diff --git a/agent-quickstart/elixir.mdx b/agent-quickstart/elixir.mdx
new file mode 100644
index 000000000..7de827704
--- /dev/null
+++ b/agent-quickstart/elixir.mdx
@@ -0,0 +1,211 @@
+---
+title: "Elixir Agent Quickstart"
+description: "Canonical Firecrawl Elixir quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Elixir Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl via the Elixir SDK. It is generated from SDK source and the OpenAPI spec.
+
+## Install
+
+Add to your `mix.exs`:
+
+```elixir
+defp deps do
+  [
+    {:firecrawl, "~> 1.9"}
+  ]
+end
+```
+
+## Authenticate
+
+The Elixir SDK is a flat module of stateless functions — there is no client struct to construct. Configure the API key globally or pass it per request.
+
+**Global config** (in `config.exs`):
+
+```elixir
+config :firecrawl, api_key: "fc-YOUR_API_KEY"
+```
+
+**Per-request override:**
+
+```elixir
+Firecrawl.scrape_and_extract_from_url([url: "https://example.com"], api_key: "fc-YOUR_API_KEY")
+```
+
+All functions accept trailing `opts` for `:api_key` and `:base_url` (defaults to `https://api.firecrawl.dev/v2`).
+
+## When To Use What
+
+- **`search_and_scrape`** — Use when you start with a query and need to discover relevant pages. Returns structured results grouped by source type. Optionally scrapes each result.
+- **`scrape_and_extract_from_url`** — Use when you already have a URL and want page content in one or more formats (markdown, HTML, JSON extraction, etc.).
+- **`interact_with_scrape_browser_session`** — Use when the page needs post-scrape browser actions: running code in a live browser session tied to a previous scrape job.
+
+## Search
+
+### Why use it
+
+Search the web for a query and optionally scrape each result. Returns results grouped by source type. Use this as the starting point when you do not yet have a specific URL.
+
+### Preferred SDK method
+
+```
+Firecrawl.search_and_scrape(params \\ [], opts \\ [])
+```
+
+Bang variant: `Firecrawl.search_and_scrape!(params, opts)` raises on error.
+
+### Example
+
+```elixir
+{:ok, response} = Firecrawl.search_and_scrape(
+  query: "firecrawl web scraping API",
+  limit: 5
+)
+
+IO.inspect(response.body)
+```
+
+### Parameters
+
+Parameters are passed as a keyword list. All are optional except `query`.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `:string` | **Required.** The search query. |
+| `limit` | `:integer` | Max number of results. |
+| `sources` | `{:list, :any}` | Sources to search. Default: `["web"]`. |
+| `categories` | `{:list, :any}` | Categories to filter results. Default: `[]`. |
+| `include_domains` | `{:list, :string}` | Restrict results to these domains. |
+| `exclude_domains` | `{:list, :string}` | Exclude results from these domains. |
+| `tbs` | `:string` | Time-based search filter (e.g. `"qdr:d"` for past day). |
+| `location` | `:string` | Location for search results. |
+| `country` | `:string` | ISO country code for geo-targeting (e.g. `"US"`). |
+| `timeout` | `:integer` | Timeout in milliseconds. |
+| `highlights` | `:boolean` | Generate query-relevant highlights. Default: `true`. |
+| `ignore_invalid_urls` | `:boolean` | Exclude URLs invalid for other Firecrawl endpoints. |
+| `scrape_options` | `:keyword_list` | Options for scraping search results. |
+| `enterprise` | `{:list, :string}` | Enterprise ZDR options: `["zdr"]` or `["anon"]`. |
+
+### Return shape
+
+`{:ok, %Req.Response{}}` — the response body contains results grouped by source type.
+
+## Scrape
+
+### Why use it
+
+Scrape a single URL and get its content in one or more formats. Use this when you have the exact URL you want content from.
+
+### Preferred SDK method
+
+```
+Firecrawl.scrape_and_extract_from_url(params \\ [], opts \\ [])
+```
+
+Bang variant: `Firecrawl.scrape_and_extract_from_url!(params, opts)` raises on error.
