Andy Dixon
703d080d13
Phase 10. Metacognition is a cognitive process with deterministic self-checks (insufficient evidence, single-source reliance, model output without evidence, repeated failed hypotheses, stale contradictions, calibration overconfidence); its warnings compete for attention and, when admitted, add counter-evidence or open an investigation goal. Reflection reviews the period since the last run (prediction errors, rejected beliefs, corrections, status changes, completed goals, contradictions, calibration), turns repeated failures into procedural lessons written once, and records a reflection event; a model may only word the prose within the mind's budget. Consolidation clusters unconsolidated episodes by shared stemmed terms, creates a belief whose confidence is computed from the episodes as evidence and a semantic memory linked to each episode by derived_from, and records jobs with inputs and outputs. Wording may come from the consolidate prompt within a per-run model budget; the job says which. Operators can run, pause and reject; originals are never touched. The narrative hook keeps a five-part first-person narrative built from state and stored with narrative_updated events. The notification hook applies explicit thresholded rules, aggregates repeats within a cooldown and records suppressions with reasons. A scheduled job runs consolidation and reflection per mind, switching the runtime mode while it works. API, Background tab, notifications page with unread badge, overview narrative and warnings, CLI commands, docs/cognition.md.
Noema
Noema is a persistent, inspectable artificial cognitive runtime.
It is an always-running daemon that hosts one or more minds: cognitive entities with their own identity, personality, memories, beliefs, goals, drives, affective state and history. Minds perceive events, compete internally for attention through a global workspace, retrieve and consolidate memories, form and revise beliefs with explicit evidence, make predictions and learn from prediction error, and act only through a policy-governed capability layer. Everything of consequence is recorded as an immutable cognitive event, so an operator can always ask why.
Language models are used by Noema as cognitive service providers for language understanding, concept extraction, hypothesis generation and narrative. They are not the mind. A mind keeps its identity, memories, beliefs and configuration when the underlying model provider changes.
What Noema is not
Noema does not claim consciousness, sentience, self-awareness or personhood. It simulates mechanisms associated with cognition so that they can be studied and used. Behaviour that resembles emotion, curiosity, preference or identity is a property of the model being run and must not be read as evidence of subjective experience. See docs/interpretation.md.
Noema is also not a chatbot with a memory bolted on. A user message does not go straight to an LLM. It becomes an observation, is perceived, triggers memory retrieval, competes in the workspace, is reasoned about, produces a response intent grounded in stored beliefs and uncertainty, and only then is turned into language.
Architecture overview
┌───────────────────────────── noemad ─────────────────────────────┐
stimuli ───▶ │ perception ─▶ cognitive events (append-only) ─▶ per-mind runtime │
(chat,files, │ │ │
metrics, │ cognitive processes (bounded pool) ◀──┘ │
git, hooks) │ retrieval · association · curiosity · prediction · contradiction│
│ goal monitor · metacognition · reflection · dreaming │
│ │ thought candidates │
│ ▼ │
│ attention scoring (deterministic, inspectable) ─▶ workspace │
│ │ broadcast │
│ ▼ │
│ executive: beliefs · goals · predictions · narrative · response │
│ │ actions │
│ ▼ │
│ capability + policy layer (ALLOW / ASK / DENY) ─▶ tools │
│ │
│ LLM providers · embeddings · PostgreSQL (+pgvector) · metrics │
└───────────────────────────────────────────────────────────────────┘
▲ HTTP API · SSE · web UI · noemactl
Full description: ARCHITECTURE.md. Decisions: docs/adr. Plan and status: PLAN.md.
Quick start
Requirements: Go 1.26+, Docker with Compose, make.
cp .env.example .env
# set NOEMA_MASTER_KEY (openssl rand -base64 32) and NOEMA_BOOTSTRAP_ADMIN_PASSWORD
make dev
This starts PostgreSQL (with pgvector) in a container, applies migrations, and runs noemad on http://127.0.0.1:8080. Log in with the bootstrap administrator, add an LLM provider under LLM and assign models to the perceive and respond roles, create a mind (or load the sample mind Dani with noemactl mind import configs/minds/dani.json after creating an API token under Account), and open its Conversation tab. Without a model the mind still answers, rendering its state directly.
Configuration
Precedence: built-in defaults → JSON config file (noemad -config path) → environment variables (NOEMA_*) → runtime settings stored in the database and edited in the UI. Secrets come only from environment variables, secret files, or encrypted references; they are never included in exports or rendered back to HTML. See docs/configuration.md.
Development
make tools # staticcheck, gosec, govulncheck
make test-race # unit tests
make test-db # tests that need PostgreSQL
make lint security
See CONTRIBUTING.md and docs/ENVIRONMENT.md.
Security warning
Noema ingests untrusted data (documents, web pages, logs, repositories, model output) and can be granted capabilities that touch real systems. Read SECURITY.md and THREAT_MODEL.md before connecting it to anything you care about. Defaults are restrictive: every action capability starts as ASK or DENY, dreaming can never act, and shutdown is always under operator control.
Cognitive concepts
| Concept | Meaning in Noema |
|---|---|
| Cognitive event | Immutable, typed record of anything that happened inside a mind, with provenance links |
| Epistemic kind | observation, fact, memory, claim, hypothesis, belief, prediction, assumption, inference, opinion. Never collapsed |
| Global workspace | Small, capacity-limited set of currently broadcast thoughts, selected by deterministic attention scoring |
| Working memory | Short-lived, decaying set of active items feeding every cognitive process |
| Memory systems | episodic, semantic, procedural, autobiographical; decay changes accessibility, never deletes |
| Belief | Proposition with confidence, status, evidence for/against, alternatives and version history |
| Prediction | Explicit expectation with window and criteria; resolution produces prediction-error events that recalibrate confidence |
| Drives and affect | Configurable scalar state that biases attention and style; inspectable and resettable |
| Self-model | What the mind can, cannot, and is currently doing; prevents false capability claims |
| Metacognition | Processes that audit the mind's own reasoning and emit warnings |
| Replay | Re-running a recorded cognitive sequence, labelled exact or approximate |
CLI examples
noemactl status
noemactl mind list
noemactl mind create dani
noemactl ask dani "why was atlas slow yesterday?"
noemactl belief list --mind dani
noemactl event inspect <id>
noemactl replay <event-id>
noemactl provider test openai-main
noemactl approvals list
noemactl snapshot create dani
noemactl fork dani --snapshot <id> --name dani-test
Status
Milestone M1 is complete: start, log in, create a mind, shape its personality, configure a model, chat, watch cognitive events live, inspect working memory, the workspace, memories, beliefs and provenance, restart, and continue the same mind. go test ./tests/m1/ exercises that slice end to end. Phases 9–16 (goals, drives, predictions, metacognition, reflection, consolidation, relationship graph, capabilities, integrations, dreaming, snapshots, replay, experiments, hardening) are in progress; see PLAN.md and CHANGELOG.md. Screenshots will be added once the UI stabilises.
Licence
TBD by the project owner.