{ "openapi": "3.0.1", "info": { "title": "AI/ML Jobs Scraper - Greenhouse, Lever, Ashby", "description": "Scrape AI, ML and data job postings from public Greenhouse, Lever and Ashby boards. Every result is validated, deduplicated and tagged AI-core vs. AI-mention, with a stable versioned schema and built-in source-change monitoring. Also callable from Claude/Cursor via the Apify MCP server.", "version": "0.1", "x-build-id": "r80UWWTabvAZh914P" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kotaro001~ai-jobs-daily/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kotaro001-ai-jobs-daily", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kotaro001~ai-jobs-daily/runs": { "post": { "operationId": "runs-sync-kotaro001-ai-jobs-daily", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kotaro001~ai-jobs-daily/run-sync": { "post": { "operationId": "run-sync-kotaro001-ai-jobs-daily", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "companies": { "title": "Companies", "type": "array", "description": "Override the seed list. Each item is either an object with name, ats (greenhouse|lever|ashby|workable) and slug, or a company domain / careers URL string (e.g. 'openai.com' or 'https://jobs.ashbyhq.com/openai'). String entries are auto-detected across Ashby, Greenhouse, Lever and Workable; an entry that cannot be resolved is reported as a clear error and skipped, and the rest of the list still runs. Leave empty to use config/companies.yaml.", "default": [] }, "max_companies": { "title": "Max companies per run", "minimum": 0, "type": "integer", "description": "Cap the number of companies (0 = no cap). Useful for cheap test runs.", "default": 0 }, "only_ai_core": { "title": "Only AI-core jobs", "type": "boolean", "description": "When true, output only jobs classified as AI-core. When false, include jobs that merely mention AI.", "default": true }, "runMode": { "title": "Run mode", "enum": [ "daily_active", "lifecycle_changes_only", "full_history_dump" ], "type": "string", "description": "What to write into the dataset. daily_active (default): today's validated jobs, each enriched with standard first_seen/last_seen. lifecycle_changes_only: only jobs first seen today plus jobs that just disappeared from their boards. full_history_dump: the full lifecycle history kept in your account (active + removed records).", "default": "daily_active" }, "aiCategoryFilter": { "title": "AI category filter", "enum": [ "all", "ai-core", "ai-mention" ], "type": "string", "description": "Server-side filter on the output rows. 'all' (default) keeps every row that passed the other filters; 'ai-core' keeps only roles that are themselves AI/ML/Data; 'ai-mention' keeps only postings that mention AI without being AI-core roles (non-core rows are fetched automatically for this mode). You are billed for the rows actually written.", "default": "all" }, "minSalaryUsd": { "title": "Minimum salary (USD)", "minimum": 0, "type": "integer", "description": "Keep only jobs whose parsed minimum annual salary (comp_min_usd) is at least this value, e.g. 150000. Jobs without a parsed salary are excluded while this filter is active. Leave empty or 0 for no salary filtering." }, "seniorityFilter": { "title": "Seniority filter", "type": "array", "description": "Keep only jobs whose detected seniority matches one of these values: intern, junior, mid, senior, staff, lead. Values outside this list are ignored; jobs with unknown (null) seniority are excluded while this filter is active. Leave empty for no seniority filtering.", "items": { "type": "string" }, "default": [] }, "compactOutputForMcp": { "title": "Compact output (MCP / agents)", "type": "boolean", "description": "When true, each row omits the long description_text field and keeps only the structured fields (plus ai_skills and salary fields) - handy for MCP / agent use with tight context windows. Row count and per-row billing stay unchanged.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }