← Home All Case Files ▦
SCROLL 000%
HARNESS: SELF-BUILT
01Home 02Case Files 03About 04Skills 05Contact Resume Hire Me ↗
// CASE FILE 03 — CODENAME: CHAOS WORKS — CODING AGENT · SELF-SCAFFOLDING

CODE THAT CONJURES ITSELF, ORNITH 1.0.

A desktop coding-agent harness (Next.js + Electron, React + TypeScript) for the self-scaffolding ornith:9b model on local Ollama — each session binds its own pluggable Python agent harness that plans tasks and streams native tool-calls: file edits, reads, shell runs. Like Wanda's constructs: the scaffolding appears exactly when the work demands it.

Inspired By
Wanda
Role
Creator
Model
ornith:9b · Local
Tool-Calls
Native
PlanScaffoldTool-CallCritiqueInspectShip PlanScaffoldTool-CallCritiqueInspectShip
FILE 01 — THE MISSION

A HARNESS FOR A MODEL THAT BUILDS ITS OWN

Coding agents usually get one hard-coded harness and like it. Ornith 1.0 inverts that: built for the self-scaffolding ornith:9b model running on local Ollama, every session binds its own pluggable Python agent harness — the scaffolding is part of the experiment, not a constant.

The model plans tasks and streams native tool-calls — file edits, reads, shell runs — while the desktop app makes every step visible: an Inspector / Thinking / Critiques workspace surfaces the agent's ReAct reasoning and an L2–L7 critic ledger for every response. Chaos, fully observed.

"The best harness is the one the session conjures for itself."

  • FILE SNAPSHOT
  • Model — self-scaffolding ornith:9b, local Ollama
  • Harnesses — pluggable Python, per session
  • Tool-calls — native: edits, reads, shell runs
  • Critics — L2–L7 ledger on every response
  • Desktop — Next.js + Electron, React + TS
  • Tested — full Playwright e2e suite
FILE 02 — THE RITUAL

FROM EMPTY SESSION TO RUNNING AGENT

01

Bind a Harness

Each session picks from the harness registry (load / unload) — a pluggable Python agent harness that defines how this agent will work.

02

Plan the Task

The self-scaffolding ornith:9b model plans the work — running entirely on local Ollama, no cloud dependency.

03

Stream Native Tool-Calls

File edits, reads, and shell runs stream live as native tool-calls — you watch the code change as the agent reasons.

04

Face the Critics

An L2–L7 critic ledger attaches to every response — layered verdicts on the agent's output before you trust it.

05

Inspect Everything

The Inspector / Thinking / Critiques workspace lays out ReAct reasoning, tool activity, and critic verdicts side by side — with session and folder organisation keeping long projects sane.

FILE 03 — CORE SYSTEMS

CHAOS MAGIC, FULLY OBSERVED

🔮

Self-Scaffolding Model

ornith:9b on Local Ollama

A model that constructs its own working scaffolding — the harness binds per session instead of being welded to the app.

ornith:9bOllama
🧩

Harness Registry

Pluggable Python · Load / Unload

Swap agent harnesses like spell books — each session binds the Python harness it needs, and the registry manages the collection.

Pluggable HarnessesPer-Session
🛠️

Native Tool-Calls

Edits · Reads · Shell Runs

No brittle text-parsing — the model emits native tool-calls that stream into the workspace as they execute.

ReActStreaming
🕵️

Inspector Workspace

Thinking · Critiques · L2–L7 Ledger

Reasoning, tool activity, and a seven-layer critic ledger per response — the whole session is glass-walled.

Critic LedgerObservability
🖥️

Desktop-Grade App

Next.js + Electron · React + TS

Session and folder organisation for real projects — a coding agent that lives where the code lives.

Next.jsElectron
🎭

Playwright E2E Suite

The Harness Is Itself Tested

A full end-to-end test suite covers the app — because a tool for judging agents should survive judgment itself.

PlaywrightE2E
6
Critic Layers (L2–L7) per Response
100%
Local Model Inference
9B
Params in the Self-Scaffolding Model
END OF FILE

MISSION LOGGED. RETURN TO BASE.