AGENTS.md vs GEMINI.md vs .cursorrules
Every comparison page on the web is a capability table someone wrote from the vendor docs in an afternoon. None of them can tell you how many real repositories ship each file, how long the median one runs, or how often two of them turn up in the same project. Those answers need a corpus, and RuleStack counts one every night.
| Format | AGENTS.md 2026-08-02 | GEMINI.md 2026-08-01 | .cursorrules 2026-08-02 |
|---|---|---|---|
| Asserted — what the docs say it can express | |||
| File | AGENTS.md | GEMINI.md | .cursorrules |
| Status | open-standard | vendor | deprecated |
| Cross-tool | Yes | No | No |
| Tools that read it |
|
|
|
| Frontmatter | No | No | No |
| Glob targeting | No | No | No |
| Imports other files | No | Yes | No |
| Nested / per-directory | Yes | Yes | No |
| Multiple files | Yes | Yes | No |
| User-level scope | No | Yes | No |
| When it applies | Always in scope; in a monorepo the nearest AGENTS.md to the edited file wins. | Hierarchical memory: a global ~/.gemini/GEMINI.md, then the project file, then nested files, concatenated from broadest to narrowest. | Always in scope, single file at the repo root. |
| Size limits | None | None | None |
| Measured — counted from real repositories on 2026-08-04 | |||
| Repositories carrying it | 399 | 33 | 27 |
| Share of indexed repos | 57.2% | 4.7% | 3.9% |
| Files indexed | 1,373 | 46 | 308 |
| Median length (words) | 953 | 257 | 366 |
| 90th percentile length | 2,956 | 1,704 | 1,104 |
| Files naming commands | 42.8% | 52.2% | 13.6% |
| Files containing code | 36.0% | 45.6% | 25.0% |
| Median quality score | 52 | 60 | 41 |
| Median repository stars | 9,402 | 11,320 | 26 |
How often they turn up together
A capability table cannot answer this at all. Of the repositories carrying the first format, this is the share that also carry the second — counted, both directions, on 2026-08-04.
.cursorrules + GEMINI.md
2026-08-044
repositories carry both. That is 14.8% of everything with .cursorrules, and 12.1% of everything with GEMINI.md.
AGENTS.md + GEMINI.md
2026-08-0423
repositories carry both. That is 5.8% of everything with AGENTS.md, and 69.7% of everything with GEMINI.md.
AGENTS.md + .cursorrules
2026-08-0410
repositories carry both. That is 2.5% of everything with AGENTS.md, and 37.0% of everything with .cursorrules.
What each one is for
AGENTS.md
2026-08-02A plain-markdown README for coding agents, deliberately unopinionated: no frontmatter, no globs, no vendor keys. That minimalism is why it became the one file a dozen different agents will read, and why it carries the least per-file targeting power of any format here.
Strengths
- Read by more agents than any other format — one file covers most of a team's tooling
- No schema to get wrong; a plain markdown file always parses
- Nested files let a monorepo scope instructions per package
Weaknesses
- No glob targeting — every rule is loaded for every file, spending context
- No imports, so shared rules must be duplicated across packages
- No frontmatter means no machine-readable metadata for tooling to act on
GEMINI.md
2026-08-01Gemini CLI's memory file, structurally close to CLAUDE.md — @imports and a user-scope layer — which is why repos that carry both usually carry near-identical text in each.
Strengths
- @path imports and a global user file, same composition model as CLAUDE.md
- Explicit hierarchy from global to local
Weaknesses
- Google-only
- No glob targeting
.cursorrules
2026-08-02Cursor's original single-file format, superseded by .cursor/rules/*.mdc. Tracked here precisely because it is dead: how much of the ecosystem is still shipping a deprecated file is a measurable answer, and a large share of the "best cursor rules" pages on the web still teach this format.
Strengths
- One file, nothing to configure
Weaknesses
- Deprecated — do not start here
- No targeting, no composition, no metadata
