Skip to content
Agent Friendly Code

OpenHands vs Claude Code: which do top repos set up for?

Claude Code averages higher: 64.5 for OpenHands and 71.9 for Claude Code, across 402 repos. OpenHands scores higher on 15, Claude Code on 384, and 3 tie.

Scores measure how well each repo is set up for an agent: instruction files, tests, CI and the other checks, weighted by what each agent's docs say it uses, not which agent writes better code.

Which files does each one read?

Reads from the repo
OpenHands: AGENTS.mdCLAUDE.md.openhands/setup.sh.agents/skills/
Claude Code: CLAUDE.md.claude/CLAUDE.md.claude/rules/CLAUDE.local.mdAGENTS.md.claude/AGENTS.md
Reads AGENTS.md
OpenHands: Always
Claude Code: Only when there is no CLAUDE.md
Reads CLAUDE.md
OpenHands: Yes
Claude Code: Yes
From its docs
OpenHands: Runs .openhands/setup.sh when it starts work on a repo. Treats CLAUDE.md and GEMINI.md as context for Claude and Gemini models.
Claude Code: Reads AGENTS.md only when no CLAUDE.md, .claude/CLAUDE.md or CLAUDE.local.md is found (v2.1.277 and later). A CLAUDE.md that imports @AGENTS.md loads both, as does a setting.
Repos with its own file
OpenHands: .openhands/setup.sh: 2 of 402 (0.5%)
Claude Code: CLAUDE.md only: 18 of 402 (4%)

AGENTS.md and CLAUDE.md mean the file at the repo root; a repo with both counts under AGENTS.md, and empty files don't count. Every agent's files.

Which checks does each weigh more?

Share of each agent's score that a check carries, where OpenHands and Claude Code differ most
CheckOpenHandsClaude Code
.openhands/setup.sh10%0%
AGENTS.md / CLAUDE.md5%13%
Test suite9%13%
Skills (.agents/skills)4%0%
CI configuration10%7%
Type configuration5%8%

Each figure is the check's share of the agent's total weight, from the docs linked below. A check few repos pass, such as an agent's own file, lowers that agent's scores wherever it carries weight. The methodology lists every weight.

Which repos are set up better for OpenHands than Claude Code?

Which repos are set up better for Claude Code than OpenHands?

Which one leads in each language?

Average OpenHands and Claude Code scores of the repos in each language; the higher is in bold
LanguageReposOpenHandsClaude Code
TypeScript8368.977.0
Python5668.675.6
Rust4566.874.9
Go4067.576.7
Java2858.966.9
C++2158.064.0
JavaScript1570.279.2

What if I use both?

  1. Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
  2. OpenHands: reads AGENTS.md and runs .openhands/setup.sh when it starts work on a repo.
  3. Claude Code: import @AGENTS.md in a CLAUDE.md; without that, a CLAUDE.md hides AGENTS.md from it.

AGENTS.md vs CLAUDE.md · Which files each agent reads · Make a repo agent-ready

From the docs: docs.openhands.dev/repository (new tab) · docs.openhands.dev/skills (new tab) · docs.openhands.dev/overview (new tab) · code.claude.com/memory (new tab) · code.claude.com/skills (new tab)

Boards: best set up for OpenHands · best set up for Claude Code

More comparisons: Claude Code vs Cursor · Claude Code vs Codex · Gemini CLI vs Claude Code · Cursor vs Codex · Aider vs Claude Code · Pi vs Claude Code · Kimi Code CLI vs Claude Code · Devin vs Claude Code · Codex vs Gemini CLI