A self-improving orchestrator built from standard parts
A self-improving AI seems to demand a new model. The self-driving orchestrator (ramparte/amplifier-bundle-self-driving) manufactures the equivalent of self-awareness from external structure alone — no new model, no bespoke framework.
So where does the "self" come from? Start with what it's actually made of.
The whole orchestrator is under 3,800 tracked lines, built in a single ~5-hour day. DESIGN.md 1.1: "Not a new LLM or fine-tune… Not an Amplifier kernel modification."
If it isn't the model doing the work, what is?
Introspection isn't a dependable source of self-awareness. DESIGN.md frames metacognition "built from the outside in: not by making the model introspective, but by building external structures — state files, review loops, goal registries — that create the functional equivalent of self-awareness."
If self-awareness can't come from inside the model, it has to be built outside it. Here's the first piece.
705 LOC of pure amplifier_core primitives — every pyproject.toml declares dependencies = []. Token tracking exists because Amplifier has no built-in cumulative token count.
Survival is one axis. Quality is another — and it can't be self-graded.
Both worker and reviewer run with context_depth: none. The reviewer sees only the task spec, the claimed output, and files on disk — and is read-only, so the quality signal is honest, not self-flattery.
State, heartbeat, review — all outside the model. What happens when the process dies?
context_depth: noneallowed_write_paths: []All state is file-based JSON in self-driving-state/ — no database. An ultra-thin 220-line PID watchdog watches liveness and restarts on death, up to 3 times.
Every layer lives outside the model, in inspectable structure. Now the whole design snaps into one shape.
The Maslow-style hierarchy (L1 Survival → L5 Growth) is enforced bottom-up before any task. Each layer answers a self-awareness question with external structure — not a smarter model.
None of these needed a smarter model. Only structure you can build today.
L1–L4 are built and integration-tested (Phases 1–4). L5 "Growth" — the wisdom store and self-proposed goals — is designed but explicitly aspirational: DESIGN.md marks it Future ("This is the hard one"). The honest frontier, stated as such.
L1–L4 built • L5 designed / future
Data as of: repo state at last commit 2026-02-10 (ec31a18)
Feature status: Design + Phases 1–4 built and integration-tested; DESIGN.md header still reads "Design phase" (stale metadata). L5 Growth designed but aspirational.
Repository: ramparte/amplifier-bundle-self-driving (includes microsoft/amplifier-foundation@main)
Research performed:
git log --pretty=format:'%h | %ad | %an | %s' --date=short (8 commits, single author)git log --pretty=tformat: --numstat | awk '{a+=$1;d+=$2} END{print a,d}' (4056 added, 193 deleted)find . \( -name '*.md' -o -name '*.yaml' -o -name '*.py' -o -name '*.sh' -o -name '*.json' \) -exec wc -l {} + (3,779 total)wc -l modules/*/*/__init__.py (session-state 364, heartbeat 112, token-tracker 229)grep -A3 dependencies modules/*/pyproject.toml (all dependencies = [])grep -rn 'github.com/microsoft' bundle.md agents/ behaviors/agents/worker.md, agents/reviewer.md, DESIGN.md, scripts/watchdog.shGaps: The design cites amplifier-distro "overnight build" numbers as prior art (NOT independently verified). No end-to-end overnight session was run — runtime performance claims are unverified. L5 Growth is designed, not yet built.
Primary contributor: Sam Schillace (sole git author, 8/8 commits; DESIGN.md "Sam Schillace + Amplifier design session"). Commits carry a Co-Authored-By: Amplifier trailer.