Skip to content
Agent Friendly Code

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

Claude Code averages higher: 69.2 for Kimi Code CLI and 71.9 for Claude Code, across 402 repos. Kimi Code CLI scores higher on 71, Claude Code on 331, and 0 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
Kimi Code CLI: AGENTS.md.kimi-code/AGENTS.md.agents/skills/
Claude Code: CLAUDE.md.claude/CLAUDE.md.claude/rules/CLAUDE.local.mdAGENTS.md.claude/AGENTS.md
Reads AGENTS.md
Kimi Code CLI: Always
Claude Code: Only when there is no CLAUDE.md
Reads CLAUDE.md
Kimi Code CLI: No
Claude Code: Yes
From its docs
Kimi Code CLI: /init writes an AGENTS.md. Its docs name no CLAUDE.md fallback.
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
Kimi Code CLI: AGENTS.md: 207 of 402 (51%)
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 Kimi Code CLI and Claude Code differ most
CheckKimi Code CLIClaude Code
Skills (.agents/skills)5%0%
Reproducible dev env9%12%
CI configuration5%7%
Manageable size5%7%
Test suite12%13%
AGENTS.md / CLAUDE.md13%13%

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 Kimi Code CLI than Claude Code?

Which repos are set up better for Claude Code than Kimi Code CLI?

Which one leads in each language?

Average Kimi Code CLI and Claude Code scores of the repos in each language; the higher is in bold
LanguageReposKimi Code CLIClaude Code
TypeScript8374.977.0
Python5673.275.6
Rust4572.374.9
Go4073.276.7
Java2863.766.9
C++2161.464.0
JavaScript1576.379.2

What if I use both?

  1. Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
  2. Kimi Code CLI: reads AGENTS.md; its docs name no CLAUDE.md fallback.
  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: github.com/agents.md (new tab) · github.com/slash-commands.md (new tab) · github.com/skills.md (new tab) · code.claude.com/memory (new tab) · code.claude.com/skills (new tab)

Boards: best set up for Kimi Code CLI · 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 · OpenHands vs Claude Code · Pi vs Claude Code · Devin vs Claude Code · Codex vs Gemini CLI