# oh-my-openagent (OmO)

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

Repository: https://github.com/code-yeongyu/oh-my-openagent
Canonical: https://ross.abutalabs.com/products/oh-my-openagent-omo
Homepage: https://omo.dev
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: opencode, ai, anthropic, claude, claude-skills, cursor, gemini, ide, openai, orchestration, tui, typescript, ai-agents, chatgpt, codex
Last push: 2026-08-26T18:05:25+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 19
- inputs: {"age_days": 274, "days_push": 7, "days_rel": 9, "gap_med": 0.0, "n_releases_24m": 243}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 68406, forks 5597 (observed 2026-08-28T04:12:20.888736+00:00)

## What it is
oh-my-openagent (OmO) is a TypeScript-based agent harness and orchestration layer for coding agents like OpenCode and Codex, designed for working in complex codebases. Its companion distribution LazyCodex provides a one-command install of the OmO setup for OpenAI's Codex.

## Use cases
- set up a coding agent harness for complex codebases
- orchestrate multiple AI coding agents in team mode
- install a preconfigured Codex coding agent with one command
- reduce token usage when running AI coding agents
- customize OpenCode with skills and agent configurations
- run coding agents across multiple harnesses like OpenCode and Codex

## When to choose
- you use OpenCode or Codex and want a battle-tested agent harness with opinionated configs
- you work in large complex codebases and need orchestrated multi-agent coding workflows
- you want a quick one-command setup via npx lazycodex-ai install

## When to avoid
- you need a permissively licensed dependency (license is listed as NOASSERTION)
- you want a simple single-agent setup without opinionated orchestration
- you use a coding agent harness not yet supported by the multi-harness refactor

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, cli, developer-tools, workflow-automation
- domain: developer-tools, large-language-models
- platform: cli, cross-platform
- tags: coding-agent, opencode, codex, agent-harness, orchestration, tui, claude-skills, token-optimization, ai-agents, command-line, nodejs

## Member repositories
- code-yeongyu/oh-my-openagent (main) score 79
- code-yeongyu/lazycodex (mirror) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:20.888736+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:16:23.644888+00:00, confidence not recorded.
  - readme: https://github.com/code-yeongyu/oh-my-openagent (fetched 2026-08-28T04:12:20.888736+00:00, sha 09222b957ad2)
- Data as of 2026-08-30T08:39:29.467469+00:00.