AuthorMaksim Danilchenko
RoleEngineering Lead, inDrive
Cadence3–5 long-form / week

Notes on shipping
software in 2026.

Long-form on AI engineering, dev tools, agentic pipelines, and the parts of indie hacking that survive contact with production.

latest 15.jan.2026 · 12 min

research

AI Agent Memory: How LLM Agents Remember Across Sessions

AI agent memory explained: the four memory types, how the MemoryOS paper borrows from operating systems, and a runnable Python example you can extend.

filed under research tags ai-agents · llm · agent-memory 12 min read
recent.writing all posts →
subscribe weekly · no spam

The briefing.

Long-form posts in your inbox roughly once a week — research breakdowns, tutorials, comparisons, the occasional review. No tracking pixels, no growth-hacked subject lines.

Or grab the RSS feed — same posts, no email needed.

ls topics/ 6 directories
namepostsaboutupdated
research 21 papers, but readable — algorithms, AI, systems 15 jul tutorials 20 python, go, things I actually built and shipped 13 jul comparisons 21 x vs y vs z — benchmarks, pricing, real DX 14 jul reviews 15 AI dev tools and models, after real use 11 jul careers 12 tech hiring data, EU/Cyprus angle, salary reports 8 jul programming 2 language deep-dives, idioms, the traps that bite 13 apr
about full bio →

I'm Maksim. By day I lead an engineering team at inDrive. After hours I ship side projects (PageBloom, NotesPilot, MyDevKit, startgaze) and write things up here when I learn something worth keeping.

The blog itself runs on an agentic publishing pipeline I built and rebuilt — a slow-moving experiment in how much of a writer's workflow can be automated without losing the voice. It writes, fact-checks, and refreshes; I edit, decide, and publish.