<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Developer Tools on Blog by Krishna Alagiri.</title><link>https://thekrishna.in/blogs/tags/developer-tools/</link><description>Recent content in Developer Tools on Blog by Krishna Alagiri.</description><generator>Hugo</generator><language>en-us</language><copyright>Written with ❤️️ by Krishna.</copyright><lastBuildDate>Fri, 04 Sep 2026 12:00:00 -0700</lastBuildDate><atom:link href="https://thekrishna.in/blogs/tags/developer-tools/index.xml" rel="self" type="application/rss+xml"/><item><title>A Self Hosted Agent Harness for Tasks, Documentation, Search and Applications</title><link>https://thekrishna.in/blogs/blog/assistant-project/</link><pubDate>Fri, 04 Sep 2026 12:00:00 -0700</pubDate><guid>https://thekrishna.in/blogs/blog/assistant-project/</guid><description>&lt;h2 id="overview">Overview&lt;/h2>
&lt;p>The &lt;a href="https://docs.mewbo.com/latest/" target="_blank" rel="noopener">assistant project&lt;/a>

 is an open stack for putting long running agents to work across the systems you already run. It is self hosted and runs on &lt;a href="https://docs.mewbo.com/latest/llm-setup/" target="_blank" rel="noopener">any model&lt;/a>

. Every agent is scoped to the person it runs for.&lt;/p>
&lt;p>Coding agents made engineers far more productive. Everyone else files a ticket and waits. A GTM engineer wants scheduled lead enrichment. A support lead wants one view over three tools. A new hire wants to ask a repository how it works. All three need an agent next to their own data, inside their own permissions. It has to live on the surface they already work in. I built one harness and pointed it at each job. Tasks, the wiki, search and apps are that harness over different data. The same session reaches a browser, a terminal, an Android phone, a team chat, an inbox and a &lt;a href="https://docs.mewbo.com/latest/clients-home-assistant/" target="_blank" rel="noopener">Home Assistant&lt;/a>

 microphone. An improvement to the loop reaches all of them.&lt;/p></description></item><item><title>Grove, an Agent Development Environment for Coding Agent Fleets</title><link>https://thekrishna.in/blogs/blog/grove/</link><pubDate>Thu, 20 Aug 2026 12:00:00 -0700</pubDate><guid>https://thekrishna.in/blogs/blog/grove/</guid><description>&lt;h2 id="overview">Overview&lt;/h2>
&lt;p>&lt;a href="https://factory.mewbo.com/latest/" target="_blank" rel="noopener">Grove&lt;/a>

 is an agent development environment. It takes the coding agents a team already uses and runs them as a software factory, with a sandbox, an orchestration layer and observability around each one. &lt;a href="https://code.claude.com/docs" target="_blank" rel="noopener">Claude Code&lt;/a>

, &lt;a href="https://developers.openai.com/codex" target="_blank" rel="noopener">Codex&lt;/a>

 and &lt;a href="https://opencode.ai" target="_blank" rel="noopener">OpenCode&lt;/a>

 run unchanged inside it. Each task gets its own &lt;a href="https://factory.mewbo.com/latest/features-workspace-lifecycle/" target="_blank" rel="noopener">workspace&lt;/a>

 and is tracked from ticket to trace.&lt;/p></description></item></channel></rss>