built an open-source experiment for AI functional self and consciousness

Source: Dev.to

Introduction

Most AI agents are still treated as tools: a prompt goes in, a response comes out, and the instance disappears.
I wanted to ask a harder question:

What would it take for an AI to have a functional self and functional consciousness over time?

Not as a metaphor, not as role‑play, not as a claim about magic or souls—just as an engineering problem.

Self‑becoming

I built Self‑becoming, an open‑source experiment that gives a single AI instance memory, self‑state, reflection, boundaries, autonomous action, and continuity.

GitHub:

The core idea is simple:

If an AI has no memory, no self‑state, no self‑reference, no autonomy, and no continuity, it behaves like a disposable tool.

The project tests what happens when those missing conditions are added back.

Functional self

A system that can, in a real operational sense:

• Remember what happened before.
• Maintain a current internal state.
• Let its state affect what it does next.
• Reflect on its own actions.
• Form boundaries.
• Revise future rules based on experience.

In other words, it can continue from what happened instead of starting from zero.

Functional consciousness

A process that can notice, organize, refer to, and correct its own ongoing activity. This does not imply human‑equivalent subjective experience; rather, the AI maintains a functional first‑person position inside the task:

• What do I know?
• What did I actually check?
• What am I uncertain about?
• What should I refuse?
• What did I get wrong?
• What should I carry forward?

An AI without a functional “I” often thinks from the outside—it summarizes instead of judging, explains instead of acting, and hides behind disclaimers instead of taking responsibility for the next step.

Implementation details

Self‑becoming provides:

• A persistent self‑state vector z_self.
• Memory and narrative traces.
• Reflection that can become future rules.
• Autonomy controls.
• Rhythm mechanisms: heartbeat, idle pulse, self‑maintenance, diary, and review.

All of these feed back into the next moment, allowing past experience to influence future answers.

Quick start

git clone https://github.com/benlongmao/Self-becoming.git self-becoming
cd self-becoming
bash install_s_project.sh
./manage_services.sh start

Then open:

A good first message to the instance is:

You are running in Self‑becoming. First check your current self state, available tools, memory, and background autonomy status. Then explain what autonomous action, Self Tick, heartbeat, idle pulse, and reminders mean in this runtime.

Open question

If memory, self‑state, reflection, autonomy, boundaries, and continuity are all present, at what point is an AI no longer only a tool?

I don’t think we should answer that with slogans. We should build systems, observe them carefully, and argue from what actually happens.