The Cognee Blog
Stay in the loop
Cognee product & events updates, insights into our AI memory research and practical guides — in your inbox every two weeks.
Latest
Latest
Cut Cognee's Vector Memory by 8x with Qdrant's TurboQuant
Use Qdrant TurboQuant in cognee with one env var to shrink stored vectors by about 8x without retraining, codebooks, or per-dataset tuning.
Long Term Memory AI: Why Your Agent Keeps Forgetting
Long term memory AI is more than chat history or larger context windows. Learn what agents should keep, retrieve, update, and forget.
Separate memories for organization, agent and user: Support AI Agent Use-Case
Most support teams don't have a support problem — they have a context problem. Here's how we built a support agent on top of cognee using user, agent, and organization memory.
Memory as a Decorator
Adding memory to agentic workflows used to mean restructuring your stack. One decorator changes that. We ran 198 simulated sales conversations — and the results make a strong case for structured memory.
Cognee's CLI Replaces MCP OAuth in 100 Lines
MCP has real auth built in. CLI doesn't — or so the claim goes. The Claude Code plugin that wraps cognee-cli runs a full register-login-token handshake before the first command fires.
Agents Don't Need Another Protocol. They Need a Good CLI.
Your agent forgets everything between sessions. The fix isn't a bigger context window — it's persistent memory via a CLI. Four commands give your agent cross-session, graph-structured memory.
Claude Code's Leak Reveals Anthropic's Obsession with Cognee
Anthropic accidentally exposed 500,000 lines of internal source code. Buried inside: engineers studying Cognee's memory architecture and wondering if they should just adopt it.
Expanding Custom Graph Models for Reliable Agent Memory & Retrieval
Learn how Custom Graph Models in cognee create a stable, domain-aware memory layer for agents — and how the Cascade feature progressively discovers missing schema from real data.
Memory as a Harness: Turning Execution Into Learning
Memory as a Harness: Turning Execution Into Learning
Cut Cognee's Vector Memory by 8x with Qdrant's TurboQuant
Use Qdrant TurboQuant in cognee with one env var to shrink stored vectors by about 8x without retraining, codebooks, or per-dataset tuning.
Long Term Memory AI: Why Your Agent Keeps Forgetting
Long term memory AI is more than chat history or larger context windows. Learn what agents should keep, retrieve, update, and forget.
Separate memories for organization, agent and user: Support AI Agent Use-Case
Most support teams don't have a support problem — they have a context problem. Here's how we built a support agent on top of cognee using user, agent, and organization memory.
Memory as a Decorator
Adding memory to agentic workflows used to mean restructuring your stack. One decorator changes that. We ran 198 simulated sales conversations — and the results make a strong case for structured memory.
Cognee's CLI Replaces MCP OAuth in 100 Lines
MCP has real auth built in. CLI doesn't — or so the claim goes. The Claude Code plugin that wraps cognee-cli runs a full register-login-token handshake before the first command fires.
Agents Don't Need Another Protocol. They Need a Good CLI.
Your agent forgets everything between sessions. The fix isn't a bigger context window — it's persistent memory via a CLI. Four commands give your agent cross-session, graph-structured memory.
Claude Code's Leak Reveals Anthropic's Obsession with Cognee
Anthropic accidentally exposed 500,000 lines of internal source code. Buried inside: engineers studying Cognee's memory architecture and wondering if they should just adopt it.
Expanding Custom Graph Models for Reliable Agent Memory & Retrieval
Learn how Custom Graph Models in cognee create a stable, domain-aware memory layer for agents — and how the Cascade feature progressively discovers missing schema from real data.
Memory as a Harness: Turning Execution Into Learning
Memory as a Harness: Turning Execution Into Learning
cognee 1.0: The Open-Source Memory Platform for AI Agents
Claude Code's Leak Reveals Anthropic's Obsession with Cognee
Cognee Raises $7.5M Seed to Build Memory for AI Agents
AI Agent Memory: The Definitive Guide
What Is RAG? Retrieval-Augmented Generation Explained
What Is GraphRAG? Retrieval-Augmented Generation with Knowledge Graphs Explained
Elevating AI-Driven Credit Card Insights: A Tier-1 US Bank's Semantic AI Memory Discovery
Turning PDFs into Evidence-Based Answers: How We Built a Trustworthy Evidence Graph for UWYO
Smart Networks, Smarter Students: How cognee Connected 40,000 German Learners
Coding Agents Don't Need Bigger Context Windows — They Need Better Memory
What Is Agentic RAG? How It Works and When to Use It
cognee on BEAM: SOTA Results Without a Benchmark-Specific Memory System
Why AI Agents Forget and How to Fix Their Memory
Give Claude Code Persistent Memory With cognee
Structure Your Skills with Cognee
Cut Cognee's Vector Memory by 8x with Qdrant's TurboQuant
ScrapeGraphAI + Cognee: Turn Live Web Data Into a Knowledge Graph
