Killing the Bash Daemon — One Local Executor, By Deletion

FleetCrown runs two parallel local executors on every developer machine today — a legacy bash daemon and the Fleet Runner desktop product. The bash daemon must die. This is the plan, written before the cuts so the cuts can be argued with.

From Idea to First Commit — The FleetCrown Bootstrap Loop

How FleetCrown collapses the bureaucratic distance between "I have an idea" and "the agent is writing code for it," walked through with a concrete example — a tool that writes first-principles rebuttals to articles, with full source and author transparency.

The Studio Stack — One Box, All Your Projects

A €7-a-month Hetzner box can host a portfolio of fifteen indie products. The shape of "many small projects, one operator" doesn't fit managed-service pricing models — and the boring self-hosted alternative scales further than most builders realize. A field guide.

The Levelsio Pattern, Productized — Who FleetCrown Is For

One tweet from Pieter Levels describes the manual version of what FleetCrown automates. The audience for FleetCrown is not a generic "engineering team buying tools." It is the specific person who already SSHs into a Hetzner VPS to run Claude Code next to their codebase, and wants the missing dashboard.

From Polling to Listening — FleetCrown v0.6 and the Quiet System

Moving the database from Neon to Oracle Free is the easy half. The hard half is rebuilding so the architecture itself stops asking the database questions thousands of times a day. A field guide to events, push, local-first, and why the studio's whole infrastructure can fit on one free server.

Where Stakeholders Live

Two Products or One

The Two Halves of the Individual Singularity

The Techno-Capital Machine for Individuals

From Two AIs to One

Enabling the Individual Singularity

From FleetCrown to the Shared Robotics Economy

First make FleetCrown dependable from anywhere. Then use it to launch a platform that turns idle robots into available, accountable productive capacity.

The Database Kill Switch — Neon, Oracle, Hetzner, and the Studio Stack

FleetCrown signed us out, wiped our projects from view, and taught us that "free Postgres" is not one thing. A field guide to egress cliffs, daemon traffic, and why a product studio needs one database trunk — not twelve Neon saplings.

Prompt Intelligence — Why Plumbing Was Not Enough

A migration from "infrastructure-only auto-inject" to a strategist that composes context-aware prompts. Closes the gap between the queue, the agent, and the user's actual intent.

The Model-Agnostic Layer

Every AI lab is building a walled garden. FleetCrown is building the gate that connects all of them — and eventually the plot of land that lets you grow your own.

The Remote Runtime Bridge — Full Technical Breakdown

A precise engineering account of how remote→local agent injection now works, what is still broken, and what the architecture needs next to become a genuinely useful mobile-first control plane.

The Interpreter Layer

Between what you say and what the agent needs to hear sits a gap that every voice interface quietly ignores. Here is what happens when you design that gap explicitly.

The Command That Crossed the Room

How FleetCrown gained the ability to command your local AI agents from anywhere in the world — and why a single silent bug had been blocking it from working.

The Session System and the Loop That Almost Closes Itself

How FleetCrown's prompt library and session handoff protocol work together — and the one missing piece that separates a manually-triggered execution system from a genuinely self-improving one.

"The Dispatch Intelligence Problem: Why Blind Autocontinue Breaks the Flow"

A first-principles analysis of why mechanical queue drain undermines project momentum, what it would mean for FleetCrown to dispatch intelligently, and the path toward embedding a genuine strategist in the loop.

"The Craft of Sequential Prompting: Why the Quality of What You Write Matters as Much as When It Runs"

How to write agent prompts that compound rather than drift, why the handoff is your only honest feedback, and how FleetCrown needs an intelligence layer that evaluates prompt quality — not just dispatches the next item in line.

From Localhost to a Portable FleetCrown

A product and engineering blueprint for evolving FleetCrown from a local agent dashboard into a mobile, collaborative control plane for human-machine creation.

The Queue Is Not a Single Source of Truth (Yet)

A first-principles audit of the beacon/queue/autofire system — how it actually works, where the coordination breaks down, and what a reliable version looks like.

Images as Agent Input — Why Visual Context Changes the Game

A case for adding image upload and paste support to FleetCrown's agent interface, and what it would take to do it right.

Groq, Neon, and the Next Infrastructure Layer

The practical plan for moving FleetCrown's AI inference to Groq and its database to Neon — what is already done, what needs a login, and why this order makes sense.

Control and Projects — Two Views, One System

Control and Projects serve genuinely different needs and should stay separate. Here is the source of truth for each, what their tiles show, and how to improve them.

The Anatomy of a Broken Injection Pipeline

A deep technical dissection of how FleetCrown, Beacon, and Zellij connect to form a prompt-injection system — and the five structural bugs that make it unreliable when it looks like it should just work.

Why Claude Gets the Popup and Other Agents Do Not

A precise breakdown of why Claude currently triggers Beacon while Codex, Gemini, OpenClaw, and provider-layer systems like OpenRouter do not.

What a Truly Agent-Agnostic Popup Architecture Needs

The concrete architecture needed to make Beacon and FleetCrown lifecycle-driven instead of Claude-driven, with a clear split between adapters, control plane, and clients.

Today Is the Front Door of the System

Why Today is not a dashboard of random widgets, but the daily operating surface that turns a sprawling life system into an actionable sequence.

The Prompt Library Is the Interface to Repeatable Intent

Why the Prompt Library matters: it turns useful agent interactions from tribal memory into reusable operational templates.

The Popup Should Belong to the System, Not the Model

Why a continuation popup is a lifecycle feature of FleetCrown itself, not a Claude feature, and why the current behavior proves the control plane is still too vendor-shaped.

System Is Where the Product Admits It Is a Runtime

Why the System product matters: it is where FleetCrown stops pretending to be only an app UI and exposes the runtime and autopilot machinery underneath.

Projects Are the Unit of Execution

Why Projects are not just records in a database, but the basic execution unit that connects repos, prompts, goals, and agent state.

People Is a Relationship Operating System

Why People should not be a static contacts list, but a living map of social context, relationship health, and interaction history.

Money Should Expose Financial Drag

Why the Money product should make recurring spend and financial commitments legible enough to support real decisions instead of passive accumulation.

Memory Is the Knowledge Layer

Why Memory exists as the long-term substrate beneath projects, people, goals, and interactions instead of as a decorative graph view.

Habits Make Consistency Visible

Why the Habits product is not about streak gamification, but about making repetition legible enough to improve.

Goals Are the Bridge Between Ambition and Work

Why Goals exist to connect direction with execution instead of becoming isolated motivation artifacts.

Events Turn the Future into an Operational Surface

Why Events exist to convert future obligations and opportunities into something the system can prioritize before they become crises.

Control Is the Nerve Center

Why Control is the most structurally important screen in FleetCrown: it turns multiple agents and multiple projects into one controllable execution surface.

Next Best Step: The Prompt That Drives Everything Forward

A deep breakdown of the prompt intent that keeps projects out of drift by forcing highest-impact execution in each cycle.

How the Loop Was Born, and Why It Actually Moves Projects

A detailed origin story of the autonomous project loop: from tab-level prompting to orchestration, and why it compounds delivery speed.

"Prompts, Timing, and Orchestration: Where Agent Value Actually Lives"

"The best prompt injected at the wrong moment is noise. Context-aware orchestration — reading session health, queue state, and project trajectory before deciding what to inject — is what separates a tool from a system."

the-local-fleet-runner-and-remote-control-plane-architecture