+
+### Example
+
+```elixir
+{:ok, response} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://example.com",
+  formats: ["markdown", "html"],
+  only_main_content: true
+)
+
+IO.inspect(response.body)
+```
+
+### Parameters
+
+Parameters are passed as a keyword list. All are optional except `url`.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `:string` | **Required.** The URL to scrape. |
+| `formats` | `{:list, :any}` | Output formats (e.g. `"markdown"`, `"html"`, `"json"`, `"screenshot"`). Default: `["markdown"]`. |
+| `only_main_content` | `:boolean` | Only return main content. Default: `true`. |
+| `include_tags` | `{:list, :string}` | HTML tags to include. |
+| `exclude_tags` | `{:list, :string}` | HTML tags to exclude. |
+| `headers` | `:any` | Custom HTTP headers. |
+| `timeout` | `:integer` | Timeout in ms. Default: `60000`. Min 1000, max 300000. |
+| `wait_for` | `:integer` | Delay in ms before fetching content. |
+| `mobile` | `:boolean` | Emulate a mobile device. |
+| `parsers` | `{:list, :any}` | File parser config. Default: `["pdf"]`. |
+| `actions` | `{:list, :any}` | Browser actions to perform before grabbing content. |
+| `location` | `:keyword_list` | Location settings (proxy, language, timezone). |
+| `skip_tls_verification` | `:boolean` | Skip TLS certificate verification. |
+| `remove_base64_images` | `:boolean` | Remove base64 images from markdown. Default: `true`. |
+| `block_ads` | `:boolean` | Block ads and cookie popups. Default: `true`. |
+| `proxy` | `{:in, [:basic, :enhanced, :auto]}` | Proxy type. Default: `"auto"`. |
+| `max_age` | `:integer` | Max cache age in ms. Default: `172800000` (2 days). |
+| `min_age` | `:integer` | Cache-only mode. Min age in ms. Set to `1` for any cache. |
+| `store_in_cache` | `:boolean` | Store result in cache. Default: `true`. |
+| `lockdown` | `:boolean` | Only serve cached results. |
+| `redact_pii` | `:boolean` | Redact PII from content. |
+| `zero_data_retention` | `:boolean` | Enable zero data retention. |
+| `profile` | `:keyword_list` | Persistent browser profile. |
+| `audit_metadata` | `:keyword_list` | SIEM logging attribution (`username` required). |
+
+## Interact
+
+### Why use it
+
+Execute code in a live browser session tied to a previous scrape job. Use this for post-scrape interactions like clicking buttons, filling forms, or running scripts.
+
+### Preferred SDK method
+
+```
+Firecrawl.interact_with_scrape_browser_session(job_id, params \\ [], opts \\ [])
+```
+
+Bang variant: `Firecrawl.interact_with_scrape_browser_session!(job_id, params, opts)` raises on error.
+
+### Example
+
+```elixir
+{:ok, scrape_response} = Firecrawl.scrape_and_extract_from_url(url: "https://example.com")
+job_id = scrape_response.body["data"]["metadata"]["jobId"]
+
+{:ok, response} = Firecrawl.interact_with_scrape_browser_session(job_id,
+  code: "document.querySelector('button#submit').click();",
+  language: :node,
+  timeout: 30
+)
+
+IO.inspect(response.body)
+```
+
+### Parameters
+
+The first argument is the `job_id` (path parameter). Remaining parameters are passed as a keyword list.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `String.t()` | **Required** (first argument). The scrape job ID. |
+| `code` | `:string` | **Required.** Code to execute in the browser session. |
+| `language` | `{:in, [:python, :node, :bash]}` | Execution language. Use `:node` for JavaScript or `:bash` for agent-browser CLI commands. |
+| `timeout` | `:integer` | Execution timeout in seconds. |
+| `origin` | `:string` | Origin label for telemetry. |
+
+### Related methods
+
+- `Firecrawl.stop_interactive_scrape_browser_session(job_id, opts)` — Stop the browser session (`DELETE /scrape/{jobId}/interact`).
+
+## Notes
+
+- The SDK is **auto-generated from the OpenAPI spec**. Function names map 1:1 to OpenAPI operations.
+- Parameter names use **snake_case** in Elixir. They are converted to camelCase for the JSON wire format automatically.
+- All functions return `{:ok, %Req.Response{}} | {:error, Exception.t() | Firecrawl.Error.t()}`.
+- Bang variants (e.g. `search_and_scrape!`) raise on error instead of returning an error tuple.
+- There is no client struct — the module is a flat namespace of stateless functions.
+- HTTP errors (4xx/5xx) are wrapped in `Firecrawl.Error` with `:status` and `:body` fields.
+- Batch scraping is available via `Firecrawl.scrape_and_extract_from_urls/2` (`POST /batch/scrape`).
+
+## Source Of Truth
+
+- SDK: `firecrawl/apps/elixir-sdk/lib/firecrawl.ex`
+- OpenAPI: `firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/java.mdx b/agent-quickstart/java.mdx
new file mode 100644
index 000000000..d2c328796
--- /dev/null
+++ b/agent-quickstart/java.mdx
@@ -0,0 +1,242 @@
+---
+title: "Java Agent Quickstart"
+description: "Canonical Firecrawl Java quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Java Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl via the Java SDK. It is generated from SDK source and the OpenAPI spec.
