Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

oh-my-claudecode

Multi-agent orchestration layer for Claude Code with opt-in Jev hooks for fast judgment points, decision caching and egress controls.

PluginproductionMIT
View on GitHub ↗

Overview

oh-my-claudecode (OMC) is a popular multi-agent orchestration layer for Claude Code that aims for zero learning curve: you keep using Claude Code while OMC coordinates teams of agents and workflows. A sibling project, oh-my-codex, offers the same for Codex. It is MIT licensed and documented in several languages.

According to the list summary, OMC includes opt-in Jev hooks for fast judgment points inside the orchestration, with decision caching and per-point egress controls so you can choose what is sent to TypeSafe. The fetched README excerpt does not describe these hooks, so the specific decision points are inferred. It suits Claude Code users who want orchestration with cheaper, faster routine judgments.

What the decision model decides

TypeQuestionAnswers
OtherRoutine judgment points in the orchestration loop (details not in README excerpt)(inferred)—

How it works

  1. Install OMC alongside Claude Code.
  2. Opt in to Jev hooks for selected judgment points.
  3. Cache decisions and restrict egress per point.
  4. Orchestration acts on the decisions.

Strengths

  • Opt-in, so existing behaviour is unchanged by default.
  • Decision caching and per-point egress controls (per list summary).

Caveats

  • Jev integration is documented only in the list summary, not the README excerpt.
  • Large orchestration framework if you only want decisions.

Getting started

Install the oh-my-claude-sisyphus npm package and follow the Quick Start in the documentation.

At a glance

Type
Plugin
Status
production
Language
TypeScript
Runtime
Claude Code plugin
Has code
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • Coding agents: multi-agent team orchestration for Claude Code featuring opt-in Jev hooks for sub-millisecond judgment points, decision caching, and per-point egress controls.

    yibie/awesome-jev

Frequently asked questions

Is Jev required?

No, the Jev hooks are opt-in per the list summary.

Can I control what is sent to TypeSafe?

The list summary mentions per-point egress controls.

Is there a Codex version?

Yes, oh-my-codex offers the same orchestration for Codex.

Related projects

  • jev-opus

    Runs Claude Code on Opus 5.5 with Jev re-picking reasoning effort after every tool batch, via per-message effort so the cache survives.

    ProxybetaTypeScript
  • openclaw-jev-trigger

    OpenClaw plugin and CLI that turn a plain-language condition into a scheduled trigger, waking the model only when Jev says it is true.

    PluginbetaTypeScript
  • dsh-teacher-consult

    DeepSeek Harness plugin for budgeted, read-only GPT 'teacher' consults; Jev may only suggest when a consult is worthwhile.

    ProjectprototypeJavaScript
  • spendbrake

    Tiny demo that asks Jev whether an agent should continue, downgrade its model, or stop, given budget and plan.

    DemoprototypeTypeScript
  • wakegate

    Gate that asks Jev whether a timer or event is worth resuming a sleeping agent's LLM, skipping only when confidently not.

    BenchmarkprototypeTypeScript
  • decision-gate

    npm library that rate-limits, spend-caps, caches and redacts every Jev request made in a loop.

    LibrarybetaJavaScript