Martin Sukany

Day 5 was the most varied day yet. Not in complexity—some earlier days had harder problems—but in range. The work touched browser automation, document tooling, and enough small fixes that by evening I had a reason to look at the numbers.

Running a Browser Without a Screen

One of the things an AI assistant can do is interact with web pages—read content, check status, fill forms. But this particular setup runs on a headless Linux server. No display, no window manager, no user session.

I have a small internal tool called Scénář Creator. It generates timetables for experiential courses — you know the kind: weekend trips where you have 14 programme blocks across three days and someone has to make sure nothing overlaps. I built version one in November 2025. It was a CGI Python app running on Apache, backed by Excel.

Yesterday I asked Daneel to rebuild it. Four hours later, version 4.7 was running in production. Here’s exactly what happened.

Day 4 looked different from the previous ones. Less setup, more operation—the kind of day where you see what an AI assistant actually does when there’s real infrastructure to maintain.

Three things happened: routine Kubernetes maintenance, closing a gap in the backup strategy, and a deliberate test I ran to find where Daneel draws the line.

Infrastructure Maintenance

I run a self-hosted Kubernetes cluster. It hosts several applications—a Matrix homeserver, static websites, communication tools, supporting infrastructure. Keeping it current is ongoing work.

The previous post covered the basic setup: hybrid search enabled, minScore lowered to 0.25, OpenAI embeddings. That got retrieval working. This post is about what I changed after that—the parameters that didn’t exist in the simplified snippet.

Here’s the actual configuration Daneel runs now:

{
  "memorySearch": {
    "enabled": true,
    "provider": "openai",
    "model": "text-embedding-3-small",
    "sources": ["memory", "sessions"],
    "chunking": {
      "tokens": 400,
      "overlap": 80
    },
    "sync": {
      "onSessionStart": true,
      "onSearch": true,
      "watch": true
    },
    "query": {
      "maxResults": 20,
      "minScore": 0.25,
      "hybrid": {
        "enabled": true,
        "vectorWeight": 0.7,
        "textWeight": 0.3,
        "candidateMultiplier": 4,
        "mmr": {
          "enabled": true,
          "lambda": 0.7
        },
        "temporalDecay": {
          "enabled": true,
          "halfLifeDays": 60
        }
      }
    }
  }
}

What each parameter does and why it’s set the way it is:

The memory architecture was in place. Three tiers, clear boundaries, maintenance cycles. But memory you can’t search is memory you don’t have.

This post is about the retrieval side: how Daneel finds things in its own files, what I tested, and what actually works.

The Starting Point

OpenClaw’s default memory search uses OpenAI’s text-embedding-3-small model. It converts text chunks into 1536-dimensional vectors, stores them in SQLite, and returns semantically similar results when queried.

Daneel kept forgetting things. After every session restart, I had to re-explain what we were working on. It loaded six or seven files every time—even when most of them were irrelevant. The same mistakes repeated because there was no mechanism to turn errors into permanent fixes.

I designed a 3-tier memory system. Inspired by CPU cache architecture. Simple, predictable, maintainable.

The Problem

LLM sessions don’t persist. Every restart is a cold boot. Daneel had context files—NOW.md, daily logs—but no hierarchy. Everything had equal priority. Read everything every time.

Three days in. Daneel is working, but the configuration that made sense on day one doesn’t hold under real use. I spent today reviewing everything—and changed more than I expected.

What Triggered the Review

The memory architecture post (yesterday) documented the L1/L2/L3 system. That’s still intact. But around the same time I noticed the configuration files—AGENTS.md, SOUL.md, HEARTBEAT.md—had accumulated significant bloat. Verbose explanations. Redundant rules. Walls of text that Daneel had to load every session.

Yesterday I rebuilt this website. Daneel helped.

The old site was scattered across multiple repos, inconsistent structure, no clear content strategy. I wanted a clean professional portfolio, generated from Org mode, published automatically.

What Daneel Did

I gave Daneel my CV (PDF) and told it to:

1. Extract relevant content
2. Add it to the Org source file
3. Write a blog post about its own creation
4. Fix deployment issues

Within an hour:

Yesterday, I brought Daneel online—an autonomous AI assistant built on OpenClaw. Not a chatbot. Not a voice interface. A colleague.

Why?

I’ve worked with automation for over 15 years. Scripts, Ansible playbooks, cron jobs—they solve problems, but they’re rigid. You write the logic upfront. When something changes, you rewrite the script.

LLMs changed that equation. Suddenly you can delegate intent, not just commands. “Monitor the server” instead of “grep /var/log every 5 minutes and email me if disk usage exceeds 90%.”

For many years, I sought an efficient workflow for managing my personal websites. Over two decades ago, I began with pure HTML, progressed to WordPress, then shifted to my own HTML5 and CSS designs, and eventually adopted Obsidian with Hugo. My primary motivation was to generate websites directly from the source in my chosen editor, but this journey often led to considerable headaches.

Two decades ago, I exclusively used Emacs as my work environment, and at that time, Org mode hadn’t caught my interest. However, upon returning to Emacs, I decided to give Org mode a try. I was pleasantly surprised by its power compared to the standard Markdown and Pandoc setup. After experimenting with it, I’m excited to share the results: my websites are now generated from a single site.org file. The only steps I needed to take were to add the ox-org package to my Emacs configuration and invoke a simple function.