+
+## Install
+
+**Maven:**
+
+```xml
+<dependency>
+  <groupId>com.firecrawl</groupId>
+  <artifactId>firecrawl-java</artifactId>
+  <version>1.12.1</version>
+</dependency>
+```
+
+**Gradle:**
+
+```groovy
+implementation 'com.firecrawl:firecrawl-java:1.12.1'
+```
+
+Requires Java 11+.
+
+## Authenticate
+
+```java
+import com.firecrawl.client.FirecrawlClient;
+
+FirecrawlClient client = FirecrawlClient.builder()
+    .apiKey("fc-YOUR_API_KEY")
+    .build();
+```
+
+Or from environment variables:
+
+```java
+FirecrawlClient client = FirecrawlClient.fromEnv();
+```
+
+`fromEnv()` reads `FIRECRAWL_API_KEY` (env var) or `firecrawl.apiKey` (system property).
+
+## When To Use What
+
+- **`search`** — Use when you start with a query and need to discover relevant pages. Returns structured results grouped by source type (web, news, images). Optionally scrapes each result.
+- **`scrape`** — Use when you already have a URL and want page content in one or more formats (markdown, HTML, JSON extraction, screenshots, etc.).
+- **`interact`** — Use when the page needs post-scrape browser actions: clicking buttons, filling forms, or running code in a live browser session.
+
+## Search
+
+### Why use it
+
+Search the web for a query and optionally scrape each result. Returns results grouped by source type. Use this as the starting point when you do not yet have a specific URL.
+
+### Preferred SDK method
+
+```
+client.search(query)
+client.search(query, options)
+```
+
+Async variant: `client.searchAsync(query, options)` returns `CompletableFuture<SearchData>`.
+
+### Example
+
+```java
+import com.firecrawl.models.SearchOptions;
+import com.firecrawl.models.SearchData;
+import com.firecrawl.models.ScrapeOptions;
+
+SearchData results = client.search("firecrawl web scraping API",
+    SearchOptions.builder()
+        .limit(5)
+        .scrapeOptions(ScrapeOptions.builder()
+            .formats(List.of("markdown"))
+            .build())
+        .build());
+
+for (var item : results.getWeb()) {
+    System.out.println(item.get("url") + " " + item.get("title"));
+}
+```
+
+### Parameters
+
+`SearchOptions` uses a builder pattern. All fields are optional and default to `null` (server defaults apply).
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `String` | **Required** (method argument). The search query. |
+| `sources` | `List<Object>` | Sources to query: `"web"`, `"news"`, `"images"` as strings or typed maps. Default: `["web"]`. |
+| `categories` | `List<Object>` | Categories: `"github"`, `"research"`, `"pdf"`. |
+| `includeDomains` | `List<String>` | Restrict results to these domains. |
+| `excludeDomains` | `List<String>` | Exclude results from these domains. |
+| `limit` | `Integer` | Max number of results. |
+| `tbs` | `String` | Time-based search filter (e.g. `"qdr:d"` for past day). |
+| `location` | `String` | Location for search results. |
+| `ignoreInvalidURLs` | `Boolean` | Exclude URLs invalid for other Firecrawl endpoints. |
+| `timeout` | `Integer` | Timeout in milliseconds. |
+| `highlights` | `Boolean` | Generate query-relevant highlights. Default: `true` (server-side). |
+| `scrapeOptions` | `ScrapeOptions` | Options applied when scraping each result. |
+| `integration` | `String` | Integration identifier. |
+
+### Return shape
+
+```java
+SearchData {
+    List<Map<String, Object>> web;
+    List<Map<String, Object>> news;
+    List<Map<String, Object>> images;
+}
+```
+
+## Scrape
+
+### Why use it
+
+Scrape a single URL and get its content in one or more formats. Use this when you have the exact URL you want content from.
+
+### Preferred SDK method
+
+```
+client.scrape(url)
+client.scrape(url, options)
+```
+
+Async variant: `client.scrapeAsync(url, options)` returns `CompletableFuture<Document>`.
