diff --git a/agent-quickstart/elixir.mdx b/agent-quickstart/elixir.mdx
new file mode 100644
index 00000000..c56c8fff
--- /dev/null
+++ b/agent-quickstart/elixir.mdx
@@ -0,0 +1,190 @@
+---
+title: "Elixir Agent Quickstart"
+description: "Canonical Firecrawl Elixir quickstart for external agents using search, scrape, and interact."
+---
+
+Canonical Firecrawl Elixir quickstart for agents. Generated from SDK source (`firecrawl` **v1.9.1**, `firecrawl/apps/elixir-sdk`) and the v2 OpenAPI spec.
+
+## Install
+
+Add to `mix.exs`:
+
+```elixir
+{:firecrawl, "~> 1.9"}
+```
+
+## Authenticate
+
+```elixir
+# config/runtime.exs or config.exs
+config :firecrawl, api_key: System.get_env("FIRECRAWL_API_KEY")
+
+# or pass api_key per call
+{:ok, res} = Firecrawl.search_and_scrape(
+  [query: "site:docs.firecrawl.dev webhook retries"],
+  api_key: "fc-your-api-key"
+)
+```
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or post-scrape browser actions.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+`Firecrawl.search_and_scrape(params \\ [], opts \\ [])`
+
+### Example
+
+```elixir
+{:ok, res} = Firecrawl.search_and_scrape(
+  query: "site:docs.firecrawl.dev webhook retries",
+  sources: [:web, :news],
+  limit: 10,
+  scrape_options: [
+    formats: ["markdown"],
+    only_main_content: true
+  ]
+)
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `query` | string (required) | You need a search query. Use `site:example.com` to scope. |
+| `sources` | list of atoms or strings | You want to control sources. Values: `:web`, `:news`, `:images`. Default: `[:web]`. |
+| `categories` | list of atoms, strings, or maps | You want to filter by category. Values: `:github`, `:research`, `:pdf`. |
+| `include_domains` | list of strings | You want results only from specific domains. |
+| `exclude_domains` | list of strings | You want to exclude specific domains. |
+| `limit` | integer | You want to cap results. |
+| `tbs` | string | You need a time filter (e.g. `qdr:d`, `qdr:w`). |
+| `location` | string | You want localized results. |
+| `country` | string | You want ISO 3166-1 alpha-2 targeting (e.g. `"US"`). |
+| `ignore_invalid_urls` | boolean | You want to drop URLs that cannot be scraped. |
+| `timeout` | integer | You need a request timeout in milliseconds. |
+| `highlights` | boolean | You want query-relevant highlights. Default: `true`. |
+| `scrape_options` | keyword list | You want to scrape each search result inline. |
+| `enterprise` | list of strings | You need enterprise controls. Values: `"zdr"`, `"anon"`. |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+`Firecrawl.scrape_and_extract_from_url(params \\ [], opts \\ [])`
+
+### Example
+
+```elixir
+{:ok, res} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://example.com/pricing",
+  formats: [
+    "markdown",
+    "links",
+    %{type: "json", prompt: "Extract plan names and prices."}
+  ],
+  only_main_content: true,
+  wait_for: 1000
+)
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `url` | string (required) | You want to scrape a specific page. |
+| `formats` | list of strings or maps | You want multiple output formats. See format types below. |
+| `headers` | map | You need custom request headers. |
+| `include_tags` | list of strings | You want to include only specific HTML tags. |
+| `exclude_tags` | list of strings | You want to exclude specific HTML tags. |
+| `only_main_content` | boolean | You want to strip nav, footer, and boilerplate. |
+| `timeout` | integer | You need a timeout in milliseconds. Default: `60000`. Min: `1000`. Max: `300000`. |
+| `wait_for` | integer | You need to wait for page render (milliseconds). |
+| `mobile` | boolean | You want a mobile viewport. |
+| `parsers` | list of strings or maps | You need file parsing controls. |
+| `actions` | list of maps | You need pre-scrape browser actions. |
+| `location` | keyword list | You need geo or language-aware scraping. |
+| `skip_tls_verification` | boolean | You need to skip TLS verification. |
+| `remove_base64_images` | boolean | You want to drop base64 images from markdown. |
+| `block_ads` | boolean | You want ad and cookie popup blocking. |
+| `proxy` | atom | You need proxy control. Values: `:basic`, `:enhanced`, `:auto`. |
+| `max_age` | integer | You want cached data up to a maximum age (ms). Default: 2 days. |
+| `min_age` | integer | You want cached data only if at least this old (ms). |
+| `store_in_cache` | boolean | You want Firecrawl to cache the result. |
+| `lockdown` | boolean | You want only cached results, no outbound requests. |
+| `redact_pii` | boolean | You want PII redacted from content. |
+| `audit_metadata` | keyword list | You need user attribution for SIEM. Key: `username` (required). |
+| `profile` | keyword list | You want a persistent browser profile. Keys: `name`, `save_changes`. |
+| `zero_data_retention` | boolean | You want zero data retention for this scrape. |
+
+**Format strings:** `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"changeTracking"`, `"json"`, `"branding"`, `"audio"`, `"video"`
+
+**Format maps:** `%{type: "json", prompt: ...}`, `%{type: "screenshot", fullPage: true}`, `%{type: "changeTracking", modes: ["git-diff"]}`
+
+**Action types:** `wait`, `click`, `write`, `press`, `scroll`, `screenshot`, `scrape`, `executeJavascript`, `pdf`
+
+## Interact
+
+### Why use it
+
+Use interact when a page requires browser actions or code execution after a scrape starts. The Elixir SDK exposes **code-based interactions only** (no `prompt` parameter).
