# first-fluke/oh-my-agent

The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.

Repository: https://github.com/first-fluke/oh-my-agent
Canonical: https://ross.abutalabs.com/products/oh-my-agent
Homepage: https://firstfluke.com/oh-my-agent/
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai-agents, multi-agent, orchestrator, serena, agent-harness, oh-my-agent, agent-skills, agentic-coding, claude-code, codex, cursor, multi-agent-systems, opencode, orchestration, cli, developer-tools, llm
Last push: 2026-09-03T01:46:32+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 88, longevity 15
- inputs: {"age_days": 215, "days_push": 0, "days_rel": 0, "gap_med": 0.0, "n_releases_24m": 603}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1261, forks 146 (observed 2026-09-03T02:15:11.948289+00:00)

## What it is
oh-my-agent is a multi-agent orchestration framework for AI-powered IDEs and CLI coding tools like Claude Code, Codex, and Cursor. It decomposes work across 21 specialized agents and mechanically verifies agent output via stop-hook gates, artifact-based gate commands, independent judges, and append-only event logs, all portable in a .agents/ directory.

## Use cases
- orchestrate multiple AI coding agents in parallel
- verify that AI agents actually completed their work via artifacts
- enforce typecheck/test/lint gates before an agent session ends
- share agent configurations across Claude Code, Codex, Cursor, and other runtimes
- route tasks to specialized frontend, backend, and database agents
- audit agent decisions with an append-only event log

## When to choose
- you use AI coding assistants and want mechanical verification instead of trusting agent summaries
- you want specialized role-based agents (frontend, backend, QA) instead of one generalist
- you work across multiple AI IDEs/CLIs and need portable agent configuration
- you need parallel agent execution with coordination and memory

## When to avoid
- you don't use AI-powered coding tools or agent runtimes
- you want a simple single-agent assistant without orchestration overhead
- you need a fully managed cloud service rather than a local harness
- your project can't accommodate a .agents/ directory and hook integrations

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, developer-tools, cli, testing
- domain: developer-tools, large-language-models
- platform: cli, cross-platform, windows
- tags: multi-agent, orchestration, agent-harness, claude-code, codex, cursor, verification, stop-hooks, event-log, serena, agent-skills, portable-config, ai-agents, automation, nodejs, macos, linux

## Member repositories
- first-fluke/oh-my-agent (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:11.948289+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 2026-08-30T05:07:52.317582+00:00, confidence not recorded.
  - readme: https://github.com/first-fluke/oh-my-agent (fetched 2026-09-03T02:15:11.948289+00:00, sha fe8beace5897)
  - homepage: https://firstfluke.com/oh-my-agent/ (fetched 2026-08-29T12:19:03.102025+00:00, sha 35bf35cb522d)
  - site_page: https://firstfluke.com/oh-my-agent/docs/getting-started/introduction (fetched 2026-08-29T12:19:03.111123+00:00, sha 910bc76d9192)
  - site_page: https://firstfluke.com/oh-my-agent/docs/getting-started/installation (fetched 2026-08-29T12:19:03.114326+00:00, sha 265a2f078597)
- Data as of 2026-08-30T08:39:29.467469+00:00.