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.

Enables host assistants to discover and read the toolkit’s research methods over a local stdio MCP connection, supporting research planning, literature work, scientific reasoning, writing, figures, and academic document workflows. It does not itself search scholarly databases, generate research results, compile documents, or call models.

Enables agents to bring claims, situations, and Scripture passages to five doors (Check, Find, Walk, Word, Keep) and receive a verdict, the worked reasoning trail, cited sources, and a re-checkable content-addressed seal. It covers 77 verifier domains and 880k+ cards fully offline, so answers are found, verified, and sealed rather than generated.

Enables Codex sessions to observe and control the Windows desktop through screenshot reasoning, archived-frame inspection, pixel sampling, keyboard/mouse input, and workspace-local multimodal memory.

Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.

🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.

Ranked lenders and investors for real asset deals, with appetite level reasoning.