+
+### Preferred SDK method
+
+`Firecrawl.interact_with_scrape_browser_session(job_id, params \\ [], opts \\ [])`
+
+### Example
+
+```elixir
+{:ok, scrape_res} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://example.com",
+  formats: ["markdown"]
+)
+
+job_id = get_in(scrape_res.body, ["data", "metadata", "scrapeId"])
+
+{:ok, res} = Firecrawl.interact_with_scrape_browser_session(
+  job_id,
+  code: "console.log(await page.title());",
+  language: :node,
+  timeout: 60
+)
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `job_id` | string | You have a scrape job ID. |
+| `code` | string (required) | You want to run code in the browser session. |
+| `language` | atom or string | You need a specific runtime. Values: `:python`, `:node`, `:bash`. |
+| `timeout` | integer | You need an execution timeout in seconds. |
+
+### Stop session
+
+`Firecrawl.stop_interactive_scrape_browser_session(job_id)` → ends the browser session. A bang variant `stop_interactive_scrape_browser_session!/2` is also available.
+
+## Notes
+
+- The Elixir client is OpenAPI-shaped; function names and parameter keys are generated from the spec.
+- Each public function has a bang (`!`) variant that raises on error instead of returning `{:error, _}`.
+- This SDK exposes code-based interactions only (no `prompt` parameter on `interact_with_scrape_browser_session`).
+- Pass `api_key:` in `opts` to override the configured key per call.
+
+## Source Of Truth
+
+- `firecrawl/apps/elixir-sdk/mix.exs`
+- `firecrawl/apps/elixir-sdk/lib/firecrawl.ex`
+- `firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/java.mdx b/agent-quickstart/java.mdx
new file mode 100644
index 00000000..8d4de5b7
--- /dev/null
+++ b/agent-quickstart/java.mdx
@@ -0,0 +1,214 @@
+---
+title: "Java Agent Quickstart"
+description: "Canonical Firecrawl Java quickstart for external agents using search, scrape, and interact."
+---
+
+Canonical Firecrawl Java quickstart for agents. Generated from SDK source (`firecrawl-java` **v1.12.1**, `firecrawl/apps/java-sdk`) and the v2 OpenAPI spec.
+
+## Install
+
+Maven:
+
+```xml
+<dependency>
+  <groupId>com.firecrawl</groupId>
+  <artifactId>firecrawl-java</artifactId>
+  <version>1.12.1</version>
+</dependency>
+```
+
+Gradle:
+
+```gradle
+implementation("com.firecrawl:firecrawl-java:1.12.1")
+```
+
+## Authenticate
+
+```java
+import com.firecrawl.client.FirecrawlClient;
+
+FirecrawlClient client = FirecrawlClient.builder()
+    .apiKey(System.getenv("FIRECRAWL_API_KEY"))
+    .build();
+```
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or post-scrape browser actions.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+- `client.search(query)` → `SearchData`
+- `client.search(query, options)` → `SearchData`
+
+### Example
+
+```java
+import com.firecrawl.models.SearchOptions;
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.SearchData;
+
+SearchOptions options = SearchOptions.builder()
+    .sources(List.of("web", "news"))
+    .limit(10)
+    .scrapeOptions(
+        ScrapeOptions.builder()
+            .formats(List.of("markdown"))
+            .onlyMainContent(true)
+            .build()
+    )
+    .build();
+
+SearchData results = client.search("site:docs.firecrawl.dev webhook retries", options);
+List<Map<String, Object>> web = results.getWeb();
+```
+
+**Return value:** `SearchData` with `getWeb()`, `getNews()`, `getImages()` (each is `List<Map<String, Object>>`, may be null).
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `query` | String | You need a search query. Use `site:example.com` to scope. |
+| `options.sources` | `List<Object>` | You want to control sources. Values: `"web"`, `"news"`, `"images"`. |
+| `options.categories` | `List<Object>` | You want to filter by category. Values: `"github"`, `"research"`, `"pdf"`. |
+| `options.includeDomains` | `List<String>` | You want results only from specific domains. |
+| `options.excludeDomains` | `List<String>` | You want to exclude specific domains. |
+| `options.limit` | Integer | You want to cap results. |
+| `options.tbs` | String | You need a time filter (e.g. `qdr:d`, `qdr:w`). |
+| `options.location` | String | You want localized results. |
+| `options.ignoreInvalidURLs` | Boolean | You want to drop URLs that cannot be scraped. |
+| `options.timeout` | Integer | You need a request timeout in milliseconds. |
+| `options.highlights` | Boolean | You want query-relevant highlights. Default: `true`. |
+| `options.scrapeOptions` | `ScrapeOptions` | You want to scrape each search result inline. |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+- `client.scrape(url)` → `Document`
+- `client.scrape(url, options)` → `Document`
+
+### Example
+
+```java
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.JsonFormat;
+import com.firecrawl.models.Document;
+
+ScrapeOptions options = ScrapeOptions.builder()
+    .formats(List.of(
+        "markdown",
+        "links",
+        JsonFormat.builder().prompt("Extract plan names and prices.").build()
+    ))
+    .onlyMainContent(true)
+    .waitFor(1000)
