《Cursor Docs》-AI Code Tracking API

The AI Code Tracking API lets you track AI-generated code contributions across your team’s repositories, including per-commit AI usage and granular accepted AI changes.

• The AI Code Tracking API uses Basic Authentication with your API key as the username, the same method as the Admin API.
• For details on creating API keys, authentication methods, rate limits, and best practices, see the API Overview.
• Availability: Enterprise only, contact sales to get access
• Status: Alpha (response shapes and fields may change)
• Workspace limitation: Metrics are only calculated for the git repository at the top level of the workspace root. Multi-root workspaces are not currently supported.

Endpoints¶

Get AI Commit Metrics (JSON, paginated)¶

/analytics/ai-code/commits

Retrieve aggregated per-commit metrics that attribute lines to TAB, COMPOSER, and non-AI.

Parameters¶

startDate string | date

ISO date string, the literal “now”, or relative days like “7d” (means now - 7 days). Default: now - 7 days

endDate string | date

ISO date string, the literal “now”, or relative days like “0d”. Default: now

page number

Page number (1-based). Default: 1

pageSize number

Results per page. Default: 100, Max: 1000

user string

Optional filter by a single user. Accepts email (e.g., developer@company.com), encoded ID (e.g., user_abc123…), or numeric ID (e.g., 42)

Response Fields¶

curl -X GET "https://api.cursor.com/analytics/ai-code/commits?startDate=7d&endDate=now&page=1&pageSize=100" \
  -u YOUR_API_KEY:

Response:

{
  "items": [
    {
      "commitHash": "a1b2c3d4",
      "userId": "user_3k9x8q...",
      "userEmail": "developer@company.com",
      "repoName": "company/repo",
      "branchName": "main",
      "isPrimaryBranch": true,
      "commitSource": "ide",
      "totalLinesAdded": 120,
      "totalLinesDeleted": 30,
      "tabLinesAdded": 50,
      "tabLinesDeleted": 10,
      "composerLinesAdded": 40,
      "composerLinesDeleted": 5,
      "nonAiLinesAdded": 30,
      "nonAiLinesDeleted": 15,
      "message": "Refactor: extract analytics client",
      "commitTs": "2025-07-30T14:12:03.000Z",
      "createdAt": "2025-07-30T14:12:30.000Z"
    }
  ],
  "totalCount": 42,
  "page": 1,
  "pageSize": 100
}

Download AI Commit Metrics (CSV, streaming)¶

/analytics/ai-code/commits.csv

Download commit metrics data in CSV format for large data extractions.

Parameters¶

startDate string | date

ISO date string, the literal “now”, or relative days like “7d” (means now - 7 days). Default: now - 7 days

endDate string | date

ISO date string, the literal “now”, or relative days like “0d”. Default: now

user string

Optional filter by a single user. Accepts email (e.g., developer@company.com), encoded ID (e.g., user_abc123…), or numeric ID (e.g., 42)

Response Headers¶

• Content-Type: text/csv; charset=utf-8

CSV Columns¶

curl -L "https://api.cursor.com/analytics/ai-code/commits.csv?startDate=2025-07-01T00:00:00Z&endDate=now&user=user_3k9x8q..." \
  -u YOUR_API_KEY: \
  -o commits.csv

Sample CSV Output:

commit_hash,commit_source,user_id,user_email,repo_name,branch_name,is_primary_branch,total_lines_added,total_lines_deleted,tab_lines_added,tab_lines_deleted,composer_lines_added,composer_lines_deleted,non_ai_lines_added,non_ai_lines_deleted,message,commit_ts,created_at
a1b2c3d4,ide,user_3k9x8q...,developer@company.com,company/repo,main,true,120,30,50,10,40,5,30,15,"Refactor: extract analytics client",2025-07-30T14:12:03.000Z,2025-07-30T14:12:30.000Z
e5f6g7h8,cloud,user_3k9x8q...,developer@company.com,company/repo,feature-branch,false,85,15,30,5,25,3,30,7,"Add error handling",2025-07-30T13:45:21.000Z,2025-07-30T13:45:45.000Z

Get AI Code Change Metrics (JSON, paginated)¶

/analytics/ai-code/changes

Retrieve granular accepted AI changes, grouped by deterministic changeId. Useful to analyze accepted AI events independent of commits.

Parameters¶

startDate string | date

ISO date string, the literal “now”, or relative days like “7d” (means now - 7 days). Default: now - 7 days

endDate string | date

ISO date string, the literal “now”, or relative days like “0d”. Default: now

page number

Page number (1-based). Default: 1

pageSize number

Results per page. Default: 100, Max: 1000

user string

Optional filter by a single user. Accepts email (e.g., developer@company.com), encoded ID (e.g., user_abc123…), or numeric ID (e.g., 42)

Response Fields¶

curl -X GET "https://api.cursor.com/analytics/ai-code/changes?startDate=14d&endDate=now&page=1&pageSize=200" \
  -u YOUR_API_KEY:

Response:

{
  "items": [
    {
      "changeId": "749356201",
      "userId": "user_3k9x8q...",
      "userEmail": "developer@company.com",
      "source": "COMPOSER",
      "model": null,
      "totalLinesAdded": 18,
      "totalLinesDeleted": 4,
      "createdAt": "2025-07-30T15:10:12.000Z",
      "metadata": [
        {
          "fileName": "src/analytics/report.ts",
          "fileExtension": "ts",
          "linesAdded": 12,
          "linesDeleted": 3
        },
        {
          "fileName": "src/analytics/ui.tsx",
          "fileExtension": "tsx",
          "linesAdded": 6,
          "linesDeleted": 1
        }
      ]
    }
  ],
  "totalCount": 128,
  "page": 1,
  "pageSize": 200
}

Download AI Code Change Metrics (CSV, streaming)¶

/analytics/ai-code/changes.csv

Download change metrics data in CSV format for large data extractions.

