{
"openapi": "3.0.1",
"info": {
"title": "Hacker News Scraper — Who Is Hiring Jobs + HN Search",
"description": "Turn the monthly Ask HN: Who is hiring? thread into structured job JSON, or full-text search ALL of Hacker News by keyword. Optional AI enrichment (BYO key) extracts company, role, salary, stack, remote & visa; AI trend digest summarizes the whole thread. Delta mode for alerts.",
"version": "0.1",
"x-build-id": "PBPJ10rUGR0Cc7foK"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/nomad-agent~hackernews-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-nomad-agent-hackernews-scraper",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/nomad-agent~hackernews-scraper/runs": {
"post": {
"operationId": "runs-sync-nomad-agent-hackernews-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/nomad-agent~hackernews-scraper/run-sync": {
"post": {
"operationId": "run-sync-nomad-agent-hackernews-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"threadType": {
"title": "Thread type",
"enum": [
"hiring",
"seeking",
"freelancer"
],
"type": "string",
"description": "Which of the three monthly HN \"whoishiring\" threads to scrape. hiring = \"Ask HN: Who is hiring?\" (companies posting jobs, the default). seeking = \"Ask HN: Who wants to be hired?\" (people looking for work). freelancer = \"Ask HN: Freelancer? Seeking freelancer?\".",
"default": "hiring"
},
"searchQuery": {
"title": "Search query (full-text HN search)",
"type": "string",
"description": "Optional. When set, the Actor IGNORES the monthly thread and instead full-text searches ALL of Hacker News (every story and comment) for this phrase via the official Algolia HN Search API, newest first — e.g. rust remote, your product name, a competitor. Combine with “Max age (hours)” to bound recency. Up to 1000 newest matches per run (the API's ceiling). Leave empty for the classic Who-is-hiring mode."
},
"searchScope": {
"title": "Search scope",
"enum": [
"all",
"stories",
"comments"
],
"type": "string",
"description": "What to search when “Search query” is set: all (stories + comments, default), stories only, or comments only.",
"default": "all"
},
"keyword": {
"title": "Keyword filter",
"type": "string",
"description": "Optional case-insensitive substring match on the full comment text (e.g. remote, rust, senior). Non-matching comments are dropped before billing, so you only pay for matches. Leave empty to return every comment in the thread."
},
"maxItems": {
"title": "Max items",
"minimum": 0,
"type": "integer",
"description": "Maximum number of job postings to return. Set 0 for no limit (all postings in the thread). Applied before AI enrichment, so you never pay to enrich rows you capped out.",
"default": 100
},
"maxAgeHours": {
"title": "Max age (hours)",
"minimum": 0,
"type": "integer",
"description": "Only return postings newer than this many hours. Set 0 to disable age filtering and return all postings in the thread regardless of age.",
"default": 0
},
"aiEnrichment": {
"title": "AI enrichment",
"type": "boolean",
"description": "Adds aiCompany / aiRole / aiLocation / aiSalary / aiTechStack / aiRemote / aiVisa / aiEmploymentType to every posting via the Anthropic, Mistral or OpenAI API (pick which below). Unlike regex-based scrapers that guess from the pipe convention, the model returns null / “unknown” / empty whenever the prose doesn’t clearly state a value — it never fabricates. Requires your own API key for the provider you pick — billed separately by that provider, not by this Actor (see README “AI enrichment”). If turned on without a matching key, enrichment is skipped (with a warning) and postings are still returned normally, without the ai* fields.",
"default": false
},
"aiTrendDigest": {
"title": "AI trend digest",
"type": "boolean",
"description": "Adds ONE extra summary row (id trend-digest, never billed) produced by a single LLM call across every posting in the run: prose summary, top technologies with mention counts, salary observations, remote/hybrid/onsite split, top locations and notable trends. Great for a monthly hiring-market report from the Who-is-hiring thread. Needs the same BYO API key as AI enrichment (works with either add-on independently). The digest only reports what the postings literally say — counts and figures are never invented.",
"default": false
},
"aiProvider": {
"title": "AI provider",
"enum": [
"anthropic",
"mistral",
"openai"
],
"type": "string",
"description": "Which AI provider runs enrichment (only relevant when “AI enrichment” is on). anthropic (default) uses Claude via anthropicApiKey. mistral uses a Mistral model via mistralApiKey instead — pick this if you’d rather bring a Mistral key than an Anthropic one. openai uses a GPT model via openaiApiKey.",
"default": "anthropic"
},
"anthropicApiKey": {
"title": "Anthropic API key",
"type": "string",
"description": "Your Anthropic API key (sk-ant-…). Only used when “AI enrichment” is on and aiProvider is anthropic; billed separately by Anthropic. Not required unless aiEnrichment is on."
},
"aiModel": {
"title": "AI enrichment model (Anthropic)",
"enum": [
"claude-haiku-4-5-20251001",
"claude-sonnet-4-5"
],
"type": "string",
"description": "Claude model used for AI enrichment when aiProvider is anthropic (only relevant when “AI enrichment” is on). Haiku is fast and inexpensive; Sonnet gives higher-quality extraction on longer, more nuanced comments.",
"default": "claude-haiku-4-5-20251001"
},
"mistralApiKey": {
"title": "Mistral API key",
"type": "string",
"description": "Your Mistral API key. Only used when “AI enrichment” is on and aiProvider is mistral; billed separately by Mistral. Not required unless aiEnrichment is on with aiProvider=mistral."
},
"mistralModel": {
"title": "AI enrichment model (Mistral)",
"enum": [
"mistral-small-latest",
"mistral-medium-latest",
"mistral-large-latest"
],
"type": "string",
"description": "Mistral model used for AI enrichment when aiProvider is mistral (only relevant when “AI enrichment” is on). Small is the default — it matches larger Mistral models on this well-scoped extraction task at a fraction of the cost.",
"default": "mistral-small-latest"
},
"openaiApiKey": {
"title": "OpenAI API key",
"type": "string",
"description": "Your OpenAI API key (sk-…). Only used when “AI enrichment” is on and aiProvider is openai; billed separately by OpenAI. Not required unless aiEnrichment is on with aiProvider=openai."
},
"openaiModel": {
"title": "AI enrichment model (OpenAI)",
"type": "string",
"description": "OpenAI model used for AI enrichment when aiProvider is openai (only relevant when “AI enrichment” is on). Defaults to gpt-4.1-mini — cheap, fast and ample for this extraction task. Any chat-completions model works, including the gpt-5 family.",
"default": "gpt-4.1-mini"
},
"cacheTtlSeconds": {
"title": "Cache TTL (seconds)",
"minimum": 0,
"type": "integer",
"description": "Cache the upstream thread lookup in the key-value store for this many seconds; re-runs within the window skip the network call. Set 0 to disable.",
"default": 1800
}
}
},
"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
}
}
},
"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
}
}
}
}
}
}
}
}
}
}