+    .build();
+
+Document doc = client.scrape("https://example.com/pricing", options);
+System.out.println(doc.getMarkdown());
+System.out.println(doc.getJson());
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `url` | String | You want to scrape a specific page. |
+| `options.formats` | `List<Object>` | You want multiple output formats. Strings or format objects. |
+| `options.headers` | `Map<String, String>` | You need custom request headers. |
+| `options.includeTags` | `List<String>` | You want to include only specific HTML tags. |
+| `options.excludeTags` | `List<String>` | You want to exclude specific HTML tags. |
+| `options.onlyMainContent` | Boolean | You want to strip nav, footer, and boilerplate. |
+| `options.timeout` | Integer | You need a timeout in milliseconds. |
+| `options.waitFor` | Integer | You need to wait for page render (milliseconds). |
+| `options.mobile` | Boolean | You want a mobile viewport. |
+| `options.parsers` | `List<Object>` | You need file parsing controls. |
+| `options.actions` | `List<Map<String, Object>>` | You need pre-scrape browser actions. |
+| `options.location` | `LocationConfig` | You need geo or language-aware scraping. |
+| `options.skipTlsVerification` | Boolean | You need to skip TLS verification. |
+| `options.removeBase64Images` | Boolean | You want to drop base64 images from markdown. |
+| `options.blockAds` | Boolean | You want ad and cookie popup blocking. |
+| `options.proxy` | String | You need proxy control. Values: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`. |
+| `options.maxAge` | Long | You want cached data up to a maximum age (ms). |
+| `options.storeInCache` | Boolean | You want Firecrawl to cache the result. |
+| `options.lockdown` | Boolean | You want only cached results, no outbound requests. |
+| `options.redactPII` | Boolean | You want PII redacted from content. |
+| `options.auditMetadata` | `AuditMetadata` | You need user attribution for SIEM. |
+
+**Format strings:** `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"changeTracking"`, `"json"`, `"attributes"`, `"branding"`, `"audio"`, `"video"`
+
+**Format objects:** `JsonFormat` (prompt, schema), `QuestionFormat` (question), `HighlightsFormat` (query)
+
+**Action types:** `wait`, `click`, `write`, `press`, `scroll`, `screenshot`, `scrape`, `executeJavascript`, `pdf`
+
+## Interact
+
+### Why use it
+
+Use interact when a page requires browser actions or code execution after a scrape starts. The Java SDK exposes **code-based interactions only** (no `prompt` parameter).
+
+### Preferred SDK method
+
+- `client.interact(jobId, code)` — default language `"node"`
+- `client.interact(jobId, code, language, timeout)` — timeout in seconds (1–300)
+
+### Example
+
+```java
+import com.firecrawl.models.BrowserExecuteResponse;
+
+Document doc = client.scrape("https://example.com",
+    ScrapeOptions.builder().formats(List.of("markdown")).build());
+String jobId = (String) doc.getMetadata().get("scrapeId");
+
+BrowserExecuteResponse result = client.interact(
+    jobId,
+    "console.log(await page.title());",
+    "node",
+    60
+);
+System.out.println(result.getStdout());
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `jobId` | String | You have a scrape job ID. |
+| `code` | String | You want to run code in the browser session. |
+| `language` | String | You need a specific runtime. Values: `"python"`, `"node"`, `"bash"`. Default: `"node"`. |
+| `timeout` | Integer | You need an execution timeout in seconds (1–300). Null uses API default (30s). |
+
+### Stop session
+
+`client.stopInteractiveBrowser(jobId)` → ends the browser session. Returns `BrowserDeleteResponse` with `isSuccess()`, optional `getSessionDurationMs()`, `getCreditsBilled()`, `getError()`.
+
+## Notes
+
+- Deprecated aliases: `scrapeExecute` → `interact`; `deleteScrapeBrowser` → `stopInteractiveBrowser`.
+- The Java SDK exposes code-based interactions only — no `prompt` parameter on `interact` (unlike JS/Python/Rust).
+- All methods have `Async` variants returning `CompletableFuture`.
+
+## Source Of Truth
+
+- `firecrawl/apps/java-sdk/build.gradle.kts`
+- `firecrawl/apps/java-sdk/src/main/java/com/firecrawl/client/FirecrawlClient.java`
+- `firecrawl/apps/java-sdk/src/main/java/com/firecrawl/models/ScrapeOptions.java`
+- `firecrawl/apps/java-sdk/src/main/java/com/firecrawl/models/SearchOptions.java`
+- `firecrawl/apps/java-sdk/src/main/java/com/firecrawl/models/SearchData.java`
+- `firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/node.mdx b/agent-quickstart/node.mdx
new file mode 100644
index 00000000..7a760439
--- /dev/null
+++ b/agent-quickstart/node.mdx
@@ -0,0 +1,229 @@
+---
+title: "Node.js Agent Quickstart"
+description: "Canonical Firecrawl Node.js quickstart for external agents using search, scrape, and interact."
+---
+
+Canonical Firecrawl Node.js quickstart for agents. Generated from SDK source (`firecrawl` **v4.32.2**, `firecrawl/apps/js-sdk/firecrawl`) and the v2 OpenAPI spec. Method names, parameters, and types match the SDK public API.
