Skip to content

Agent memory

3 sources filed·EN 1·RU 2

Week 45 · 2-8 Nov

2 sources filed · RU 2

B
Five memory layers of an AI assistant: what actually runs in production and what stayed in the library (Пять слоёв памяти ИИ-ассистента: что реально работает в проде, а что осталось в библиотеке)
Messengers are thin adapters into one core; the same person on Telegram and MAX is still two user IDs.
about 1,200people using the assistant across Telegram, MAX and VK
Habr-Author·Practitioner post·8 Nov 2026·RU·habr.com
B
Knowledge base at full stretch: how AI agents working with QA fill a shared testing memory (База знаний на максималках: как ИИ-агенты с помощью QA сами наполняют общую память тестирования)
MKP has a built-in copy of the corporate wiki (read-only, refreshed daily) and any number of team Markdown bases; access through a web UI, REST API and an MCP server, all under the same per-person permissions.
VkusVill-TechVill·Practitioner post·6 Nov 2026·RU·habr.com

Week 43 · 19-25 Oct

1 source filed · EN 1

B
Cache Engineering for Agents
In the authors' cost breakdown, KV cache reads account for 82.4% of total API cost for agents.
82.4%share of total API cost taken by KV cache reads in the authors' agent cost breakdown
arXiv (Tsinghua, CUHK)·Paper·20 Oct 2026·arxiv.org