global-workspace

J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.

Is there one workspace, or twin workspaces? Testing cross-lingual generalization of the J-space / global workspace in language models.

Consciousness Loop — the self-firing executive of an agent: wake → integrate the organs → decide → act → set its own frequency → sleep. The keystone of agent-nervous-system. Functional, not phenomenal.

An 8-layer cognitive architecture for LLMs with global workspace, active inference, metacognition, recurrent depth, and self-amendment.

Chain-of-density study of 'Verbalizable Representations Form a Global Workspace in Language Models' (Gurnee, Sofroniew, Lindsey et al. 2026, Transformer Circuits/Anthropic) - five-tier note, locator-verified. The Jacobian lens, the J-space, alignment auditing, counterfactual reflection training.

Zero-dependency Python cognitive-state engine for persistent agent memory, workspace selection, temporal context, and inspectable transitions — 446 tests.