+
+## Install
+
+```bash
+npm install firecrawl
+```
+
+## Authenticate
+
+```ts
+import { Firecrawl } from "firecrawl";
+
+const client = new Firecrawl({
+  apiKey: process.env.FIRECRAWL_API_KEY,
+  // apiUrl: "https://api.firecrawl.dev" // optional; falls back to FIRECRAWL_API_URL or cloud default
+});
+```
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or other browser actions after a scrape has created a session.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+`client.search(query, options?)` → `Promise<SearchData>`
+
+### Example
+
+```ts
+const results = await client.search("site:docs.firecrawl.dev webhook retries", {
+  sources: ["web", "news"],
+  limit: 10,
+  scrapeOptions: {
+    formats: ["markdown"],
+    onlyMainContent: true,
+  },
+});
+
+for (const item of results.web ?? []) {
+  console.log(item.url, item.title);
+}
+```
+
+**Return value:** `SearchData` has optional arrays `web`, `news`, `images`, `developer`. Do **not** access `result.data` — results are grouped by source bucket.
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `query` | string | You need a search query. Use `site:example.com` to scope. |
+| `options.sources` | `("web" \| "news" \| "images")[]` | You want to control which sources are searched. |
+| `options.categories` | `("github" \| "research" \| "pdf" \| "developer")[]` | You want to filter by category. |
+| `options.includeDomains` | `string[]` | You want results only from specific domains. |
+| `options.excludeDomains` | `string[]` | You want to exclude specific domains. |
+| `options.limit` | number | You want to cap results. |
+| `options.tbs` | string | You need a time filter (e.g. `qdr:d`, `qdr:w`, `sbd:1,qdr:m`). |
+| `options.location` | string | You want localized results. |
+| `options.ignoreInvalidURLs` | boolean | You want to drop URLs that cannot be scraped. |
+| `options.timeout` | number | You need a request timeout in milliseconds. |
+| `options.highlights` | boolean | You want query-relevant highlights in results. |
+| `options.scrapeOptions` | `ScrapeOptions` | You want to scrape each search result inline. |
+| `options.enterprise` | `("default" \| "anon" \| "zdr")[]` | You need enterprise zero-data-retention controls. |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+`client.scrape(url, options?)` → `Promise<Document>`
+
+### Example
+
+```ts
+const doc = await client.scrape("https://example.com/pricing", {
+  formats: [
+    "markdown",
+    "links",
+    { type: "json", prompt: "Extract plan names and prices." },
+  ],
+  onlyMainContent: true,
+  waitFor: 1000,
+});
+
+console.log(doc.markdown);
+console.log(doc.json);
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `url` | string | You want to scrape a specific page. |
+| `options.formats` | `FormatOption[]` | You want multiple output formats. See format types below. |
+| `options.headers` | `Record<string, string>` | You need custom request headers. |
+| `options.includeTags` | `string[]` | You want to include only specific HTML tags. |
+| `options.excludeTags` | `string[]` | You want to exclude specific HTML tags. |
+| `options.onlyMainContent` | boolean | You want to strip nav, footer, and boilerplate. |
+| `options.timeout` | number | You need a timeout in milliseconds. |
+| `options.waitFor` | number | You need to wait for page render (milliseconds). |
+| `options.mobile` | boolean | You want a mobile viewport. |
+| `options.parsers` | `(string \| PdfParser)[]` | You need file parsing controls (e.g. PDF). |
+| `options.actions` | `ActionOption[]` | You need pre-scrape browser actions. |
+| `options.location` | `{ country, languages }` | You need geo or language-aware scraping. |
+| `options.skipTlsVerification` | boolean | You need to skip TLS verification. |
+| `options.removeBase64Images` | boolean | You want to drop base64 images from markdown. |
+| `options.fastMode` | boolean | You want faster scrapes with reduced fidelity. |
+| `options.blockAds` | boolean | You want ad and cookie popup blocking. |
+| `options.proxy` | `"basic" \| "stealth" \| "enhanced" \| "auto"` | You need proxy control. |
+| `options.maxAge` | number | You want cached data up to a maximum age (ms). |
+| `options.minAge` | number | You want cached data only if at least this old (ms). |
+| `options.storeInCache` | boolean | You want Firecrawl to cache the result. |
+| `options.lockdown` | boolean | You want only cached results, no outbound requests. |
+| `options.redactPII` | `boolean \| RedactPIIOptions` | You want PII redacted from content. |
+| `options.profile` | `{ name, saveChanges? }` | You want a persistent browser profile. |
+
+**Format types:**
+
+| String format | Description |
+|---|---|
+| `"markdown"` | Markdown content |
+| `"html"` | Cleaned HTML |
+| `"rawHtml"` | Raw HTML |
+| `"links"` | Page links |
+| `"images"` | Image URLs |
+| `"screenshot"` | Screenshot output |
+| `"summary"` | Summary output |
+| `"changeTracking"` | Change tracking output |
+| `"attributes"` | Attribute extraction |
+| `"branding"` | Branding profile |
+| `"product"` | Product data extraction |
+| `"menu"` | Menu extraction |
+| `"audio"` | Audio extraction |
+| `"video"` | Video extraction |
+
+**Object-only formats** (require `{ type: ... }`):
+
+| Format object | Key fields |
+|---|---|
+| `{ type: "json", prompt?, schema? }` | At least one of `prompt` or `schema` required. SDK rejects plain `"json"` string. |
+| `{ type: "question", question }` | Question-answer extraction. |
+| `{ type: "highlights", query }` | Relevant source-text extraction. |
+| `{ type: "screenshot", fullPage?, quality?, viewport? }` | Screenshot with options. |
+| `{ type: "changeTracking", modes, schema?, prompt?, tag? }` | `modes` (`"git-diff"` / `"json"`) required. |
+| `{ type: "attributes", selectors }` | `selectors` is `[{ selector, attribute }]`. |
+
+**Action types** (for `options.actions`):
+
+| Action | Required fields |
+|---|---|
+| `wait` | `milliseconds` or `selector` |
+| `click` | `selector` |
+| `write` | `text` (click to focus input first) |
+| `press` | `key` |
+| `scroll` | `direction` (`up` / `down`) |
+| `screenshot` | none (all fields optional) |
+| `scrape` | none |
+| `executeJavascript` | `script` |
+| `pdf` | none (all fields optional) |
+
+## Interact
+
+### Why use it
+
+Use `interact` for code or natural-language control of the browser session tied to a scrape job. The SDK requires at least one of `code` or `prompt`.