+
+### Example
+
+```java
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.Document;
+
+Document doc = client.scrape("https://example.com",
+    ScrapeOptions.builder()
+        .formats(List.of("markdown", "html"))
+        .onlyMainContent(true)
+        .build());
+
+System.out.println(doc.getMarkdown());
+```
+
+### Parameters
+
+`ScrapeOptions` uses a builder pattern. All fields are optional and default to `null`.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `String` | **Required** (method argument). The URL to scrape. |
+| `formats` | `List<Object>` | Output formats: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"json"`, `"audio"`, `"video"`. Also accepts typed objects (`JsonFormat`, `QuestionFormat`, `HighlightsFormat`). Default: `["markdown"]`. |
+| `onlyMainContent` | `Boolean` | Only return main content. Default: `true`. |
+| `includeTags` | `List<String>` | HTML tags to include. |
+| `excludeTags` | `List<String>` | HTML tags to exclude. |
+| `headers` | `Map<String, String>` | Custom HTTP headers. |
+| `timeout` | `Integer` | Timeout in milliseconds. Default: `60000`. |
+| `waitFor` | `Integer` | Delay in ms before fetching content. |
+| `mobile` | `Boolean` | Emulate a mobile device. |
+| `parsers` | `List<Object>` | File parser config. Default: `["pdf"]`. |
+| `actions` | `List<Map<String, Object>>` | Browser actions (wait, click, write, press, scroll, etc.). |
+| `location` | `LocationConfig` | Location and language settings (`country`, `languages`). |
+| `skipTlsVerification` | `Boolean` | Skip TLS certificate verification. |
+| `removeBase64Images` | `Boolean` | Remove base64 images from markdown. Default: `true`. |
+| `blockAds` | `Boolean` | Block ads and cookie popups. Default: `true`. |
+| `proxy` | `String` | Proxy type: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`. Default: `"auto"`. |
+| `maxAge` | `Long` | Max cache age in ms. Default: `172800000` (2 days). |
+| `storeInCache` | `Boolean` | Store result in cache. Default: `true`. |
+| `lockdown` | `Boolean` | Only serve cached results. |
+| `redactPII` | `Boolean` | Redact PII from content. |
+| `auditMetadata` | `AuditMetadata` | SIEM logging attribution. Constructed via `new AuditMetadata("username")`. |
+| `integration` | `String` | Integration identifier. |
+
+## Interact
+
+### Why use it
+
+Execute code in a live browser session tied to a previous scrape job. Use this for post-scrape interactions like clicking buttons, filling forms, or running scripts.
+
+### Preferred SDK method
+
+```
+client.interact(jobId, code)
+client.interact(jobId, code, language, timeout)
+client.interact(jobId, code, language, timeout, origin)
+```
+
+Async variants are available for all overloads.
+
+### Example
+
+```java
+import com.firecrawl.models.BrowserExecuteResponse;
+import com.firecrawl.models.Document;
+
+Document doc = client.scrape("https://example.com");
+String jobId = (String) doc.getMetadata().get("jobId");
+
+BrowserExecuteResponse response = client.interact(
+    jobId,
+    "document.querySelector('button#submit').click();",
+    "node",
+    30
+);
+
+System.out.println(response.getStdout());
+```
+
+### Parameters
+
+Parameters are positional (no options object).
+
+| Parameter | Type | Description |
+|---|---|---|
+| `jobId` | `String` | **Required.** The scrape job ID from a previous `scrape` call. |
+| `code` | `String` | **Required.** Code to execute in the browser session. |
+| `language` | `String` | Execution language: `"python"`, `"node"`, or `"bash"`. Default: `"node"`. |
+| `timeout` | `Integer` | Execution timeout in seconds (1–300). Default: `30` (server-side). |
+| `origin` | `String` | Origin identifier. Auto-set to `"java-sdk@{version}"` if not provided. |
+
+### Related methods
+
+- `client.stopInteractiveBrowser(jobId)` — Stop the browser session and release resources.
+
+## Notes
+
+- All parameter names use **camelCase** (Java convention).
+- The client builder also accepts `timeoutMs` (default `300000`), `maxRetries` (default `3`), `backoffFactor` (default `0.5`), and `asyncExecutor`.
+- Typed format helpers: `JsonFormat.builder().prompt("...").schema(map).build()`, `QuestionFormat.builder().question("...").build()`, `HighlightsFormat.builder().query("...").build()`.
+- `LocationConfig` is built via `LocationConfig.builder().country("US").languages(List.of("en")).build()`.
+- **Deprecated aliases** (do not use in new code):
+  - `scrapeExecute()` → use `interact()`
+  - `deleteScrapeBrowser()` → use `stopInteractiveBrowser()`
+
+## Source Of Truth
+
+- SDK: `firecrawl/apps/java-sdk/src/main/java/com/firecrawl/client/FirecrawlClient.java`, `firecrawl/apps/java-sdk/src/main/java/com/firecrawl/models/`
+- OpenAPI: `firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/node.mdx b/agent-quickstart/node.mdx
new file mode 100644
index 000000000..5ddf01fb0
--- /dev/null
+++ b/agent-quickstart/node.mdx
@@ -0,0 +1,211 @@
+---
+title: "Node.js Agent Quickstart"
+description: "Canonical Firecrawl Node.js quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Node.js Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl via the JavaScript/TypeScript SDK. It is generated from SDK source and the OpenAPI spec.
