Zukko Blog
Guides to Claude Code, Cursor, Codex and the Claude and GPT APIs: setup, token savings and troubleshooting.
LangChainGo: connecting a Go application to an OpenAI-compatible API
5 min · · development
The langchaingo library accepts any OpenAI-compatible address. We show the client, a request, streaming and a templated chain in Go, and estimate call costs.
Cursor for 1C: writing BSL code with an AI agent
6 min · · IDE
How to open a 1C configuration dump in Cursor, write rules for BSL, give the agent metadata and avoid accepting invented code. With a session cost estimate.
LangChain with_structured_output: a typed model response
5 min · · development
How to get a Pydantic object instead of text from a model: with_structured_output, three methods, include_raw, retries on errors and testing several models on your data.
Claude CLI on Linux and macOS: Install and Connect to the Gateway
5 min · · development
Install Claude Code on Linux and macOS, put the address and key into your shell profile and verify the connection with curl. PATH and permission errors included.
Skills in Claude Code: what they are and how to write your own
7 min · · агенты
A skill is a folder with a SKILL.md file that Claude Code loads only when needed. We compare it with CLAUDE.md and write one of our own.
Cursor AI setup: models, your own key, rules and indexing
6 min · · IDE
A step-by-step Cursor setup: your own key with the gateway address, models, project rules, context exclusions and a connection check. What to do on day one.
LangChain4j: connect a Java app to Claude and GPT via a gateway
4 min · · development
LangChain4j works with any OpenAI-compatible address. Build setup, chat, streaming and an AI Service with @Tool on the Zukko gateway.
Vibe coding apps: from idea to a working MVP with an agent
6 min · · development
A practical route for building a small web app with an agent, from the idea to deployment. Where a human is required, and what it costs.
Vibe coding downsides: a risk checklist and how to reduce them
5 min · · агенты
Vibe coding speeds up prototypes, but it has a price. A checklist of nine risks with a practical measure for each and a calculation of possible losses.
Codex on Windows: native and WSL install with a gateway
5 min · · development
Codex CLI runs on Windows natively or inside WSL. Installation, where config.toml lives, connecting a Zukko key, and what to do when it fails.
Vibe coding on Android: how to program with AI from a phone
5 min · · development
A phone will not replace a laptop, but vibe coding from it is possible: the agent runs on a server and you drive it over SSH or a web chat. What you need and where the limit is.
Cline in JetBrains: Installing in IntelliJ IDEA and PyCharm
6 min · · IDE
The Cline plugin is in the JetBrains Marketplace. Installation, provider setup with the gateway address, auto-approve and a fallback via ACP.
LangGraph in Python: a first graph with a model via a gateway
5 min · · агенты
We build a small support graph in LangGraph: two models at different prices, branching, a capped retry loop and a clear picture of how execution works.
Vibe coding in 1C: an agent, a configuration dump and checking the result
5 min · · агенты
A working scheme for a 1C developer: files instead of the database, an agent in the terminal, rules in CLAUDE.md and a mandatory check in the Configurator.
Claude API docs in plain terms: the Messages API without the fluff
6 min · · API keys
A short reference to the Claude Messages API: what is required, what is deprecated, how to read the response and errors. Examples target the gateway.
A neural network for solving programming problems: learn, do not copy
4 min · · development
A model can be set up so it does not hand over the answer at once but walks you up a ladder of hints. The prompt, the script and the checking tricks.
How to write your own MCP server in Python and connect it to an agent
5 min · · development
We write an MCP server in Python in about 30 lines, test it without an agent, connect it to Claude Code and watch the agent call the tool.
PDF to Excel with a neural network: extract tables without copy-paste
4 min · · автоматизация
A working pipeline: pull a table out of a PDF, ask the model for JSON, write xlsx and reconcile the totals so a silent error does not slip through.
Cursor in Russian: interface, AI replies and code comments
6 min · · IDE
Three different questions behind one query: the language of AI replies, of the interface and of code comments. Each covered, with .cursor/rules and a token calculation.
LLM in production: a checklist before launching an AI feature
6 min · · API keys
What to check before releasing a feature built on a language model: keys, limits, timeouts, retries, a fallback model, PII-free logs, cost tracking and regression tests.
OpenAI API in Ollama: one code path for a local and a cloud model
5 min · · development
Ollama answers requests in the OpenAI format. So one piece of code can target a local model or a gateway just by changing base_url and the model name.
How to update Claude Code, roll back a version or remove it completely
6 min · · development
Commands to update, roll back and remove Claude Code by install method, and how to keep your gateway connection settings when reinstalling.
Open WebUI API: sending requests to your models from code
5 min · · API keys
Open WebUI has its own API: the models you see in the chat are reachable from scripts. We show how to get a key, which endpoints to call and where the two keys get mixed up.
Translating games with AI: localizing strings without broken tags
5 min · · автоматизация
How to translate thousands of game strings without breaking placeholders, tags or UI layout: batch format, checks, retries and cost.