+
+### Preferred SDK method
+
+`client.interact(jobId, args)` → `Promise<ScrapeExecuteResponse>`
+
+### Example
+
+```ts
+const doc = await client.scrape("https://example.com", { formats: ["markdown"] });
+const jobId = doc.metadata?.scrapeId;
+if (!jobId) throw new Error("Missing scrapeId");
+
+const result = await client.interact(jobId, {
+  prompt: "Click the pricing tab and summarize the plans.",
+});
+console.log(result.output);
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `jobId` | string | You have a scrape job ID from `document.metadata.scrapeId`. |
+| `args.code` | string | You want to run code in the browser session. |
+| `args.prompt` | string | You want the browser agent to follow a natural-language instruction. |
+| `args.language` | `"python" \| "node" \| "bash"` | You need a specific runtime. Default: `"node"`. |
+| `args.timeout` | number | You need an execution timeout in seconds. |
+
+At least one of `args.code` or `args.prompt` must be non-empty.
+
+### Stop session
+
+`client.stopInteraction(jobId)` → ends the browser session. Returns `{ success, sessionDurationMs?, creditsBilled?, error? }`.
+
+## Notes
+
+- Deprecated aliases: `scrapeExecute` → `interact`; `stopInteractiveBrowser` / `deleteScrapeBrowser` → `stopInteraction`.
+- The default `Firecrawl` export is the v2 client; v1 remains under `client.v1`.
+- Zod schemas passed to `formats` (for `json` or `changeTracking`) are converted to JSON Schema by the SDK.
+- The package declares **Node.js >= 22** in `engines`.
+
+## Source Of Truth
+
+- `firecrawl/apps/js-sdk/firecrawl/package.json`
+- `firecrawl/apps/js-sdk/firecrawl/src/index.ts`
+- `firecrawl/apps/js-sdk/firecrawl/src/v2/client.ts`
+- `firecrawl/apps/js-sdk/firecrawl/src/v2/types.ts`
+- `firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/python.mdx b/agent-quickstart/python.mdx
new file mode 100644
index 00000000..8d37a0ba
--- /dev/null
+++ b/agent-quickstart/python.mdx
@@ -0,0 +1,231 @@
+---
+title: "Python Agent Quickstart"
+description: "Canonical Firecrawl Python quickstart for external agents using search, scrape, and interact."
+---
+
+Canonical Firecrawl Python quickstart for agents. Generated from SDK source (`firecrawl-py` **v4.35.1**, `firecrawl/apps/python-sdk`) and the v2 OpenAPI spec. Method names, parameters, and return types match the v2 client.
+
+## Install
+
+```bash
+pip install firecrawl-py
+```
+
+## Authenticate
+
+```py
+import os
+from firecrawl import Firecrawl
+
+client = Firecrawl(api_key=os.environ.get("FIRECRAWL_API_KEY"))
+# client = Firecrawl(api_key="fc-...", api_url="https://api.firecrawl.dev")
+```
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or post-scrape browser actions.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+`client.search(query, **options)` → `SearchData`
+
+### Example
+
+```py
+results = client.search(
+    "site:docs.firecrawl.dev webhook retries",
+    sources=["web", "news"],
+    limit=10,
+    scrape_options=ScrapeOptions(
+        formats=["markdown"],
+        only_main_content=True,
+    ),
+)
+
+for item in results.web or []:
+    print(getattr(item, "url", None), getattr(item, "title", None))
+```
+
+**Return value:** `SearchData` has optional lists `web`, `news`, `images`, `developer`. Do **not** access `result.data` — results are grouped by source bucket.