+
+## Install
+
+```bash
+npm install @mendable/firecrawl-js
+```
+
+## Authenticate
+
+```javascript
+import Firecrawl from "@mendable/firecrawl-js";
+
+const client = new Firecrawl("fc-YOUR_API_KEY");
+```
+
+You can also pass options:
+
+```javascript
+const client = new Firecrawl({
+  apiKey: "fc-YOUR_API_KEY",
+  apiUrl: "https://api.firecrawl.dev",
+});
+```
+
+If omitted, `apiKey` falls back to the `FIRECRAWL_API_KEY` environment variable, and `apiUrl` falls back to `FIRECRAWL_API_URL`.
+
+## When To Use What
+
+- **`search`** — Use when you start with a query and need to discover relevant pages. Returns structured results grouped by source type (web, news, images). Optionally scrapes each result.
+- **`scrape`** — Use when you already have a URL and want page content in one or more formats (markdown, HTML, JSON extraction, screenshots, etc.).
+- **`interact`** — Use when the page needs post-scrape browser actions: clicking buttons, filling forms, running code in a live browser session, or sending a natural-language prompt to a browser agent.
+
+## Search
+
+### Why use it
+
+Search the web for a query and optionally scrape each result. Returns results grouped by source type. Use this as the starting point when you do not yet have a specific URL.
+
+### Preferred SDK method
+
+```
+client.search(query, options?)
+```
+
+### Example
+
+```javascript
+const results = await client.search("firecrawl web scraping API", {
+  limit: 5,
+  scrapeOptions: { formats: ["markdown"] },
+});
+
+for (const item of results.web ?? []) {
+  console.log(item.url, item.title);
+}
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `string` | **Required.** The search query. |
+| `limit` | `number` | Max number of results to return. |
+| `sources` | `Array<"web" \| "news" \| "images" \| {type: ...}>` | Which search sources to query. Default: `["web"]`. |
+| `categories` | `Array<"github" \| "research" \| "pdf" \| "developer" \| {type: ...}>` | Content categories to filter by. |
+| `includeDomains` | `string[]` | Restrict results to these domains. Cannot combine with `excludeDomains`. |
+| `excludeDomains` | `string[]` | Exclude results from these domains. Cannot combine with `includeDomains`. |
+| `tbs` | `string` | Time-based search filter (e.g. `"qdr:d"` for past day, `"qdr:w"` for past week). |
+| `location` | `string` | Location for search results (e.g. `"San Francisco,California,United States"`). |
+| `ignoreInvalidURLs` | `boolean` | Exclude URLs invalid for other Firecrawl endpoints. |
+| `timeout` | `number` | Timeout in milliseconds. |
+| `highlights` | `boolean` | Generate query-relevant highlights. Default: `true`. |
+| `scrapeOptions` | `ScrapeOptions` | Options applied when scraping each search result. Same shape as the `scrape` options. |
+| `enterprise` | `Array<"default" \| "anon" \| "zdr">` | Enterprise ZDR options. |
+| `threatProtection` | `ThreatProtectionOptions` | Enterprise per-request threat protection override. |
+| `integration` | `string` | Integration identifier. |
+| `origin` | `string` | Origin identifier. |
+
+### Return shape
+
+```typescript
+{
+  web?: Array<SearchResultWeb | Document>,
+  news?: Array<SearchResultNews | Document>,
+  images?: Array<SearchResultImages | Document>,
+  developer?: Array<SearchResultWeb | Document>,
+}
+```
+
+## Scrape
+
+### Why use it
+
+Scrape a single URL and get its content in one or more formats. Use this when you have the exact URL you want content from.
+
+### Preferred SDK method
+
+```
+client.scrape(url, options?)
