Xavier Francuski
AI Researcher
Xavier Francuski contributes to the Cognee blog, with articles in deep dives, integrations, fundamentals, tutorials, cognee news. Explore their published work below.
Published topics
Deep DivesIntegrationsFundamentalsTutorialsCognee News

Published articles (39)
Local AI Memory: Keeping Agent Memory Off the Cloud
What has to run on your own hardware for agent memory to count as local: four levels of locality, where cloud calls hide in extraction, embeddings, and reranking, how much hardware each stage needs, and a disconnect test for fully offline memory.
Read article ↗AI Memory Tools vs. Databases: 5 Memory Layers Compared (2026)
Compare LangMem, Mem0, cognee, Zep, and Letta by how much of the stack each AI memory tool takes over — from memory primitives over your own store to managed temporal graphs and memory built into the agent runtime.
Read article ↗How to Evaluate AI Memory in 2026: 5 Tools Compared
Compare how Mem0, Zep, cognee, Letta, and LangMem let you evaluate AI memory — open benchmark harnesses, retrieval-versus-answer scoring, published results, and what you still have to test yourself.
Read article ↗5 AI Memory Tools for Small Models and Local Agents (2026)
Compare Graphiti, Mem0, cognee, Basic Memory, and Letta for small models and local agents — which AI memory tools need generative inference, what runs offline, and how much work lands on the agent’s own model.
Read article ↗5 Open-Source LLM & Agent Evaluation Tools in 2026
Compare DeepEval, Ragas, Promptfoo, Inspect AI, and Opik across output, retrieval, trajectory, and task-outcome evaluation layers — what each tool actually tests and how far it goes beyond scoring a single model response.
Read article ↗5 New Databases for AI Workloads in 2026
Compare HelixDB, turbopuffer, LanceDB, SurrealDB, and Turso across architecture, retrieval, and primary AI use — from graph-and-vector engines to object-storage-backed search and a database provisioned per agent.
Read article ↗Keenable × cognee: Giving Web Retrieval Persistent Memory
Keenable returns clean Markdown for any URL, and cognee turns it into persistent, graph-backed memory an agent can recall later — how the fetch backend, config, and pipeline fit together.
Read article ↗5 Small Language Model Providers for Local and Specialized AI
Compare Fastino, distil labs, Liquid AI, Arcee AI, and Mistral AI across model focus, deployment, and use case — from structured extraction and distilled students to on-device inference, sparse MoE, and general-purpose compact generation.
Read article ↗Anthropic API Cost in 2026: Claude Pricing and Calculator
A breakdown of Anthropic API pricing for 2026: per-model Claude token rates, prompt caching and Batch API discounts, worked cost examples, and how much a memory layer can cut off the bill.
Read article ↗Grok Pricing in 2026: API Costs and Calculator
A breakdown of Grok API pricing for 2026: per-model token rates, what happens when a prompt crosses 200K tokens, caching and tool costs, and how much a memory layer can cut off the bill.
Read article ↗Top AI Podcasts for Engineers: 10 Shows Worth Your Time in 2026
A field guide to the AI podcasts worth an engineer's queue in 2026 — what each show actually covers, a recent episode to start with, and a clear reason to skip the ones that aren't for you.
Read article ↗Best Embedding Models in 2026: OpenAI vs Open Source by MTEB
Compare OpenAI, Gemini, Voyage, Cohere, Qwen3-Embedding, BGE-M3, and Microsoft Harrier OSS v1 across MTEB results, dimensions, context limits, modalities, deployment, and cost.
Read article ↗