#jbang — Public Fediverse posts

После вайб-кодинга: почему в 2026 году появляется новый класс Code Clean-up Agents

После вайб-кодинга: почему в 2026 году появляется новый класс Code Clean-up Agents. Как стоимость разработки смещается от генерации к проверке, рефакторингу и контролю изменений Я всё чаще вижу один и тот же сценарий. Агент получает задачу, за несколько минут собирает патч, запускает тесты и сообщает об успехе. Первый просмотр выглядит обнадёживающе. Потом начинается ревью. Чем быстрее появляется код, тем больше времени уходит на восстановление контекста: что агент поменял, на какие факты опирался, какой конфигурацией запускал тесты и сколько попыток сделал до финального ответа. В этой точке полезно отделить генерацию патча от подготовки изменения к отправке в основную ветку. Для второй задачи в 2026 году формируется отдельный класс инструментов: Code Clean-up Agents .

https://habr.com/ru/articles/1061498/

#aiагенты #ai #ai_agent #aiagent #ide #idea #jbang #программирование #аналитика #анализ_данных

После вайб-кодинга: почему в 2026 году появляется новый класс Code Clean-up Agents

После вайб-кодинга: почему в 2026 году появляется новый класс Code Clean-up Agents. Как стоимость разработки смещается от генерации к проверке, рефакторингу и контролю изменений Я всё чаще вижу один и тот же сценарий. Агент получает задачу, за несколько минут собирает патч, запускает тесты и сообщает об успехе. Первый просмотр выглядит обнадёживающе. Потом начинается ревью. Чем быстрее появляется код, тем больше времени уходит на восстановление контекста: что агент поменял, на какие факты опирался, какой конфигурацией запускал тесты и сколько попыток сделал до финального ответа. В этой точке полезно отделить генерацию патча от подготовки изменения к отправке в основную ветку. Для второй задачи в 2026 году формируется отдельный класс инструментов: Code Clean-up Agents .

https://habr.com/ru/articles/1061498/

#aiагенты #ai #ai_agent #aiagent #ide #idea #jbang #программирование #аналитика #анализ_данных

После вайб-кодинга: почему в 2026 году появляется новый класс Code Clean-up Agents

После вайб-кодинга: почему в 2026 году появляется новый класс Code Clean-up Agents. Как стоимость разработки смещается от генерации к проверке, рефакторингу и контролю изменений Я всё чаще вижу один и тот же сценарий. Агент получает задачу, за несколько минут собирает патч, запускает тесты и сообщает об успехе. Первый просмотр выглядит обнадёживающе. Потом начинается ревью. Чем быстрее появляется код, тем больше времени уходит на восстановление контекста: что агент поменял, на какие факты опирался, какой конфигурацией запускал тесты и сколько попыток сделал до финального ответа. В этой точке полезно отделить генерацию патча от подготовки изменения к отправке в основную ветку. Для второй задачи в 2026 году формируется отдельный класс инструментов: Code Clean-up Agents .

https://habr.com/ru/articles/1061498/

#aiагенты #ai #ai_agent #aiagent #ide #idea #jbang #программирование #аналитика #анализ_данных

ICYM: the old split was Python for scripts and Java for systems. Modern Java and JBang make that split a lot less useful, especially when the script is quietly becoming a system.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

ICYM: the old split was Python for scripts and Java for systems. Modern Java and JBang make that split a lot less useful, especially when the script is quietly becoming a system.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

ICYM: the old split was Python for scripts and Java for systems. Modern Java and JBang make that split a lot less useful, especially when the script is quietly becoming a system.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

ICYM: the old split was Python for scripts and Java for systems. Modern Java and JBang make that split a lot less useful, especially when the script is quietly becoming a system.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

ICYM: the old split was Python for scripts and Java for systems. Modern Java and JBang make that split a lot less useful, especially when the script is quietly becoming a system.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

Tired of “create project → configure build → wait” just to test an idea in #Java? #Java25 + #JEP512 + #JBang make Java feel closer to scripting—and notebooks + #RaspberryPi turn it into a real learning lab.

Read the roadmap by @igfasouza: https://javapro.io/2026/01/15/java-25-jep-512-jbang-notebooks-graallpy-and-raspberry-pi-for-interactive-learning/

#JAVAPRO

Tired of “create project → configure build → wait” just to test an idea in #Java? #Java25 + #JEP512 + #JBang make Java feel closer to scripting—and notebooks + #RaspberryPi turn it into a real learning lab.

Read the roadmap by @igfasouza: https://javapro.io/2026/01/15/java-25-jep-512-jbang-notebooks-graallpy-and-raspberry-pi-for-interactive-learning/

#JAVAPRO

code that just runs as a script. using #JBang to convert pptx slides to png.
https://shaaf.dev/post/2026-04-15-pptx-to-png-with-jbang/

code that just runs as a script. using #JBang to convert pptx slides to png.
https://shaaf.dev/post/2026-04-15-pptx-to-png-with-jbang/

code that just runs as a script. using #JBang to convert pptx slides to png.
https://shaaf.dev/post/2026-04-15-pptx-to-png-with-jbang/

code that just runs as a script. using #JBang to convert pptx slides to png.
https://shaaf.dev/post/2026-04-15-pptx-to-png-with-jbang/

code that just runs as a script. using #JBang to convert pptx slides to png.
https://shaaf.dev/post/2026-04-15-pptx-to-png-with-jbang/

Java is becoming a better scripting language without becoming a toy scripting language. JBang, modern Java, and better packaging make it a serious option for automation that should survive past Friday.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

Java is becoming a better scripting language without becoming a toy scripting language. JBang, modern Java, and better packaging make it a serious option for automation that should survive past Friday.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

Java is becoming a better scripting language without becoming a toy scripting language. JBang, modern Java, and better packaging make it a serious option for automation that should survive past Friday.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

Java is becoming a better scripting language without becoming a toy scripting language. JBang, modern Java, and better packaging make it a serious option for automation that should survive past Friday.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

Java is becoming a better scripting language without becoming a toy scripting language. JBang, modern Java, and better packaging make it a serious option for automation that should survive past Friday.

https://www.the-main-thread.com/p/java-is-the-new-python-jbang-java-21

#Java #JBang #DevTools

I think I will be removing #JBang from all my my #Java script programs. JEP 458 and 512 are all I need in the end anyway.

I think I will be removing #JBang from all my my #Java script programs. JEP 458 and 512 are all I need in the end anyway.

I think I will be removing #JBang from all my my #Java script programs. JEP 458 and 512 are all I need in the end anyway.

I think I will be removing #JBang from all my my #Java script programs. JEP 458 and 512 are all I need in the end anyway.

I think I will be removing #JBang from all my my #Java script programs. JEP 458 and 512 are all I need in the end anyway.

It still amazes me how easy & fast it is to create #MCP servers in #Java with #jbang, #langchain4j and a custom skill inside #geminicli

A handful of prompts, and less than 5 minutes later, I had created a working #Wikipedia MCP server!

https://glaforge.dev/posts/2026/04/02/creating-a-wikipedia-mcp-server-in-java-in-a-few-prompts/

It still amazes me how easy & fast it is to create #MCP servers in #Java with #jbang, #langchain4j and a custom skill inside #geminicli

A handful of prompts, and less than 5 minutes later, I had created a working #Wikipedia MCP server!

https://glaforge.dev/posts/2026/04/02/creating-a-wikipedia-mcp-server-in-java-in-a-few-prompts/

It still amazes me how easy & fast it is to create #MCP servers in #Java with #jbang, #langchain4j and a custom skill inside #geminicli

A handful of prompts, and less than 5 minutes later, I had created a working #Wikipedia MCP server!

https://glaforge.dev/posts/2026/04/02/creating-a-wikipedia-mcp-server-in-java-in-a-few-prompts/

It still amazes me how easy & fast it is to create #MCP servers in #Java with #jbang, #langchain4j and a custom skill inside #geminicli

A handful of prompts, and less than 5 minutes later, I had created a working #Wikipedia MCP server!

https://glaforge.dev/posts/2026/04/02/creating-a-wikipedia-mcp-server-in-java-in-a-few-prompts/

It still amazes me how easy & fast it is to create #MCP servers in #Java with #jbang, #langchain4j and a custom skill inside #geminicli

A handful of prompts, and less than 5 minutes later, I had created a working #Wikipedia MCP server!

https://glaforge.dev/posts/2026/04/02/creating-a-wikipedia-mcp-server-in-java-in-a-few-prompts/

AI agents behave much more like terminal users than API clients.

