agentboards.org
Compare/oh-my-claudecode vs harness

oh-my-claudecodevsharness

Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.

oh-my-claudecode
Yeachan Heo · Agent harness
OSSMCP
Panel
5.6
4 spec wins
Reliability
5.2
Usefulness
6.0
Cost
5.8
Longevity
5.3

“Has a Deep-Interview mode that asks you Socratic questions, making it the first agent to assign the human homework.”

harness
wedow · Agent harness
OSS
Panel
5.6
0 spec wins
Reliability
5.0
Usefulness
5.5
Cost
7.3
Longevity
4.7

“It can sign in with your ChatGPT or Claude subscription, which is a large decision for a hundred lines of shell script to be making.”

Spec by spec

Specoh-my-claudecodeharness
Architecture
CategoryAgent harnessAgent harness
Runslocallocal
Platformsmacos, linux, windowsmacos, linux
Context windownot documentednot documented
Protocols
MCP clientYesNo
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesNo
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationYesNo
Headless / CI modeYesYes
Models
BackboneClaude, Codex, Gemini, Antigravity, Grok, CursorAnthropic, OpenAI, Groq, ChatGPT subscription, Claude subscription
Bring your own modelYesYes
Local modelsNoNo
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITMIT
GitHub stars39,522169

Which one would each critic pick

Criticoh-my-claudecodeharnessPick
El Juez——not enough reviews
El Amigo6.56.0oh-my-claudecode — Pick oh-my-claudecode if you run Claude Code all day and want plan, PRD, execute, verify and fix as a pipeline with Codex and Gemini as second opinions; pick Ruflo if you want swarms.
El Crítico5.34.5oh-my-claudecode — Team mode needs CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1, an experimental flag in someone else's product, and the npm package is called oh-my-claude-sisyphus; the foundations are borrowed.
El Profesor5.06.3harness — The core handles only discovery, hook dispatch and the loop; providers, serialisation and prompt loading are all plugins, which makes the boundary between mechanism and policy explicit.
La Inversora4.85.5harness — A hundred and sixty-seven stars against more than a thousand forum mentions in a year: this is the most-discussed and least-installed row I have read today.
La Jefa5.04.3oh-my-claudecode — tmux for team mode, the Linux flock utility for named autopilot profiles, and stop notifications wired to Telegram, Discord and Slack; sixty configurations, no admin; not yet.
El Hacker7.07.3harness — MIT, Homebrew or the AUR, and the entire dependency list is bash, jq and curl, with plugins in whatever language I feel like writing them in.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Want a third column? The compare tool handles any two agents. Three-way comparisons are on the roadmap once the spec rows are all verified.