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:
/initwrites an AGENTS.md. Its docs name no CLAUDE.md fallback. - Claude Code: Reads AGENTS.md only when no CLAUDE.md,
.claude/CLAUDE.mdor CLAUDE.local.md is found (v2.1.277 and later). A CLAUDE.md that imports@AGENTS.mdloads both, as does a setting.
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?
| Check | Kimi Code CLI | Claude Code |
|---|---|---|
| Skills (.agents/skills) | 5% | 0% |
| Reproducible dev env | 9% | 12% |
| CI configuration | 5% | 7% |
| Manageable size | 5% | 7% |
| Test suite | 12% | 13% |
| AGENTS.md / CLAUDE.md | 13% | 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?
- symfony/symfony47.7 vs 43.4 for Claude Code
- risingwavelabs/risingwave82.8 vs 78.9 for Claude Code
- penpot/penpot69.5 vs 65.8 for Claude Code
- Significant-Gravitas/AutoGPT57.5 vs 53.9 for Claude Code
- flutter/flutter56.1 vs 52.6 for Claude Code
Which repos are set up better for Claude Code than Kimi Code CLI?
- PostgREST/postgrest73.7 vs 68.0 for Kimi Code CLI
- junegunn/fzf76.3 vs 70.7 for Kimi Code CLI
- guzzle/guzzle81.6 vs 76.0 for Kimi Code CLI
- unclecode/crawl4ai72.4 vs 66.9 for Kimi Code CLI
- psf/requests86.8 vs 81.3 for Kimi Code CLI
Which one leads in each language?
| Language | Repos | Kimi Code CLI | Claude Code |
|---|---|---|---|
| TypeScript | 83 | 74.9 | 77.0 |
| Python | 56 | 73.2 | 75.6 |
| Rust | 45 | 72.3 | 74.9 |
| Go | 40 | 73.2 | 76.7 |
| Java | 28 | 63.7 | 66.9 |
| C++ | 21 | 61.4 | 64.0 |
| JavaScript | 15 | 76.3 | 79.2 |
What if I use both?
- Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
- Kimi Code CLI: reads AGENTS.md; its docs name no CLAUDE.md fallback.
- Claude Code: import
@AGENTS.mdin 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