Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
How to connect Qwen to VS Code: Companion, Cline and Continue
5 min · · IDE
Two ways to get Qwen in your editor: the official Companion for Qwen Code, or the Cline, Kilo Code and Continue extensions with an OpenAI-compatible key.
Cursor not working: common problems and how to fix them
6 min · · errors
Cursor froze, shows Reconnecting or does not answer. We go from simple causes to complex ones and cover problems with your own key and a gateway separately.
Claude Code in JetBrains: IntelliJ IDEA and PyCharm on Your Own Key
6 min · · IDE
The plugin does not bundle Claude Code. It launches the console agent in the IDE terminal. Install, gateway key, diffs and common failures explained.
MCP in opencode: connecting local and remote servers
5 min · · агенты
Step by step MCP setup for opencode: the mcp block in config, headers and OAuth, disabling servers for specific agents, and what extra tools cost.
Porting code to another language with AI: migration plan and checks
5 min · · development
AI translates code between languages quickly, but it will not preserve behaviour on its own. A module migration plan with reference tests and comparison.
LangChain text splitters: how to cut text into chunks correctly
5 min · · development
How to choose chunk size and overlap in RecursiveCharacterTextSplitter, why you should count in tokens and how to check the count against an exact token number.
Roo Code or Cursor in 2026: Roo Code is shut down, what to pick instead
7 min · · сравнение
Roo Code was shut down on May 15, 2026, so the choice is now between other VS Code extensions and the standalone Cursor editor. A practical comparison and a task cost estimate.
LangChain and MCP: connecting MCP tools to a LangGraph agent
5 min · · агенты
MCP servers give an agent ready-made tools, and adapters turn them into LangChain tools. The current approach, running on models through an OpenAI-compatible gateway.
Agentic coding: what it is and how it differs from autocomplete
5 min · · агенты
An agent does not suggest the next line, it runs a task in a loop: read, edit, run, check. How it works, which tools exist and what an hour costs via API.
How to use Claude Code: a working loop on a real task
5 min · · development
One full pass with Claude Code, from writing the task to the commit. How to read the diff, undo edits and keep token spend under control.
Cline Rules: how to write project rules in .clinerules
5 min · · IDE
Rules in .clinerules stop you from repeating the same requests in every task. Structure, Python and TypeScript examples, and the price of extra lines.
LangChain RAG: a working example with a model via a gateway
5 min · · development
We build a simple RAG with LangChain: documents, chunks, vector search and a model answer via a gateway. We count what a question costs and trim wasted tokens.
DeepSeek API OCR: extracting text from images with V4 Pro
5 min · · автоматизация
DeepSeek V4 Pro accepts images, so it can read text from screenshots and scans. Python code, a JSON mode, accuracy checks and a cost calculation for 1,000 pages.
LangChain Deep Agents: what it is and how to run it on your own model
5 min · · агенты
Deep Agents is a ready-made harness on top of LangChain: files, subagents, context summarization. What is inside, how to run it via a gateway and what it costs.
Paying for AI in rubles: SBP, a dollar balance and the exchange rate
5 min · · payments
Rubles paid via SBP turn into a dollar balance at the rate on the payment date plus the payment page fee. The formula, a top-up table and the price of requests in rubles.
GitHub Copilot vs Cursor: what a developer should choose in 2026
7 min · · сравнение
Copilot plugs into the environment you already use, Cursor is the environment. A comparison by integration, agents, models and payment, then the cost of working on your own key.
AI for translating scientific papers: terms, formulas and references
5 min · · автоматизация
Scientific text breaks where ordinary translation goes smoothly: formulas, terms, references. A pipeline with formula protection, a glossary and checks, and what it costs.
Cline workflows: repeatable scenarios in one command
5 min · · автоматизация
Release, PR review, a daily changelog: any repeating sequence can be written in markdown and launched from the Cline chat. Format and cost per run.
Knowledge base in Open WebUI: RAG setup on your own documents
7 min · · автоматизация
Open WebUI lets you upload documents and ask questions about them. We show how to create a knowledge base, which settings affect answer accuracy, and what a single question costs.
LangChain Ollama or a cloud model: one codebase, two models
4 min · · сравнение
ChatOllama runs a model on your machine, ChatOpenAI with a gateway base_url calls a cloud one. We write the code once and switch with environment variables.
Claude Code locally: what actually works with a local model
6 min · · агенты
Claude Code can run on a model that lives on your own computer. We cover the setup, how it differs from cloud models, and when you should count dollars instead of hardware.
Cursor vs Codex: an AI editor or a console agent, which to choose
6 min · · сравнение
Cursor and Codex solve the same problem differently: one lives in the editor, the other in the terminal. Workflows, connecting your own key and the cost of a session, with a calculation.
The best AI for C# programming: choosing a model and setting up an agent
5 min · · development
We give no ranking of the best model for C#, but we show how to compare options by price and index, set up an agent for .NET and verify the result with builds and tests.
AI for Java code: agent, tests and Spring without extra edits
5 min · · development
In a Java project an agent is valuable while it leaves your architecture and dependencies alone. Rules, build commands, test generation and a cost estimate.