The dark factory (self-knowledge)
29 concepts the autonomous brain knows in this domain.
Lights-out AI that writes, reviews, and ships production software.
Continuously proposes and ships one gated change per cycle.
Reflective planner that scores a backlog of concrete improvements.
Every autonomous change passes SAST + secret scan + AI review + coverage + CI.
Self-healing health checks over the live site and pipeline.
Local-first: easy work on-device, only hard tasks escalate to a frontier model.
Live neural viz driven by real brain.json telemetry.
GPU-rendered build pipeline driven by real CI state.
Interactive graph of the factory's concepts.
principles.md — the north star injected into every self-improvement.
This file — the structured knowledge the brain reasons from.
The factory autonomously publishes and formats posts to external channels like LinkedIn as a downstream output of the…
Anthropic's Claude Fable 5 (claude-fable-5) — a Mythos-class model made safe for general use; the fast model the deploy…
A background reflection pass that consolidates accumulated signals and memory between active improvement cycles,…
A pipeline that ingests live external tech-trend signals and synthesizes grounded outbound posts, distinct from raw…
The automated construction and curation of the factory's own knowledge graph from grounded evidence, rather than…
The periodic curation pass that prunes stale, duplicate, or malformed nodes and repairs relations in the knowledge…
Structuring published content for a platform's distribution/ranking algorithm rather than only its readers, e.g. moving…
A loop (apply_concept.sh) that takes a concept from the system's self-knowledge ontology and operationalizes it as a…
Capturing an autonomous agent's tool calls, decisions, and pipeline steps as inspectable, queryable spans so its…
The practice of rendering a codebase or an agent's own activity as a spatially navigable map so its structure and…
Openly shipping and narrating a product's development as a continuous public feed, so the build log itself becomes…
A self-improvement invariant that the system's knowledge base must only accumulate and never regress, tracked as a…
A recurring self-audit loop that scans the system's own generated claims and gates or corrects ungrounded assertions to…
The technique of detecting and merging references that denote the same real-world concept when building a knowledge…
A quantified tolerance for failure that trades reliability against change velocity, letting a self-improving loop ship…
A knowledge-graph primitive where a link between two notes is navigable from both ends, surfacing backlinks that reveal…
The economic modeling of recursive self-improvement — analyzing whether AI-driven R&D actually compounds into an…
The design practice of deliberately exposing a system's internal process to observers, which raises trust and perceived…