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `query` | str | You need a search query. Use `site:example.com` to scope. |
+| `sources` | list of str or `Source` objects | You want to control which sources are searched. Values: `"web"`, `"news"`, `"images"`. |
+| `categories` | list of str or `Category` objects | You want to filter by category. Values: `"github"`, `"research"`, `"pdf"`. |
+| `include_domains` | list of str | You want results only from specific domains. |
+| `exclude_domains` | list of str | You want to exclude specific domains. |
+| `limit` | int | You want to cap results. Default: `5`. |
+| `tbs` | str | You need a time filter (e.g. `qdr:d`, `qdr:w`). |
+| `location` | str | You want localized results. |
+| `ignore_invalid_urls` | bool | You want to drop URLs that cannot be scraped. |
+| `timeout` | int | You need a request timeout in milliseconds. Default: `300000`. |
+| `highlights` | bool | You want query-relevant highlights in results. |
+| `scrape_options` | `ScrapeOptions` | You want to scrape each search result inline. |
+| `enterprise` | list of str | You need enterprise zero-data-retention controls. Values: `"anon"`, `"zdr"`. |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+`client.scrape(url, **options)` → `Document`
+
+### Example
+
+```py
+doc = client.scrape(
+    "https://example.com/pricing",
+    formats=[
+        "markdown",
+        "links",
+        {"type": "json", "prompt": "Extract plan names and prices."},
+    ],
+    only_main_content=True,
+    wait_for=1000,
+)
+
+print(doc.markdown)
+print(doc.json)
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `url` | str | You want to scrape a specific page. |
+| `formats` | list of format strings or objects | You want multiple output formats. See format types below. |
+| `headers` | dict of str to str | You need custom request headers. |
+| `include_tags` | list of str | You want to include only specific HTML tags. |
+| `exclude_tags` | list of str | You want to exclude specific HTML tags. |
+| `only_main_content` | bool | You want to strip nav, footer, and boilerplate. |
+| `timeout` | int | You need a timeout in milliseconds. |
+| `wait_for` | int | You need to wait for page render (milliseconds). |
+| `mobile` | bool | You want a mobile viewport. |
+| `parsers` | list of str or `PDFParser` | You need file parsing controls (e.g. PDF). |
+| `actions` | list of action objects | You need pre-scrape browser actions. |
+| `location` | `Location` or dict | You need geo or language-aware scraping. |
+| `skip_tls_verification` | bool | You need to skip TLS verification. |
+| `remove_base64_images` | bool | You want to drop base64 images from markdown. |
+| `fast_mode` | bool | You want faster scrapes with reduced fidelity. |
+| `block_ads` | bool | You want ad and cookie popup blocking. |
+| `proxy` | str | You need proxy control. Values: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`. |
+| `max_age` | int | You want cached data up to a maximum age (ms). |
+| `store_in_cache` | bool | You want Firecrawl to cache the result. |
+| `lockdown` | bool | You want only cached results, no outbound requests. |
+| `redact_pii` | `bool \| RedactPIIOptions` | You want PII redacted from content. (Alias: `redactPII`) |
+| `audit_metadata` | `AuditMetadata` | You need user attribution for SIEM. (Alias: `auditMetadata`) |
+| `profile` | dict with `name` and optional `save_changes` | You want a persistent browser profile. |
+
+**Format types:**
+
+| String format | Description |
+|---|---|
+| `"markdown"` | Markdown content |
+| `"html"` | Cleaned HTML |
+| `"rawHtml"` or `"raw_html"` | Raw HTML |
+| `"links"` | Page links |
+| `"images"` | Image URLs |
+| `"screenshot"` | Screenshot output |
+| `"summary"` | Summary output |
+| `"changeTracking"` or `"change_tracking"` | Change tracking output |
+| `"attributes"` | Attribute extraction |
+| `"branding"` | Branding profile |
+| `"product"` | Product data extraction |
+| `"menu"` | Menu extraction |
+| `"audio"` | Audio extraction |
+| `"video"` | Video extraction |
+
+**Object-only formats** (require `{"type": ...}`):
+
+| Format object | Key fields |
+|---|---|
+| `{"type": "json", "prompt": ..., "schema": ...}` | At least one of `prompt` or `schema`. Do not use plain `"json"` string. |
+| `{"type": "question", "question": ...}` | Question-answer extraction. |
+| `{"type": "highlights", "query": ...}` | Relevant source-text extraction. |
+| `{"type": "screenshot", "full_page": ..., "quality": ..., "viewport": ...}` | Screenshot with options. |
+| `{"type": "changeTracking", "modes": [...], "schema": ..., "tag": ...}` | `modes` (`"git-diff"` / `"json"`) required. |
+| `{"type": "attributes", "selectors": [...]}` | `selectors` is `[{"selector": ..., "attribute": ...}]`. |
+
+**Action types** (for `actions`):
+
+| Action | Required fields |
+|---|---|
+| `wait` | `milliseconds` or `selector` |
+| `click` | `selector` |
+| `write` | `text` (click to focus input first) |
+| `press` | `key` |
+| `scroll` | `direction` (`up` / `down`) |
+| `screenshot` | none (all fields optional) |
+| `scrape` | none |
+| `executeJavascript` | `script` |
+| `pdf` | none (all fields optional) |
+
+## Interact
+
+### Why use it
+
+Use `interact` when a page requires browser actions or code execution after a scrape starts. Either `code` or `prompt` must be provided.
+
+### Preferred SDK method
+
+`client.interact(job_id, code=None, *, prompt=None, language="node", timeout=None)`
+
+`prompt` is keyword-only.
+
+### Example
+
+```py
+doc = client.scrape("https://example.com", formats=["markdown"])
+job_id = doc.metadata.scrape_id if doc.metadata else None
+if not job_id:
+    raise RuntimeError("Missing scrape_id")
+
+result = client.interact(job_id, prompt="Click the pricing tab and summarize the plans.")
+print(result.output)
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `job_id` | str | You have a scrape job ID from `document.metadata.scrape_id`. |
+| `code` | str | You want to run code in the browser session. |
+| `prompt` | str (keyword-only) | You want the browser agent to follow a natural-language instruction. |
+| `language` | str | You need a specific runtime. Values: `"python"`, `"node"`, `"bash"`. Default: `"node"`. |
+| `timeout` | int | You need an execution timeout in seconds. |
+
+At least one of `code` or `prompt` must be non-empty.
+
+### Stop session
+
+`client.stop_interaction(job_id)` → ends the browser session. Returns `BrowserDeleteResponse` with `success`, optional `session_duration_ms`, `credits_billed`, `error`.
+
+## Notes
+
+- Deprecated aliases: `scrape_execute` → `interact`; `stop_interactive_browser` / `delete_scrape_browser` → `stop_interaction`.
+- The top-level `Firecrawl` client exposes v2 methods directly; v1 remains under `client.v1`.
+- `AsyncFirecrawl` provides async versions of all methods.
