Martin Sukany

On day 2, the agent tried to re-enable a Twitter integration I had explicitly cancelled the night before. It had forgotten. Not because of a bug — because session restarts wipe context, and nothing in the default setup prevents an AI from re-deriving a decision you already vetoed.

That’s when I started building the infrastructure that turned a chatbot into something that actually works.

This is not a tutorial. It’s what running an autonomous AI agent looks like after 10 days: what it costs, what breaks, and what I’d change.

I run macOS Accessibility Zoom at 16× magnification. Not occasionally — all the time, every day. Apple’s built-in screen magnifier has a mode called “Follow keyboard focus” that’s supposed to track your text cursor as you type, keeping it visible on screen. Every app I use does this correctly. Terminal, VS Code, Safari, iTerm2 — they all work. Emacs did not.

For years.

I type something. The cursor moves. The Zoom viewport doesn’t follow. I have to scroll manually to find it again. Then type another character. Repeat. If you’re reading this without needing magnification, the description might sound like a minor inconvenience. It isn’t. It’s the kind of friction that makes a tool feel broken — and I use Emacs all day.

My multi-agent pipeline was failing at random. Not always, not predictably — just often enough to make me stop trusting it. Worker-2 would run, write its output, and then nothing would happen. The orchestrator was sitting there waiting for an announce that never arrived. The bug already had a ticket number: #17000. Description: hardcoded 60-second timeout, no retry. I’d built the entire coordination model on message delivery, and message delivery was the single point of failure. The fix wasn’t more retries. It was getting rid of message-based coordination entirely.

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.