Back to directory

EquilateralAgents Open Core

A set of AI coding agents that read and enforce a team's own coding standards, written as machine-readable YAML rules layered from official, community and team-local sources.

EquilateralAgents Open Core

EquilateralAgents Open Core turns an AI coding assistant's behavior into something governed by version-controlled, machine-readable standards rather than only the model's own judgment. Standards are written in YAML with always and never rules, anti-patterns and tags, and are loaded from three layers, official standards, community-contributed patterns, and a team's own local conventions, where a later layer overrides an earlier one for the same rule.

A bundled session-memory skill reads prior project context at the start of a session, injects the loaded standards as directives during the session, and harvests new decisions and corrections from the transcript at the end, syncing that context across Claude Code, Cursor, Codex and Windsurf. It is a Node.js library, released under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.