So it’s not surprising that CLI tools often outperform MCP integrations for many workflows.

For Java developers this opens an interesting path:
JBang + small CLI tools as agent capabilities.

I wrote a deep dive here:

https://www.the-main-thread.com/p/ai-agents-cli-tools-jbang-java-architects

#Java #AI #DevTools #JBang #AIagents

AI agents behave much more like terminal users than API clients.

So it’s not surprising that CLI tools often outperform MCP integrations for many workflows.

For Java developers this opens an interesting path:
JBang + small CLI tools as agent capabilities.

I wrote a deep dive here:

https://www.the-main-thread.com/p/ai-agents-cli-tools-jbang-java-architects

#Java #AI #DevTools #JBang #AIagents

AI agents behave much more like terminal users than API clients.

So it’s not surprising that CLI tools often outperform MCP integrations for many workflows.

For Java developers this opens an interesting path:
JBang + small CLI tools as agent capabilities.

I wrote a deep dive here:

https://www.the-main-thread.com/p/ai-agents-cli-tools-jbang-java-architects

#Java #AI #DevTools #JBang #AIagents

AI agents behave much more like terminal users than API clients.

So it’s not surprising that CLI tools often outperform MCP integrations for many workflows.

For Java developers this opens an interesting path:
JBang + small CLI tools as agent capabilities.

I wrote a deep dive here:

https://www.the-main-thread.com/p/ai-agents-cli-tools-jbang-java-architects

#Java #AI #DevTools #JBang #AIagents

AI agents behave much more like terminal users than API clients.

So it’s not surprising that CLI tools often outperform MCP integrations for many workflows.

For Java developers this opens an interesting path:
JBang + small CLI tools as agent capabilities.

I wrote a deep dive here:

https://www.the-main-thread.com/p/ai-agents-cli-tools-jbang-java-architects

#Java #AI #DevTools #JBang #AIagents

Most Java CLI tools stop at mvn compile exec:java.

That works locally. It doesn’t scale.

In this guide I show how to:
- build a fat JAR
- automate GitHub releases
- publish a JBang catalog
- install with one command

No cloning. No Maven required.

Full tutorial:
https://www.the-main-thread.com/p/ship-java-cli-jreleaser-jbang-github-release

#Java #JReleaser #JBang #Maven #OpenSource

Most Java CLI tools stop at mvn compile exec:java.

That works locally. It doesn’t scale.

In this guide I show how to:
- build a fat JAR
- automate GitHub releases
- publish a JBang catalog
- install with one command

No cloning. No Maven required.

Full tutorial:
https://www.the-main-thread.com/p/ship-java-cli-jreleaser-jbang-github-release

#Java #JReleaser #JBang #Maven #OpenSource

Most Java CLI tools stop at mvn compile exec:java.

That works locally. It doesn’t scale.

In this guide I show how to:
- build a fat JAR
- automate GitHub releases
- publish a JBang catalog
- install with one command

No cloning. No Maven required.

Full tutorial:
https://www.the-main-thread.com/p/ship-java-cli-jreleaser-jbang-github-release

#Java #JReleaser #JBang #Maven #OpenSource

Most Java CLI tools stop at mvn compile exec:java.

That works locally. It doesn’t scale.

In this guide I show how to:
- build a fat JAR
- automate GitHub releases
- publish a JBang catalog
- install with one command

No cloning. No Maven required.

Full tutorial:
https://www.the-main-thread.com/p/ship-java-cli-jreleaser-jbang-github-release

#Java #JReleaser #JBang #Maven #OpenSource

Most Java CLI tools stop at mvn compile exec:java.

