Commit Stats

The stats command gives you AI authorship stats for a single commit, or a sequence of linear commits.

Single Commit

Show stats for the current HEAD or a specific commit:

git ai stats
git ai stats <commit-sha>

Commit Ranges

Pass a range to aggregate stats across multiple commits:

git ai stats <start>..<end>

To compute stats for the entire repository history, use the empty tree SHA as the start:

git ai stats 4b825dc642cb6eb9a060e54bf8d69288fbee4904..HEAD

Stats are computed per-commit from git notes, so large ranges take proportionally longer. For repositories with thousands of commits, Git AI for Teams precomputes these aggregations and serves them from a dashboard.

JSON Output

Add --json to get machine-readable output:

git ai stats --json
git ai stats <commit-sha> --json
git ai stats <start>..<end> --json

Example response:

{
  "human_additions": 8,
  "unknown_additions": 4,
  "ai_additions": 81,
  "ai_accepted": 81,
  "git_diff_deleted_lines": 14,
  "git_diff_added_lines": 93,
  "tool_model_breakdown": {
    "cursor::claude-4.5-opus": {
      "ai_additions": 75,
      "ai_accepted": 75
    },
    "claude-code::claude-opus-4-5-20251101": {
      "ai_additions": 6,
      "ai_accepted": 6
    }
  }
}

Field descriptions:

Lines in the commit:

• human_additions — Added lines attributed to a human.
• unknown_additions — Added lines with no attestation at all (not attributed to AI or to a known human).
• ai_additions — Added lines attributed to AI.
• ai_accepted — AI-generated lines committed without any human edits. Currently equal to ai_additions.

git baseline:

• git_diff_added_lines — Added lines reported by the raw git diff.
• git_diff_deleted_lines — Deleted lines reported by the raw git diff.

Per-tool:

• tool_model_breakdown — Object keyed by <tool>::<model>, with ai_additions and ai_accepted scoped to that tool and model pair.

human_additions + unknown_additions + ai_additions always equals git_diff_added_lines — every added line is attributed to exactly one of the three.

Beyond Commits: Pull Requests, Cost, and Prompt Data

git ai stats operates on commit-level data stored in git notes. This covers authorship attribution and line counts — everything recorded locally during a coding session.

Some metrics require processing that goes beyond what git notes contain. Joining attributions on SCM metadata, computing per-PR metrics while handling squash merges and rebases, tracking token costs across models, and analyzing prompt effectiveness all depend on additional telemetry and server-side computation.

Git AI for Teams provides precomputed dashboards with per-PR metrics, model cost tracking, and prompt analysis. For guidance on which metrics to prioritize, see How to Measure AI Code.