Engineering documentation for a real, working reference implementation of a reflexive cognitive architecture, built in PatLang: the journey of building it, its safety and ethics requirements, and a page for each component. A weak-AI claim throughout — an analogue, not an instance. Companion to the theoretical Modelling the Self series.
The first substantive commit, M1: shared component lifecycle, instrumentation, Ollama boundary , makes an architectural choice before writing a single cognitive component: every long-running process would compose…
The theory series on this site's topics track built an argument across four pages for treating a system's own body and capabilities as one more object inside its own cognitive machinery. This page states where that…
The parallel-drafts architecture this implementation is built from carries a companion document that governs it: a set of safety and ethics requirements which take precedence over architectural convenience, performance…
Perception is the system's sensor boundary (per the requirements specification 's Section 3 component inventory). Its required input is raw text from the environment; its required output is a structured percept…
Short Term's required function, per the requirements specification's component table, is to hold "current, specific percept content." In the actual implementation that means something narrower and more mechanical: Short…
Episodic Memory's required function, per the requirements specification's component table, is to store specific past interaction instances, fed by Short Term , and to feed Imagination (for recombination) and Reason/Plan…
Procedural Memory's required function, per the requirements specification's component table, is compiled fast-response rules, fed by (trust-gated, repeated) Short Term content and by Perception , producing a direct…
Abstraction watches the same firehose of Short Term content that every other component draws on, and does one specific job with it: it induces general categories from repeated entity/intent pairs, then answers a…
The requirements spec's Section 3 is specific about what Representation is for: it holds "the current situational model, including a self-model entry." components/representation.patlang is a deliberately small piece of…
State this plainly before anything else: this component predicts what the system is about to do, in the same functional sense that a weather model predicts rain — it computes an expectation from available evidence and…
Imagination recombines Episodic Memory into hypothetical scenarios, filtered through Abstraction (Requirements Spec Sec 3; Req 4.4). It is pure PatLang with no language-model call involved (Req 4.6) — the recombination…
Reason/Plan sits between Perception and Action in the pipeline. It reads every percept published on one or more Perception writer-topics, and for each new percept publishes a candidate action to its own writer-topic…
Action is the system's other language-model boundary (Requirements Spec Section 4.6 — the first is Perception ). It reads across one or more Reason/Plan writer-topics with a claiming, ack-based read ( qh_claim_one …
orchestrator/launch.patlang is the single-command bring-up: it reads a manifest file of name : port : script : args lines, spawns every listed component as its own real OS process via lp_spawn_component , waits for each…
dashboard/dashboard_server.patlang (758 lines) is a native PatLang HTTP server, structurally the same shape as PatLang's own task_dashboard.patlang example — GET / serves an HTML+JS monitoring page, GET /data serves…
The architecture page in this series ends by turning two of its own claims into things that can be measured rather than merely argued for: how convincing a generated self-narrative is, and whether Imagination's novelty…