+- Python SDK uses `snake_case` parameter names; the SDK handles camelCase conversion for the API.
+
+## Source Of Truth
+
+- `firecrawl/apps/python-sdk/pyproject.toml`
+- `firecrawl/apps/python-sdk/firecrawl/__init__.py`
+- `firecrawl/apps/python-sdk/firecrawl/client.py`
+- `firecrawl/apps/python-sdk/firecrawl/v2/client.py`
+- `firecrawl/apps/python-sdk/firecrawl/v2/types.py`
+- `firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/rust.mdx b/agent-quickstart/rust.mdx
new file mode 100644
index 00000000..27b58f15
--- /dev/null
+++ b/agent-quickstart/rust.mdx
@@ -0,0 +1,232 @@
+---
+title: "Rust Agent Quickstart"
+description: "Canonical Firecrawl Rust quickstart for external agents using search, scrape, and interact."
+---
+
+Canonical Firecrawl Rust quickstart for agents. Generated from SDK source (`firecrawl` **v2.12.1**, `firecrawl/apps/rust-sdk`) and the v2 OpenAPI spec.
+
+## Install
+
+```bash
+cargo add firecrawl
+```
+
+## Authenticate
+
+```rust
+use firecrawl::Client;
+
+let client = Client::new("fc-your-api-key")?;
+// Self-hosted:
+// let client = Client::new_selfhosted("http://localhost:3002", Some("fc-your-api-key"))?;
+```
+
+## When To Use What
+
+- `search`: use when you start with a query and need discovery.
+- `scrape`: use when you already have a URL and want page content.
+- `interact`: use when the page needs clicks, forms, or post-scrape browser actions.
+
+## Search
+
+### Why use it
+
+Use search to discover relevant pages from a query, then pick URLs to scrape or interact with. Constrain results to a site with `site:`, for example `site:docs.firecrawl.dev crawl webhooks`.
+
+### Preferred SDK method
+
+`client.search(query, options)` → `Result<SearchResponse, FirecrawlError>`
+
+### Example
+
+```rust
+use firecrawl::{Client, SearchOptions, SearchSource, ScrapeOptions, Format};
+
+let results = client
+    .search("site:docs.firecrawl.dev webhook retries", SearchOptions {
+        sources: Some(vec![SearchSource::Web, SearchSource::News]),
+        limit: Some(10),
+        scrape_options: Some(ScrapeOptions {
+            formats: Some(vec![Format::Markdown]),
+            only_main_content: Some(true),
+            ..Default::default()
+        }),
+        ..Default::default()
+    })
+    .await?;
+
+if let Some(web) = &results.data.web {
+    for item in web {
+        // item is SearchResultOrDocument::WebResult or ::Document
+    }
+}
+```
+
+**Return value:** `SearchResponse` contains `data: SearchData` with optional `web`, `news`, `images` fields.
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `query` | `impl AsRef<str>` | You need a search query. Use `site:example.com` to scope. |
+| `options.sources` | `Vec<SearchSource>` | You want to control sources. Values: `Web`, `News`, `Images`. |
+| `options.categories` | `Vec<SearchCategory>` | You want to filter by category. Values: `Github`, `Research`, `Pdf`. |
+| `options.include_domains` | `Vec<String>` | You want results only from specific domains. |
+| `options.exclude_domains` | `Vec<String>` | You want to exclude specific domains. |
+| `options.limit` | `u32` | You want to cap results. |
+| `options.tbs` | `String` | You need a time filter (e.g. `qdr:d`, `qdr:w`). |
+| `options.location` | `String` | You want localized results. |
+| `options.ignore_invalid_urls` | `bool` | You want to drop URLs that cannot be scraped. |
+| `options.timeout` | `u32` | You need a request timeout in milliseconds. |
+| `options.highlights` | `bool` | You want query-relevant highlights. |
+| `options.scrape_options` | `ScrapeOptions` | You want to scrape each search result inline. |
+
+## Scrape
+
+### Why use it
+
+Use scrape when you already have a URL and want structured content in one or more formats.
