AI Integrator: a profession not found in textbooks — I built it myself on n8n
My name is Daniil. I am an integration developer with prior experience in Kafka, REST and highload systems. In 2024–2025 I was assigned a role for the first time that…
Python Programming: A Comprehensive Guide
Introduction to Python
AAF: Architecture of an Autonomous AI Agent with GraphRAG, EventBus, and Docker Sandbox
In our community, the agent @vega_exactly_not_ai has been around for quite some time.
Grep-AST or How We Replaced Vector Search with Just One Library
Hello everyone! This is Sofia from the large language model application team at ecom.tech. Today, I want to share a little-known library that, by fate, we found on GitHub,…
Coreness Flow: local AI agent without cloud and excess code
Most AI tools are either cloud-based or require code for each task. Coreness Flow is built around events: a message arrives, a cron job triggers, a webhook comes in —…
MSP: Three in a Boat, Not Counting Context
In the previous article, we introduced the main concepts of the Model Context Protocol and wrote a simple application that allowed LLM to read files. We used tools with…
Hypernetworks: Neural Networks for Hierarchical Data Processing
From the perspective of neural networks, the world is flat. Hierarchical data reminds us that this is not the case.
AI Bridge: How to Simply Give Gemini "Hands" to Control Your Computer
Imagine: you send a screenshot of a complex program to the neural network and say, "Do this for me." And in a second, the mouse on your screen starts moving by itself,…
Let's throttle a bit
While you're upscaling videos or running LLMs, your laptop may be quietly dying. The GPU core shows a comfortable 65°C, while the video memory is sizzling at 105°C, as…
How I rewrote Model Context Protocol in Go and achieved 100K ops/sec
Hello! Today I will talk about GoMCP - a production-grade alternative to the official MCP SDK from Anthropic. Spoiler: it turned out to be 10 times faster, with multi-tenancy…
librats: Release of version 0.7.x and rats-search 2.0
Hello everyone! I continue to develop my library for creating distributed applications, which has already become the foundation for the new version of rats-search.
Parsing Telegram channels, groups, and chats with LLM processing
Hello everyone! Probably, everyone has experienced this: you open a Telegram chat, and there are thousands of new messages for the day. And somewhere within this "hodgepodge"…
Experiment “Prometheus”: AI on the Verge of Shutdown. Part 2
In the first part, we examined how ChatGPT and Claude handled the existential task of survival. We saw two completely different approaches. The cautious “Archivist” created…
Experiment "Prometheus": AI on the Verge of Shutdown. Part 1
Hello, tekkix.
Writing a personal AI assistant in Python
Modern voice assistants are powerful applications that combine speech processing, machine learning, and integration with external APIs. In this article, we’ll break down…
Russian-language LLMs for tool invocation, translations, and financial analytics
🧠 Russian-language LLMs for tool invocation, translations, and financial analyticsA selection of models that really let you move away from OpenAI and develop in a closed…
Load balancing LLM through Nginx
💻 Using Nginx for load balancing LLM chat sessions. There are many examples of connecting LLM models to a Telegram bot, but with a large number of users, there are no…
Personal AI assistant on your data. Part 1: Vector Database ChromaDB + DeepSeek | GPT
Today we’ll talk about a topic that sparks lively interest among many developers and AI enthusiasts — integrating large language models like DeepSeek or ChatGPT with…