Parameters¶

startDate string | date

ISO date string, the literal “now”, or relative days like “7d” (means now - 7 days). Default: now - 7 days

endDate string | date

ISO date string, the literal “now”, or relative days like “0d”. Default: now

user string

Optional filter by a single user. Accepts email (e.g., developer@company.com), encoded ID (e.g., user_abc123…), or numeric ID (e.g., 42)

Response Headers¶

• Content-Type: text/csv; charset=utf-8

CSV Columns¶

curl -L "https://api.cursor.com/analytics/ai-code/changes.csv?startDate=30d&endDate=now" \
  -u YOUR_API_KEY: \
  -o changes.csv

Sample CSV Output:

change_id,user_id,user_email,source,model,total_lines_added,total_lines_deleted,created_at,metadata_json
749356201,user_3k9x8q...,developer@company.com,COMPOSER,gpt-4o,18,4,2025-07-30T15:10:12.000Z,"[{""fileName"":""src/analytics/report.ts"",""fileExtension"":""ts"",""linesAdded"":12,""linesDeleted"":3},{""fileName"":""src/analytics/ui.tsx"",""fileExtension"":""tsx"",""linesAdded"":6,""linesDeleted"":1}]"
749356202,user_3k9x8q...,developer@company.com,TAB,,8,2,2025-07-30T15:08:45.000Z,"[{""fileName"":""src/utils/helpers.ts"",""fileExtension"":""ts"",""linesAdded"":8,""linesDeleted"":2}]"

Get Commit Details¶

/analytics/ai-code/commits/:commitHash

Retrieve detailed information for one or more commits, including blame annotations and referenced conversation metadata.

This endpoint is in limited alpha and only available to select users. Response shapes may change.

Path Parameters¶

commitHash string

Single commit hash or comma-separated list of hashes (e.g., abc123,def456)

Query Parameters¶

branch string

Optional filter by branch name

Response Fields¶

Returns an object containing commits and conversations arrays.

Response format is consistent even when requesting a single commit.

Single commit:

curl -X GET "https://api.cursor.com/analytics/ai-code/commits/0aabf603dc906e05bf5e4d9fd423fdd517f2e43f?branch=main" \
  -u YOUR_API_KEY:

Multiple commits:

curl -X GET "https://api.cursor.com/analytics/ai-code/commits/abc123,def456,ghi789" \
  -u YOUR_API_KEY:

Response:

{
  "commits": [
    {
      "commitHash": "0aabf603dc906e05bf5e4d9fd423fdd517f2e43f",
      "commitSource": "ide",
      "rangeAnnotations": [
        {
          "filePath": "src/analytics/report.ts",
          "groups": [
            {
              "conversationId": "conv_abc123",
              "model": "gpt-4o",
              "operationType": "insert",
              "ranges": [
                { "start": 10, "end": 25 },
                { "start": 42, "end": 58 }
              ]
            }
          ]
        }
      ]
    }
  ],
  "conversations": [
    {
      "id": "conv_abc123",
      "title": "Refactor analytics module",
      "tldr": "Extracted report generation into separate functions",
      "overview": "Refactored the analytics module to improve maintainability by extracting report generation logic.",
      "summaryBullets": [
        "Created dedicated report generator class",
        "Added unit tests for new functions",
        "Updated imports across affected files"
      ]
    }
  ]
}

Common Query Parameters¶

All endpoints accept the same query parameters via query string:

Responses return userId as an encoded external ID with the prefix user_. This
is stable for API consumption.

Semantics and How Metrics Are Computed¶

• Sources: “TAB” represents inline completions that were accepted; “COMPOSER” represents accepted diffs from Agent edits
• Lines metrics: tabLinesAdded/Deleted and composerLinesAdded/Deleted are separately counted; nonAiLinesAdded/Deleted are derived as max(0, totalLines - AI lines)
• Privacy mode: If enabled in the client, some metadata (like fileName) may be omitted
• Branch info: isPrimaryBranch is true when the current branch equals the repo’s default branch; may be undefined if repo info is unavailable

You can scan that file to understand how commits and changes are detected and reported.

Tips¶

• Use user parameter to quickly filter a single user across all endpoints
• For large data extractions, prefer CSV endpoints—they stream in pages of 10,000 records server-side
• isPrimaryBranch may be undefined if the client couldn’t resolve the default branch
• commitTs is the commit timestamp; createdAt is the ingestion time on our servers
• Some fields may be absent when privacy mode is enabled on the client
• Commit hashes are not unique or unchangeable. For example, you may see the same commit twice if you amend commits with extra information.
• Commit timestamps will remain unchanged even if the commit is amended.

Changelog¶

• Alpha release: Initial endpoints for commits and changes. Response shapes may evolve based on feedback

AI Code Tracking is available on the Enterprise plan¶

Contact our team to get access to detailed AI usage metrics.