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.

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Systematically clarify intent, challenge assumptions, resolve contradictions, and align goals, constraints, risks, and success criteria.

Desktop app for DeepSeek Harness with a live energy/carbon console: measure local GPU inference, estimate cloud APIs via published coefficients, alert on waste