Cognee
Category: AI Infrastructure
An open-source AI memory engine that builds dynamic, self-improving knowledge graphs and persistent memory layers for AI agents, combining graph and vector databases in a unified platform. Cognee was founded in 2024. The company is led by Vasilije Markovic. Based in Berlin, Germany. Team size: 11-50. Total funding raised: $9.09M. Latest round: Seed ($7.5M, Feb 2026). Key investors include Pebblebed, 42CAP, Vermilion Cliffs Ventures, Combination VC, Angel Invest, Angel investors from Google DeepMind, n8n, and Snowplow.
AMW Analysis
Cognee is an open-source AI infrastructure company that provides a unified platform combining graph and vector databases to create persistent memory layers and self-improving knowledge graphs for AI agents. Founded in 2024 and based in Berlin, the company has raised a total of $9.09M, with its latest $7.5M seed round in February 2026 led by Pebblebed, with participation from 42CAP, Vermilion Ventures, and angel investors from Google DeepMind, n8n, and Snowplow. Recent news flow centers on this funding, which the company is using to address a fundamental AI infrastructure gap: enabling autonomous agents to retain context across interactions rather than operating statelessly. Cognee reports over 70 production deployments, including Bayer, and 12,000+ GitHub stars. The platform transforms unstructured data into structured knowledge graphs, unifying relational, vector, and graph storage to help AI systems reason across information and reduce hallucinations. The funding round coincides with broader European AI infrastructure investment activity.
AMW analysis, generated from 4 tracked news signals.
- Founded
- 2024
- Headquarters
- Berlin, Germany
- Team size
- 11-50
- Total funding
- $9.09M
Value proposition
Simplifies AI memory infrastructure by providing a unified platform that combines graph and vector databases with automatic ontology generation, self-improving knowledge graphs, and millisecond response times—replacing custom knowledge graph and vector store implementations with production-ready memory in 6 lines of code.
Products and solutions
Cognee 1.0 Open-Source Memory Platform (memory-native API: remember/recall/improve/forget), Cloud Platform (Managed Service), Enterprise / BYOC On-Premise, Graph-on-Postgres option, TypeScript SDK, Rust Engine / cognee-RS for On-Device Memory, COGX portable memory export format, Model Context Protocol (MCP) Integration, Cognee UI (Local & Cloud Notebooks with Graph Explorer), Memify Post-Processing Pipeline, Auto-Optimization with User Feedback, 38+ Data Source Connectors
Unique value
Pioneered ECL (Extract, Cognify, Load) pipeline architecture combining graph databases for relationships with vector stores for semantic search. Features self-improving knowledge graphs that learn from user feedback, poly-store architecture supporting multiple databases (Neo4j, Memgraph, FalkorDB, Redis, Qdrant, etc.), and strong BEAM benchmark results (79% at 100k / 67% at 10M). Open-source with 30.4k+ GitHub stars and production deployment across 100+ companies.
Target customer
AI/ML developers, data engineers, and enterprises building AI agents, copilots, and applications requiring persistent memory, context awareness, and knowledge retrieval capabilities
Industries served
Artificial Intelligence & Machine Learning, Enterprise Software, Financial Services & Banking, Healthcare & Medical Research, Knowledge Management, Data Analytics & Business Intelligence, Regulated Industries, Software Development
Technology advantage
Production-ready hybrid graph-vector memory system with 0.93 human-like correctness score and millisecond response times. Plugin-based architecture supports multiple LLM providers and embedding engines without vendor lock-in. GDPR-compliant with encryption at rest and in transit, supports air-gapped enterprise deployment. Multi-tenant architecture with automatic ontology generation (commercial tier) and user database isolation. Automatic scaling and distributed graphs handle production workloads from gigabytes to terabytes.
How they differentiate
Hybrid graph-vector architecture with proprietary ECL (Extract, Cognify, Load) pipeline and memory-native API (remember/recall/improve/forget), combining self-improving knowledge graphs with automatic ontology generation. Production-ready platform serving 100+ companies; BEAM 79% (100k) / 67% (10M). Open-source (30.4k+ GitHub stars) with enterprise-grade features including GDPR compliance, multi-tenant architecture, and broad database/agent integrations.
