<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Developer-Tools on Neputer Blog</title><link>https://blog.neputer.com/tags/developer-tools/</link><description>Recent content in Developer-Tools on Neputer Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 02 Aug 2026 15:41:29 +0545</lastBuildDate><atom:link href="https://blog.neputer.com/tags/developer-tools/index.xml" rel="self" type="application/rss+xml"/><item><title>Building a Custom Agent with the Claude Agent SDK</title><link>https://blog.neputer.com/posts/building-custom-agent-claude-agent-sdk/</link><pubDate>Fri, 26 Jun 2026 00:00:00 +0000</pubDate><guid>https://blog.neputer.com/posts/building-custom-agent-claude-agent-sdk/</guid><description>Hands-on guide to building a custom agent with the Claude Agent SDK — define tools, wire MCP servers, and delegate to subagents, with runnable TypeScript and Python.</description></item><item><title>Claude Code with Local Models and OpenRouter: The Complete Guide</title><link>https://blog.neputer.com/posts/claude-code-with-local-models-and-openrouter/</link><pubDate>Tue, 16 Jun 2026 00:00:00 +0000</pubDate><guid>https://blog.neputer.com/posts/claude-code-with-local-models-and-openrouter/</guid><description>Run Anthropic&amp;#39;s Claude Code CLI against OpenRouter, Ollama, or any custom model endpoint. Setup, model compatibility, gotchas, and a real test matrix.</description></item><item><title>AI-Assisted Development: What Actually Works in 2026</title><link>https://blog.neputer.com/posts/ai-assisted-development-2026/</link><pubDate>Mon, 01 Jun 2026 00:00:00 +0000</pubDate><guid>https://blog.neputer.com/posts/ai-assisted-development-2026/</guid><description>&lt;p&gt;AI coding assistants have moved from novelty to necessity. But the hype cycle has settled, and we now have real data on what works and what doesn&amp;rsquo;t.&lt;/p&gt;
&lt;h2 id="the-landscape"&gt;The Landscape&lt;/h2&gt;
&lt;table&gt;
&lt;thead&gt;
&lt;tr&gt;
&lt;th&gt;Tool&lt;/th&gt;
&lt;th&gt;Best For&lt;/th&gt;
&lt;th&gt;Limitations&lt;/th&gt;
&lt;/tr&gt;
&lt;/thead&gt;
&lt;tbody&gt;
&lt;tr&gt;
&lt;td&gt;GitHub Copilot&lt;/td&gt;
&lt;td&gt;Autocomplete, boilerplate&lt;/td&gt;
&lt;td&gt;Struggles with multi-file refactors&lt;/td&gt;
&lt;/tr&gt;
&lt;tr&gt;
&lt;td&gt;Cursor&lt;/td&gt;
&lt;td&gt;Full-featured AI IDE&lt;/td&gt;
&lt;td&gt;Context window limits on large codebases&lt;/td&gt;
&lt;/tr&gt;
&lt;tr&gt;
&lt;td&gt;Claude Code&lt;/td&gt;
&lt;td&gt;Terminal-native agentic coding&lt;/td&gt;
&lt;td&gt;Requires explicit instruction&lt;/td&gt;
&lt;/tr&gt;
&lt;tr&gt;
&lt;td&gt;OpenCode&lt;/td&gt;
&lt;td&gt;Interactive CLI with subagents&lt;/td&gt;
&lt;td&gt;Needs good task decomposition&lt;/td&gt;
&lt;/tr&gt;
&lt;/tbody&gt;
&lt;/table&gt;
&lt;h2 id="where-ai-excels"&gt;Where AI Excels&lt;/h2&gt;
&lt;h3 id="test-generation"&gt;Test Generation&lt;/h3&gt;
&lt;p&gt;AI-generated tests catch edge cases humans miss. In our codebase, AI-authored tests found 23% more boundary condition bugs than human-written equivalents:&lt;/p&gt;</description></item></channel></rss>