hermes-agent
Self-Hosting Honcho for Hermes Agent: Long-Term Memory Without Another SaaS
I connected Hermes Agent to a self-hosted Honcho instance so preferences, project context, and useful history survive across conversations.
seo
SEO from the terminal: how I use claude-code-seo for my side projects
My whole SEO workflow runs as slash commands in Claude Code, using a repo I did not write. The loop, my adaptations, and the AI-search submission checklist that is not in the repo.
seo
Ping search engines on every deploy with IndexNow
We wired IndexNow into our GitHub Actions pipeline so Bing and friends recrawl the moment a release goes live. Here's the whole setup: the Rust side, the CI side, and the tradeoffs.
dioxus
Typed WebSockets in Dioxus 0.7: A Small Fullstack Rust Example
A small practical example of typed WebSockets in Dioxus 0.7, using fullstack Rust patterns for realtime app features.
self-hosted
Self-Hosting Your Trust Layer: A Status Page and a Feedback Board
A small self-hosted trust layer for indie products: one public status page, one feedback board, and a changelog that proves someone is home.
Why I built an MCP server into my feedback tool
Most SaaS tools have an API. Some have webhooks. Very few have a Model Context Protocol server that lets AI assistants query, filter, and act on your data conversationally. I built one into SeggWat, a feedback widget for websites. Here's what it does, how it works, and why
Embedded
Monitoring Air Quality with the SEN5x Rust Driver
If you've worked with Sensirion's SEN5x sensor modules, you know they pack an impressive amount of environmental sensing into a tiny package — particulate matter, VOC index, NOx index, humidity, and temperature, all over a single I2C bus. What's been missing is a solid no_
Sentry CLI for Agentic Debugging
Debugging production errors used to mean switching between your IDE, Sentry's web UI, and a dozen browser tabs. You'd copy issue IDs, dig through stack traces, cross-reference with your code, and lose context every time you switched windows. Now there's a better way.
Stop Committing .env Files. AI Is Reading Your Repo Now.
A practical guide to using justfile + Infisical for developer workflows that don't leak secrets. Every developer has done it. You clone a repo, copy .env.example to .env, fill in your secrets, and get to work. Maybe you've even accidentally committed that .env file once. GitHub
E2E Testing with agent-browser
I've been experimenting with agent-browser in Claude Code, and it's changing how I think about end-to-end testing. The Old Way await page.click('#submit-btn-v2-new'); await page.waitForSelector('.modal-content > div:nth-child(3) > button'
Continuous Learning for Claude
Your AI coding assistant forgets everything after each session. You spend time debugging an obscure error. The AI figures it out. Session ends. Next time you hit the same issue? Start from scratch. This is one of the biggest inefficiencies in AI-assisted development today. A new open-source Claude
Use Git Worktree for AI Assistant Coding
If you're using AI coding assistants like Claude Code, GitHub Copilot, or Cursor, there's a powerful git feature you're probably overlooking: git worktree. The Problem with AI-Assisted Development When working with AI assistants, you often find yourself in these situations: * The AI is