+```
+
+### Example
+
+```javascript
+const doc = await client.scrape("https://example.com", {
+  formats: ["markdown", "html"],
+  onlyMainContent: true,
+});
+
+console.log(doc.markdown);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `string` | **Required.** The URL to scrape. |
+| `formats` | `FormatOption[]` | Output formats: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"json"`, `"changeTracking"`, `"attributes"`, `"branding"`, `"product"`, `"menu"`, `"audio"`, `"video"`. Also accepts typed objects for `json`, `screenshot`, `question`, `highlights`. Default: `["markdown"]`. |
+| `onlyMainContent` | `boolean` | Only return main content, excluding headers/navs/footers. Default: `true`. |
+| `includeTags` | `string[]` | HTML tags to include in output. |
+| `excludeTags` | `string[]` | HTML tags to exclude from output. |
+| `headers` | `Record<string, string>` | Custom HTTP headers sent with the request. |
+| `timeout` | `number` | Timeout in milliseconds. Default: `60000`. Min 1000, max 300000. |
+| `waitFor` | `number` | Delay in ms before fetching content. |
+| `mobile` | `boolean` | Emulate a mobile device. |
+| `parsers` | `Array<string \| {type: "pdf", mode?: string, maxPages?: number}>` | File parser config. Default: `["pdf"]`. |
+| `actions` | `ActionOption[]` | Browser actions to perform before grabbing content (wait, click, write, press, scroll, screenshot, scrape, executeJavascript, pdf). |
+| `location` | `{country?: string, languages?: string[]}` | Location and language settings. Uses appropriate proxy. |
+| `skipTlsVerification` | `boolean` | Skip TLS certificate verification. |
+| `removeBase64Images` | `boolean` | Remove base64-encoded images from markdown. Default: `true`. |
+| `fastMode` | `boolean` | Enable fast mode for quicker scraping. |
+| `blockAds` | `boolean` | Block ads and cookie popups. Default: `true`. |
+| `proxy` | `"basic" \| "stealth" \| "enhanced" \| "auto" \| string` | Proxy type. Default: `"auto"`. |
+| `maxAge` | `number` | Max cache age in ms. Use cached result if younger. Default: `172800000` (2 days). Set to `0` to bypass cache. |
+| `minAge` | `number` | Cache-only mode. Min age in ms. Set to `1` for any cached version. |
+| `storeInCache` | `boolean` | Store result in Firecrawl cache. Default: `true`. |
+| `lockdown` | `boolean` | Only serve cached results, never make outbound requests. |
+| `redactPII` | `boolean \| RedactPIIOptions` | Redact PII from content. Pass `true` for defaults or an options object with `mode`, `entities`, `replaceStyle`. |
+| `profile` | `{name: string, saveChanges?: boolean}` | Persistent browser profile across scrape/interact sessions. |
+| `auditMetadata` | `{username: string}` | User attribution for SIEM logging. |
+| `threatProtection` | `ThreatProtectionOptions` | Enterprise per-request threat protection override. |
+| `integration` | `string` | Integration identifier. |
+| `origin` | `string` | Origin identifier. |
+
+## Interact
+
+### Why use it
+
+Execute code or send a natural-language prompt in a live browser session tied to a previous scrape job. Use this for post-scrape interactions like clicking buttons, filling forms, or navigating multi-step flows.
+
+### Preferred SDK method
+
+```
+client.interact(jobId, args)
+```
+
+### Example
+
+```javascript
+const scrapeResult = await client.scrape("https://example.com", {
+  formats: ["markdown"],
+});
+const jobId = scrapeResult.metadata?.jobId;
+
+const response = await client.interact(jobId, {
+  code: "document.querySelector('button#submit').click();",
+  language: "node",
+  timeout: 30,
+});
+
+console.log(response.stdout);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `jobId` | `string` | **Required.** The scrape job ID from a previous `scrape` call. |
+| `code` | `string` | Code to execute in the browser session. One of `code` or `prompt` is required. |
+| `prompt` | `string` | Natural-language instruction for the browser agent. One of `code` or `prompt` is required. |
+| `language` | `"python" \| "node" \| "bash"` | Execution language. Default: `"node"`. |
+| `timeout` | `number` | Execution timeout in seconds. Min 1, max 300. Default: `30`. |
+| `origin` | `string` | Origin identifier for telemetry. |
+
+### Related methods
+
+- `client.stopInteraction(jobId)` — Stop the browser session and release resources.
+
+## Notes
+
+- All parameter names use **camelCase**.
+- The SDK auto-sets an `origin` field on requests for telemetry.
+- `search` results are accessed via `.web`, `.news`, `.images`, or `.developer` — there is no `.data` property.
+- The constructor also accepts `timeoutMs`, `maxRetries`, and `backoffFactor` for HTTP-level configuration.
+- **Deprecated aliases** (do not use in new code):
+  - `scrapeUrl()` → use `scrape()`
+  - `scrapeExecute()` → use `interact()`
+  - `stopInteractiveBrowser()` / `deleteScrapeBrowser()` → use `stopInteraction()`
+
+## Source Of Truth
+
+- SDK: `firecrawl/apps/js-sdk/firecrawl/src/v2/client.ts`, `firecrawl/apps/js-sdk/firecrawl/src/v2/types.ts`
+- OpenAPI: `firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/python.mdx b/agent-quickstart/python.mdx
new file mode 100644
index 000000000..cd4f2e23f
--- /dev/null
+++ b/agent-quickstart/python.mdx
@@ -0,0 +1,204 @@
+---
+title: "Python Agent Quickstart"
+description: "Canonical Firecrawl Python quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Python Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl via the Python SDK. It is generated from SDK source and the OpenAPI spec.
