Agential-Semioverse on emsenn.net

Knowing Semioverse Specification

Mon, 09 Mar 2026 00:00:00 +0000

This specification defines conformance requirements for implementing a knowing semioverse. A knowing semioverse is an agential semioverse (already conforming to the base agential semioverse specifications) that additionally implements the four-group directory organization described in the knowing-semioverse index.

¶1. Normative scope

This specification IS normative about:

Which twelve directory types are standard cross-cutting subdirectories
What content belongs in each type
The grouping of those twelve into four functional groups

This specification IS NOT normative about:

Agent orchestration ecosystem survey (March 2026)

Sat, 07 Mar 2026 00:00:00 +0000

This text surveys the agent orchestration ecosystem as of March 2026, assessed against the requirements of the agential semioverse tech stack: a Python service that loads skills from a library, exposes them via HTTP and MCP, and enforces a library/engine boundary where all admissible operators live in the library.

¶Frameworks surveyed

¶Claude Agent SDK (Anthropic)

The SDK that powers Claude Code. Provides a conversation loop, built-in file/shell tools, automatic context compaction, session persistence, subagent spawning, and MCP extensibility. As of early 2026 it includes “agent teams” (TeammateTool) for peer-to-peer messaging between agents, removing the parent-relay bottleneck of the subagent model. Locked to Claude models. MIT license (Python SDK).

Encoding disciplinary methods for AI agents

Sat, 07 Mar 2026 00:00:00 +0000

When an agent works in a discipline directory, it needs to know not just what to do but how to reason. The methods of a discipline — what counts as evidence, how claims are validated, what forms of argument are legitimate — are among the biggest shapers of how work proceeds. This text surveys how methods are represented in knowledge management systems and what the ASR can learn from existing practice.

Per-directory agent instructions: patterns and practices

Sat, 07 Mar 2026 00:00:00 +0000

Agent instruction files — AGENTS.md, CLAUDE.md, .cursorrules, copilot-instructions.md — tell AI agents how to behave when working in a repository. Most start as a single root file. As repositories grow, the question arises: should subdirectories carry their own instructions?

This text surveys how per-directory agent instructions work across the ecosystem, what the research says about their effectiveness, and how the patterns apply to knowledge repositories (as opposed to code repositories).

Policy as code for knowledge repositories

Sat, 07 Mar 2026 00:00:00 +0000

Policy as code (PaC) is the practice of expressing governance rules as machine-readable files that tools evaluate and enforce automatically. The pattern is well-established in infrastructure engineering (cloud permissions, deployment pipelines, code linting) but has not been applied to knowledge repositories where AI agents operate under discipline-specific constraints. This text surveys the relevant patterns and identifies what a knowledge repository can borrow.

¶The decision architecture

Every PaC system separates three concerns: