Vasilije Markovic
CEO & Founder
Vasilije Markovic contributes to the Cognee blog, with articles in deep dives, cognee news, fundamentals, tech reports, tutorials, integrations, case studies. Explore their published work below.
Published topics
Deep DivesCognee NewsFundamentalsTech ReportsTutorialsIntegrationsCase Studies

Published articles (57)
What Are 500+ Companies Actually Building with AI Memory?
More than 500 companies build with cognee, in software, finance, legal, pharma, research, education, and more. We group what they’re building into five categories and describe the four needs that keep coming up across them.
Read article ↗Meet the new cognee: smarter memory, lower costs, and control for your team
cognee now builds memory with small models on your own CPU, about 30× faster per chunk and with no API bill, learns your business's language and taxonomy with auto-ontology, shares memory across teams within the rules you set, and connects to 12 native integrations in cognee Cloud.
Read article ↗What cognee's 91% LoCoMo Score Measures
cognee scored 90.7% and 91.3% on 1,762 audited LoCoMo questions, adversarial included, with existing components configured on the benchmark. We explain what the judge accepts, which questions we left out and why, and what the score doesn't show, with every prompt, exclusion and verdict published.
Read article ↗AI Agent Memory: The Definitive Guide
The complete guide to AI agent memory: long-term memory for LLM agents, memory architectures from vector stores to knowledge graphs, and how to build one.
Read article ↗cognee 1.0: The Open-Source Memory Platform for AI Agents
cognee 1.0 is the first open-source memory platform built around a memory-native API — remember, recall, improve, forget — with full data ownership and deployment flexibility from managed cloud to edge.
Read article ↗cognee on BEAM: SOTA Results Without a Benchmark-Specific Memory System
cognee beat SOTA on BEAM's 100k-token setting by 6.5% and matched SOTA at 10M tokens using only default open-source features — no custom benchmark-specific architecture.
Read article ↗Just Postgres: Drop the Graph Database. Keep the Graph.
cognee 1.0 runs the full agent memory layer — graph, vectors, sessions, and metadata — on a single Postgres instance, eliminating the need for separate graph database, vector store, and Redis deployments.
Read article ↗Technical Note: Understanding the Token Cost of Persistent AI Memory
Persistent memory trades an upfront ingestion cost for cheaper queries. We measure where the tokens go in cognee, model the trade-off, and find break-even at roughly 23–26 repeated queries — after which the gap keeps widening.
Read article ↗Behind the Viral Numbers: How We Got 7x Cheaper and 145% Better
Our LinkedIn and X videos put two numbers on screen — 7x cheaper than chat and 145% better than the best alternative. Here's exactly where each one came from, linked to our BEAM report.
Read article ↗cognee on-device: Bringing Agent Memory to the Edge
The cognee core rebuilt in Rust, bringing the full agent memory pipeline — graph construction, embeddings, and retrieval — to phones, robots, and offline environments without a server-side stack.
Read article ↗Inside cognee 1.0: Memory-Native APIs for Production Agents
cognee 1.0 ships four memory verbs — remember, recall, improve, forget — with a self-improving feedback loop, hybrid retrieval with evidence references, a TypeScript SDK, and migration tools for Mem0, Zep, and Letta.
Read article ↗How Cognee Builds AI Memory
Cognee is a memory engine for AI agents that builds a knowledge graph from data and makes it searchable. It's a simple, yet powerful way to build AI agents that can remember and use information over time.
Read article ↗