~1 GB) — $35+ 3,000 docs (~3 GB) — $100+ 15,000 docs (~15 GB) — $750

Popular

Cloud (Team)

For small teams working with Cognee

$200/per month

2,500 documents or 2 GB of data included

Everything in Developer, plus...

10 users
Multi-tenant architecture
Ability to group memories per user and domain
Dedicated Slack channel
10,000 API calls included

Top-up packs+ 1,000 docs (~1 GB) — $35+ 3,000 docs (~3 GB) — $100+ 15,000 docs (~15 GB) — $750

On-Prem (Enterprise)

For companies that need dedicated infrastructure, full data control, and hands-on support

Custom

Everything in Cloud, plus...

On-prem or private cloud deployment
Security, data isolation, and optimal latency
Dedicated architecture review
Premium Support Plan / SLA
Access to AI FDE Engineers
Roadmap prioritization

From the field

“We tried understanding the proximity and relationships of our users before, but SQLs got out of hand and embeddings were too sparse. With cognee, we managed to get a POC done in 2 days on 40,000 students from Bremen.”