JSSHTunnel 0.0.0 Released!
JSSHTunnel is a lightweight GUI application which forwards local & remote ports over SSH connections. It is written in Java and uses Eclipse SWT & JSch. All you need is a JVM to run it. I've released version 0.0.0, it is under GPL. Features & Limitations in 0.0.0:* Targetted at Windows platform, comes with a Windows-based installer, other platforms will follow
- Resides in the System Tray when minimised
- Requires a 1.4 or 1.5 JVM on the target machine (works with the Sun & Microsoft JVM's)
- Currently only supports one connection, with a single local forward (hey, its only a proof of concept release)
- Connection details (including passwords) are stored in plaintext form in its XML configuration file %USERPROFILE%.jsshtunnel.xml
- Since its just the very first release it is quite basic, but it works :P
Screenshots:
Screenshot of the Main Window Click to enlarge
Main Window
Screenshot of the Configuration Window Click to enlarge
Configuration Window Download: http://jsshtunnel.sourceforge.net/ Roadmap:* Multiple connections each with multiple local & remote forwards - Hot-pluggable port forwarding rules without having to re-connect
- Cross platform UI & command line versions
- Encrypted passwords for configuration file
From Solo Tool to Team Infrastructure: Scaling Gluon for Production
When I first built Gluon on my Mac mini, I was solving a personal problem: monitoring Claude agents without losing my mind to tmux logs. But when teams join the picture, everything changes — security, governance, observability, and the fundamental role of the developer. Here's what production infrastructure for autonomous agents looks like.
Ralph Loop: Teaching AI Agents to Work Autonomously (Without Burning Your Budget)
How Gluon's Ralph Loop enables autonomous Claude execution with built-in safety rails — circuit breakers, multi-signal completion detection, and cost controls that scale from simple tasks to complex workflows.
Scraper MCP: Context-Efficient Web Scraping for LLMs
I built an open-source MCP server that reduces LLM token usage by 70-90% through server-side HTML filtering, markdown conversion, and CSS selector targeting. Here's why context efficiency matters—and how Scraper MCP solves it.