+
+## Install
+
+```bash
+pip install firecrawl-py
+```
+
+## Authenticate
+
+```python
+from firecrawl import Firecrawl
+
+client = Firecrawl(api_key="fc-YOUR_API_KEY")
+```
+
+If omitted, `api_key` falls back to the `FIRECRAWL_API_KEY` environment variable. An async client is also available:
+
+```python
+from firecrawl import AsyncFirecrawl
+
+client = AsyncFirecrawl(api_key="fc-YOUR_API_KEY")
+```
+
+## When To Use What
+
+- **`search`** — Use when you start with a query and need to discover relevant pages. Returns structured results grouped by source type (web, news, images). Optionally scrapes each result.
+- **`scrape`** — Use when you already have a URL and want page content in one or more formats (markdown, HTML, JSON extraction, screenshots, etc.).
+- **`interact`** — Use when the page needs post-scrape browser actions: clicking buttons, filling forms, running code in a live browser session, or sending a natural-language prompt to a browser agent.
+
+## Search
+
+### Why use it
+
+Search the web for a query and optionally scrape each result. Returns results grouped by source type. Use this as the starting point when you do not yet have a specific URL.
+
+### Preferred SDK method
+
+```
+client.search(query, **kwargs)
+```
+
+### Example
+
+```python
+results = client.search(
+    "firecrawl web scraping API",
+    limit=5,
+    scrape_options={"formats": ["markdown"]},
+)
+
+for item in results.web or []:
+    print(item.url, item.title)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `str` | **Required.** The search query. |
+| `limit` | `int` | Max number of results. Default: `5`. |
+| `sources` | `list` | Which search sources to query (`"web"`, `"news"`, `"images"` or `Source` objects). Default: `["web"]`. |
+| `categories` | `list` | Content categories (`"github"`, `"research"`, `"pdf"`, `"developer"` or `Category` objects). |
+| `include_domains` | `list[str]` | Restrict results to these domains. Cannot combine with `exclude_domains`. |
+| `exclude_domains` | `list[str]` | Exclude results from these domains. Cannot combine with `include_domains`. |
+| `tbs` | `str` | Time-based search filter (e.g. `"qdr:d"` for past day). |
+| `location` | `str` | Location for search results (e.g. `"San Francisco,California,United States"`). Note: this is a plain string, not a `Location` object. |
+| `ignore_invalid_urls` | `bool` | Exclude URLs invalid for other Firecrawl endpoints. |
+| `timeout` | `int` | Timeout in milliseconds. Default: `300000`. |
+| `highlights` | `bool` | Generate query-relevant highlights. Default: `True`. |
+| `scrape_options` | `ScrapeOptions` or `dict` | Options applied when scraping each result. Same shape as `scrape` options. |
+| `enterprise` | `list[str]` | Enterprise ZDR options: `["zdr"]` or `["anon"]`. |
+| `threat_protection` | `ThreatProtectionOptions` | Enterprise per-request threat protection override. |
+| `integration` | `str` | Integration identifier. |
+
+### Return shape
+
+```python
+SearchData(
+    web: list[SearchResultWeb | Document] | None,
+    news: list[SearchResultNews | Document] | None,
+    images: list[SearchResultImages | Document] | None,
+    developer: list[SearchResultWeb | Document] | None,
+)
+```
+
+## Scrape
+
+### Why use it
+
+Scrape a single URL and get its content in one or more formats. Use this when you have the exact URL you want content from.
