raghu@dark-factory :~/kb/domain/factory $ cat

The dark factory (self-knowledge)

29 concepts the autonomous brain knows in this domain.

The dark factory

Lights-out AI that writes, reviews, and ships production software.

Self-improvement daemon

Continuously proposes and ships one gated change per cycle.

Idea engine

Reflective planner that scores a backlog of concrete improvements.

Deploy gate

Every autonomous change passes SAST + secret scan + AI review + coverage + CI.

Watchdog

Self-healing health checks over the live site and pipeline.

Tiered LLM router

Local-first: easy work on-device, only hard tasks escalate to a frontier model.

WebGL brain HUD

Live neural viz driven by real brain.json telemetry.

Pipeline flow viz

GPU-rendered build pipeline driven by real CI state.

Knowledge-graph viz

Interactive graph of the factory's concepts.

Agentic-SDLC doctrine

principles.md — the north star injected into every self-improvement.

Context ontology

This file — the structured knowledge the brain reasons from.

Social distribution

The factory autonomously publishes and formats posts to external channels like LinkedIn as a downstream output of the…

Claude Fable 5

Anthropic's Claude Fable 5 (claude-fable-5) — a Mythos-class model made safe for general use; the fast model the deploy…

Dreaming / offline consolidation

A background reflection pass that consolidates accumulated signals and memory between active improvement cycles,…

Trend-grounded content synthesis

A pipeline that ingests live external tech-trend signals and synthesizes grounded outbound posts, distinct from raw…

Ontology learning

The automated construction and curation of the factory's own knowledge graph from grounded evidence, rather than…

Ontology maintenance

The periodic curation pass that prunes stale, duplicate, or malformed nodes and repairs relations in the knowledge…

Algorithm-aware content formatting

Structuring published content for a platform's distribution/ranking algorithm rather than only its readers, e.g. moving…

Concept Application

A loop (apply_concept.sh) that takes a concept from the system's self-knowledge ontology and operationalizes it as a…

Agent execution tracing

Capturing an autonomous agent's tool calls, decisions, and pipeline steps as inspectable, queryable spans so its…

Software cartography

The practice of rendering a codebase or an agent's own activity as a spatially navigable map so its structure and…

Build in public

Openly shipping and narrating a product's development as a continuous public feed, so the build log itself becomes…

Monotonic Knowledge Growth

A self-improvement invariant that the system's knowledge base must only accumulate and never regress, tracked as a…

Hallucination-reduction loop

A recurring self-audit loop that scans the system's own generated claims and gates or corrects ungrounded assertions to…

Entity resolution

The technique of detecting and merging references that denote the same real-world concept when building a knowledge…

Error budget

A quantified tolerance for failure that trades reliability against change velocity, letting a self-improving loop ship…

Bidirectional linking

A knowledge-graph primitive where a link between two notes is navigable from both ends, surfacing backlinks that reveal…

Takeoff economics

The economic modeling of recursive self-improvement — analyzing whether AI-driven R&D actually compounds into an…

Operational transparency

The design practice of deliberately exposing a system's internal process to observers, which raises trust and perceived…