Pi vs Claude Code: which do top repos set up for?
Claude Code averages higher: 68.5 for Pi and 71.9 for Claude Code, across 402 repos. Pi scores higher on 51, Claude Code on 348, 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
- Pi:
AGENTS.mdCLAUDE.mdAGENTS.override.md.agents/skills/ - Claude Code:
CLAUDE.md.claude/CLAUDE.md.claude/rules/CLAUDE.local.mdAGENTS.md.claude/AGENTS.md - Reads AGENTS.md
- Pi: Always
- Claude Code: Only when there is no CLAUDE.md
- Reads CLAUDE.md
- Pi: Yes
- Claude Code: Yes
- From its docs
- Pi: Loads the first of AGENTS.override.md, AGENTS.md and CLAUDE.md from the working directory and every directory above it, so an empty AGENTS.md hides a CLAUDE.md beside it.
- 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 | Pi | Claude Code |
|---|---|---|
| Skills (.agents/skills) | 5% | 0% |
| Reproducible dev env | 8% | 12% |
| Linter / formatter config | 11% | 8% |
| License file | 3% | 4% |
| CONTRIBUTING guide | 4% | 5% |
| CI configuration | 5% | 7% |
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 Pi than Claude Code?
- pandas-dev/pandas81.1 vs 75.7 for Claude Code
- symfony/symfony48.0 vs 43.4 for Claude Code
- risingwavelabs/risingwave83.1 vs 78.9 for Claude Code
- penpot/penpot69.7 vs 65.8 for Claude Code
- flutter/flutter56.4 vs 52.6 for Claude Code
Which repos are set up better for Claude Code than Pi?
- crystal-lang/crystal62.5 vs 54.0 for Pi
- etcd-io/etcd72.4 vs 64.0 for Pi
- jgm/pandoc70.4 vs 62.0 for Pi
- PostgREST/postgrest73.7 vs 65.3 for Pi
- simplex-chat/simplex-chat77.0 vs 68.7 for Pi
Which one leads in each language?
| Language | Repos | Pi | Claude Code |
|---|---|---|---|
| TypeScript | 83 | 73.7 | 77.0 |
| Python | 56 | 73.1 | 75.6 |
| Rust | 45 | 72.4 | 74.9 |
| Go | 40 | 72.5 | 76.7 |
| Java | 28 | 61.7 | 66.9 |
| C++ | 21 | 61.4 | 64.0 |
| JavaScript | 15 | 76.1 | 79.2 |
What if I use both?
- Write the shared instructions once, in AGENTS.md at the repo root. What to put in it.
- Pi: loads the first of AGENTS.override.md, AGENTS.md and CLAUDE.md, so an empty AGENTS.md hides a CLAUDE.md.
- 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/configuration.md (new tab) · github.com/skills.md (new tab) · github.com/resource-loader.ts (new tab) · code.claude.com/memory (new tab) · code.claude.com/skills (new tab)
Boards: best set up for Pi · 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 · Kimi Code CLI vs Claude Code · Devin vs Claude Code · Codex vs Gemini CLI