That works locally. It doesn’t scale.

In this guide I show how to:
- build a fat JAR
- automate GitHub releases
- publish a JBang catalog
- install with one command

No cloning. No Maven required.

Full tutorial:
https://www.the-main-thread.com/p/ship-java-cli-jreleaser-jbang-github-release

#Java #JReleaser #JBang #Maven #OpenSource

@aalmiray I should have followed mastodon more closely; we could have exchanged about #JBang and/or #Gradle at #JavaLand. Maybe next year. 😅

@aalmiray I should have followed mastodon more closely; we could have exchanged about #JBang and/or #Gradle at #JavaLand. Maybe next year. 😅

@aalmiray I should have followed mastodon more closely; we could have exchanged about #JBang and/or #Gradle at #JavaLand. Maybe next year. 😅

@aalmiray I should have followed mastodon more closely; we could have exchanged about #JBang and/or #Gradle at #JavaLand. Maybe next year. 😅

Java still feels “too heavy” for quick learning? @igfasouza shows how #Java25 + #JEP512, #JBang & notebooks make experimentation fast—then connects it to real hardware via #RaspberryPi + #GraalPy.

Try the stack: https://javapro.io/2026/01/15/java-25-jep-512-jbang-notebooks-graallpy-and-raspberry-pi-for-interactive-learning/

Java still feels “too heavy” for quick learning? @igfasouza shows how #Java25 + #JEP512, #JBang & notebooks make experimentation fast—then connects it to real hardware via #RaspberryPi + #GraalPy.

Try the stack: https://javapro.io/2026/01/15/java-25-jep-512-jbang-notebooks-graallpy-and-raspberry-pi-for-interactive-learning/

#Agent #skills help 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲 𝗿𝗲𝗽𝗲𝘁𝗶𝘁𝗶𝘃𝗲 𝘁𝗮𝘀𝗸𝘀.

Recently I used #GeminiCLI to easily create #MCP servers in #Java with #jbang & #LangChain4j

I extracted that 𝗸𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 into a 𝗿𝗲𝘂𝘀𝗮𝗯𝗹𝗲 SKILL.md to create more servers!

https://glaforge.dev/posts/2026/02/21/easily-build-a-local-mcp-server-in-java-with-a-skill-in-gemini-cli/

#Agent #skills help 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲 𝗿𝗲𝗽𝗲𝘁𝗶𝘁𝗶𝘃𝗲 𝘁𝗮𝘀𝗸𝘀.

Recently I used #GeminiCLI to easily create #MCP servers in #Java with #jbang & #LangChain4j

I extracted that 𝗸𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 into a 𝗿𝗲𝘂𝘀𝗮𝗯𝗹𝗲 SKILL.md to create more servers!

https://glaforge.dev/posts/2026/02/21/easily-build-a-local-mcp-server-in-java-with-a-skill-in-gemini-cli/

#Agent #skills help 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲 𝗿𝗲𝗽𝗲𝘁𝗶𝘁𝗶𝘃𝗲 𝘁𝗮𝘀𝗸𝘀.

Recently I used #GeminiCLI to easily create #MCP servers in #Java with #jbang & #LangChain4j

I extracted that 𝗸𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 into a 𝗿𝗲𝘂𝘀𝗮𝗯𝗹𝗲 SKILL.md to create more servers!

https://glaforge.dev/posts/2026/02/21/easily-build-a-local-mcp-server-in-java-with-a-skill-in-gemini-cli/

#Agent #skills help 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲 𝗿𝗲𝗽𝗲𝘁𝗶𝘁𝗶𝘃𝗲 𝘁𝗮𝘀𝗸𝘀.

Recently I used #GeminiCLI to easily create #MCP servers in #Java with #jbang & #LangChain4j

I extracted that 𝗸𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 into a 𝗿𝗲𝘂𝘀𝗮𝗯𝗹𝗲 SKILL.md to create more servers!

https://glaforge.dev/posts/2026/02/21/easily-build-a-local-mcp-server-in-java-with-a-skill-in-gemini-cli/