Main competitors
Mem0, Graphiti (Zep), Letta, LightRAG
Key partnerships
Memgraph (Official Graph Database Partner), Neo4j (Graph Database Integration), Redis (Vector Store Partner), FalkorDB, Kuzu, LanceDB, Qdrant, Weaviate (Database Integrations), LangGraph, CrewAI, LangChain, LlamaIndex, Hermes Agent (Framework Integrations), Model Context Protocol (OpenAI MCP, Anthropic MCP), UC Berkeley RDI Xcelerator 2026 Agentic AI Cohort, AWS, GCP, Azure (Cloud Infrastructure), Pebblebed, 42CAP, Vermilion Cliffs Ventures, Combination VC, Angel Invest (Investors), Production Customers: Bayer, University of Wyoming, Knowunity, Dynamo, Luccid, DeepMetis, SlideSpeak, dltHub, Dilbloom
Notable customers
Bayer, University of Wyoming, Knowunity, Dynamo, Luccid, DeepMetis, SlideSpeak, dltHub, Dilbloom, Tier 1 US Bank
Major milestones
Founded in 2024 by Vasilije Markovic and Boris Arzentar in Berlin, Pre-seed round of €1.5M ($1.58M) raised in November 2024, Seed round of $7.5M led by Pebblebed in February 2026, Opened San Francisco office to expand North American operations, Released cognee 1.0 (Jun 26 2026) with memory-native API and multi-runtime deployment, Joined UC Berkeley RDI Xcelerator 2026 Agentic AI Cohort (Jul 13 2026), Reached 30,000+ GitHub stars (Aug 2026); 100+ companies in production
Growth metrics
100+ companies in production, 30.4k+ GitHub stars, 5M+ SDK runs/month, ~6M memories created/month, BEAM 79% (100k) / 67% (10M), ~24 employees (Jul 2026)
Market positioning
Mid-market enterprise AI infrastructure platform positioned between pure open-source solutions and fully managed SaaS, targeting AI/ML developers and enterprises building persistent memory systems for AI agents and copilots
Geographic focus
Europe (Germany HQ) and North America (San Francisco office), serving global enterprise customers including Bayer, University of Wyoming, Tier 1 US Bank, and 70+ companies across multiple continents
Patents and IP
No registered patents disclosed. Cognee is a registered trademark of Topoteretes UG. Competitive strategy relies on open-source community adoption (30.4k+ GitHub stars), proprietary enterprise features (auto-ontology generation, premium support), and first-mover advantage in AI memory infrastructure.
About Vasilije Markovic
Over a decade in big data engineering at Berlin-based unicorns including Team Lead at Taxfix (first Data Product Manager, built data tools, shaped data warehouse, delivered customer segmentation), Machine Learning Engineer at Zalando (deployed ML applications for production systems), and Big Data Systems Supervisor at Omio (supervised real-time systems handling large-scale data processing). Background in Economics and Clinical Psychology studies. Transitioned to AI infrastructure to solve fundamental memory persistence challenges in AI agents.
Latest news about Cognee
- Berlin-based Cognee secured €7.5 million to solve a fundamental AI infrastructure gap: persistent memory for autonomous agents. Founded in 2024, the open-source platform transforms unstructured data i
- Berlin-based Cognee raised $7.5M seed funding led by Pebblebed to build enterprise-grade persistent memory layers for AI agents, addressing a fundamental limitation in modern AI systems. With 70+ prod
- Berlin-based Cognee raised €7.5M to build structured memory layers for AI agents, addressing a critical gap: AI systems fail not from insufficient power but from inadequate memory capabilities. This s
- Cognee secured €7.5M to build persistent memory infrastructure for AI agents using knowledge graphs. With 70+ companies in production, this addresses a critical gap: AI systems fail not from insuffici
More AI Infrastructure companies
Official website: https://www.cognee.ai/