+
+### Preferred SDK method
+
+`client.scrape(url, options)` → `Result<Document, FirecrawlError>`
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, Format, JsonOptions};
+
+let doc = client
+    .scrape("https://example.com/pricing", ScrapeOptions {
+        formats: Some(vec![Format::Markdown, Format::Links, Format::Json]),
+        json_options: Some(JsonOptions {
+            prompt: Some("Extract plan names and prices.".to_string()),
+            ..Default::default()
+        }),
+        only_main_content: Some(true),
+        wait_for: Some(1000),
+        ..Default::default()
+    })
+    .await?;
+
+println!("{:?}", doc.markdown);
+println!("{:?}", doc.json);
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `url` | `impl AsRef<str>` | You want to scrape a specific page. |
+| `options.formats` | `Vec<Format>` | You want multiple output formats. See format values below. |
+| `options.headers` | `HashMap<String, String>` | You need custom request headers. |
+| `options.include_tags` | `Vec<String>` | You want to include only specific HTML tags. |
+| `options.exclude_tags` | `Vec<String>` | You want to exclude specific HTML tags. |
+| `options.only_main_content` | `bool` | You want to strip nav, footer, and boilerplate. |
+| `options.timeout` | `u32` | You need a timeout in milliseconds. |
+| `options.wait_for` | `u32` | You need to wait for page render (milliseconds). |
+| `options.mobile` | `bool` | You want a mobile viewport. |
+| `options.parsers` | `Vec<ParserConfig>` | You need file parsing controls. |
+| `options.actions` | `Vec<Action>` | You need pre-scrape browser actions. |
+| `options.location` | `LocationConfig` | You need geo or language-aware scraping. |
+| `options.skip_tls_verification` | `bool` | You need to skip TLS verification. |
+| `options.remove_base64_images` | `bool` | You want to drop base64 images from markdown. |
+| `options.fast_mode` | `bool` | You want faster scrapes with reduced fidelity. |
+| `options.block_ads` | `bool` | You want ad and cookie popup blocking. |
+| `options.proxy` | `ProxyType` | You need proxy control. Values: `Basic`, `Stealth`, `Enhanced`, `Auto`. |
+| `options.max_age` | `u32` | You want cached data up to a maximum age (ms). |
+| `options.min_age` | `u32` | You want cached data only if at least this old (ms). |
+| `options.store_in_cache` | `bool` | You want Firecrawl to cache the result. |
+| `options.lockdown` | `bool` | You want only cached results, no outbound requests. |
+| `options.redact_pii` | `bool` | You want PII redacted from content. |
+| `options.audit_metadata` | `AuditMetadata` | You need user attribution for SIEM. |
+| `options.profile` | `ProfileConfig` | You want a persistent browser profile. Fields: `name`, `save_changes`. |
+| `options.json_options` | `JsonOptions` | You want to configure JSON extraction. Fields: `schema`, `system_prompt`, `prompt`. |
+| `options.screenshot_options` | `ScreenshotOptions` | You want to configure screenshot output. Fields: `full_page`, `quality`, `viewport`. |
+| `options.change_tracking_options` | `ChangeTrackingOptions` | You want change tracking. Fields: `modes` (`GitDiff` / `Json`), `schema`, `prompt`, `tag`. |
+| `options.attribute_selectors` | `Vec<AttributeSelector>` | You want attribute extraction. Fields: `selector`, `attribute`. |
+
+**Format enum values:**
+
+`Markdown`, `Html`, `RawHtml`, `Links`, `Images`, `Screenshot`, `Summary`, `ChangeTracking`, `Json`, `Attributes`, `Branding`, `Product`, `Menu`, `Audio`, `Video`, `Question(QuestionFormat)`, `Highlights(HighlightsFormat)`
+
+**Action enum variants:**
+
+| Variant | Required fields |
+|---|---|
+| `Wait` | `milliseconds` or `selector` |
+| `Click` | `selector` |
+| `Write` | `text` |
+| `Press` | `key` |
+| `Scroll` | `direction` (`Up` / `Down`) |
+| `Screenshot` | none |
+| `Scrape` | none |
+| `ExecuteJavascript` | `script` |
+| `Pdf` | none |
+
+## Interact
+
+### Why use it
+
+Use `interact` for code or natural-language control of the browser session tied to a scrape job. At least one of `code` or `prompt` must be non-empty.
+
+### Preferred SDK method
+
+`client.interact(job_id, options)` → `Result<ScrapeExecuteResponse, FirecrawlError>`
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, Format, ScrapeExecuteOptions};
+
+let doc = client
+    .scrape("https://example.com", ScrapeOptions {
+        formats: Some(vec![Format::Markdown]),
+        ..Default::default()
+    })
+    .await?;
+
+let job_id = doc.metadata
+    .as_ref()
+    .and_then(|m| m.scrape_id.as_ref())
+    .expect("Missing scrapeId");
+
+let result = client
+    .interact(job_id, ScrapeExecuteOptions {
+        prompt: Some("Click the pricing tab and summarize the plans.".to_string()),
+        ..Default::default()
+    })
+    .await?;
+```
+
+### Parameters
+
+| Parameter | Type | Use when |
+|---|---|---|
+| `job_id` | `impl AsRef<str>` | You have a scrape job ID. |
+| `options.code` | `Option<String>` | You want to run code in the browser session. |
+| `options.prompt` | `Option<String>` | You want the browser agent to follow a natural-language instruction. |
+| `options.language` | `ScrapeExecuteLanguage` | You need a specific runtime. Values: `Python`, `Node`, `Bash`. Default: `Node`. |
+| `options.timeout` | `u32` | You need an execution timeout in seconds. |
+
+At least one of `code` or `prompt` must be non-empty; otherwise returns `FirecrawlError::Misuse`.
+
+### Stop session
+
+`client.stop_interaction(job_id)` → ends the browser session. Returns `ScrapeBrowserDeleteResponse` with `success`, optional `session_duration_ms`, `credits_billed`, `error`.
+
+## Notes
+
+- Deprecated aliases: `scrape_execute` → `interact`; `stop_interactive_browser` / `delete_scrape_browser` → `stop_interaction`.
+- `ScrapeOptions` uses dedicated `json_options`, `screenshot_options`, `change_tracking_options` structs (unlike the JS/Python SDKs which use inline format objects).
+- `search_and_scrape(query, limit)` is a convenience helper that calls `search` with default `ScrapeOptions` and returns `Vec<Document>`.
+- All types are exported at the crate root: `use firecrawl::Client`.
+
+## Source Of Truth
+
+- `firecrawl/apps/rust-sdk/Cargo.toml`
+- `firecrawl/apps/rust-sdk/src/client.rs`
+- `firecrawl/apps/rust-sdk/src/scrape.rs`
+- `firecrawl/apps/rust-sdk/src/search.rs`
+- `firecrawl/apps/rust-sdk/src/types.rs`
+- `firecrawl-docs/api-reference/v2-openapi.json`