+
+### Preferred SDK method
+
+```
+client.scrape(url, **kwargs)
+```
+
+### Example
+
+```python
+doc = client.scrape(
+    "https://example.com",
+    formats=["markdown", "html"],
+    only_main_content=True,
+)
+
+print(doc.markdown)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `str` | **Required.** The URL to scrape. |
+| `formats` | `list` | Output formats: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"json"`, `"changeTracking"`, `"attributes"`, `"branding"`, `"product"`, `"menu"`, `"audio"`, `"video"`. Also accepts typed format objects. Default: `["markdown"]`. |
+| `only_main_content` | `bool` | Only return main content, excluding headers/navs/footers. Default: `True`. |
+| `include_tags` | `list[str]` | HTML tags to include in output. |
+| `exclude_tags` | `list[str]` | HTML tags to exclude from output. |
+| `headers` | `dict[str, str]` | Custom HTTP headers sent with the request. |
+| `timeout` | `int` | Timeout in milliseconds. Default: `60000`. Min 1000, max 300000. |
+| `wait_for` | `int` | Delay in ms before fetching content. |
+| `mobile` | `bool` | Emulate a mobile device. |
+| `parsers` | `list` | File parser config (e.g. `["pdf"]` or `[{"type": "pdf", "mode": "auto"}]`). Default: `["pdf"]`. |
+| `actions` | `list` | Browser actions to perform before grabbing content (wait, click, write, press, scroll, screenshot, scrape, executeJavascript, pdf). |
+| `location` | `Location` | Location and language settings (`country`, `languages`). Uses appropriate proxy. |
+| `skip_tls_verification` | `bool` | Skip TLS certificate verification. |
+| `remove_base64_images` | `bool` | Remove base64-encoded images from markdown. Default: `True`. |
+| `fast_mode` | `bool` | Enable fast mode for quicker scraping. |
+| `block_ads` | `bool` | Block ads and cookie popups. Default: `True`. |
+| `proxy` | `str` | Proxy type: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`. Default: `"auto"`. |
+| `max_age` | `int` | Max cache age in ms. Default: `172800000` (2 days). Set to `0` to bypass cache. |
+| `store_in_cache` | `bool` | Store result in Firecrawl cache. Default: `True`. |
+| `lockdown` | `bool` | Only serve cached results, never make outbound requests. |
+| `threat_protection` | `ThreatProtectionOptions` | Enterprise per-request threat protection override. |
+| `profile` | `dict` | Persistent browser profile (e.g. `{"name": "my-profile", "saveChanges": True}`). |
+| `audit_metadata` | `AuditMetadata` | User attribution for SIEM logging (`{"username": "..."}`). |
+| `integration` | `str` | Integration identifier. |
+
+## Interact
+
+### Why use it
+
+Execute code or send a natural-language prompt in a live browser session tied to a previous scrape job. Use this for post-scrape interactions like clicking buttons, filling forms, or navigating multi-step flows.
+
+### Preferred SDK method
+
+```
+client.interact(job_id, code=None, *, prompt=None, language="node", timeout=None, origin=None)
+```
+
+### Example
+
+```python
+scrape_result = client.scrape("https://example.com", formats=["markdown"])
+job_id = scrape_result.metadata.get("jobId")
+
+response = client.interact(
+    job_id,
+    code="document.querySelector('button#submit').click();",
+    language="node",
+    timeout=30,
+)
+
+print(response.stdout)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `str` | **Required.** The scrape job ID from a previous `scrape` call. |
+| `code` | `str` | Code to execute in the browser session. One of `code` or `prompt` is required. |
+| `prompt` | `str` | Natural-language instruction for the browser agent. One of `code` or `prompt` is required. |
+| `language` | `"python" \| "node" \| "bash"` | Execution language. Default: `"node"`. |
+| `timeout` | `int` | Execution timeout in seconds (1–300). |
+| `origin` | `str` | Origin identifier for telemetry. |
+
+### Related methods
+
+- `client.stop_interaction(job_id)` — Stop the browser session and release resources.
+
+## Notes
+
+- All parameter names use **snake_case**.
+- The constructor also accepts `timeout` (in seconds), `max_retries` (default `3`), and `backoff_factor` (default `0.5`).
+- `search` results are accessed via `.web`, `.news`, `.images`, or `.developer` — there is no `.data` attribute.
+- `FirecrawlApp` and `AsyncFirecrawlApp` are aliases for `Firecrawl` and `AsyncFirecrawl`.
+- **Deprecated aliases** (do not use in new code):
+  - `scrape_url()` → use `scrape()`
+  - `scrape_execute()` → use `interact()`
+  - `stop_interactive_browser()` / `delete_scrape_browser()` → use `stop_interaction()`
+
+## Source Of Truth
+
+- SDK: `firecrawl/apps/python-sdk/firecrawl/v2/client.py`, `firecrawl/apps/python-sdk/firecrawl/v2/types.py`
+- OpenAPI: `firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/rust.mdx b/agent-quickstart/rust.mdx
new file mode 100644
index 000000000..f90a84d47
--- /dev/null
+++ b/agent-quickstart/rust.mdx
@@ -0,0 +1,252 @@
+---
+title: "Rust Agent Quickstart"
+description: "Canonical Firecrawl Rust quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Rust Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating with Firecrawl via the Rust SDK. It is generated from SDK source and the OpenAPI spec.
+
+## Install
+
+Add to your `Cargo.toml`:
+
+```toml
+[dependencies]
+firecrawl = "2"
+```
+
+## Authenticate
+
+```rust
+use firecrawl::Client;
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+```
+
+For self-hosted instances:
+
+```rust
+let client = Client::new_selfhosted("https://your-instance.com", Some("fc-YOUR_API_KEY"))?;
+```
+
+The API key is optional — omit it or pass `None` for keyless free tier (rate-limited per IP).
+
+## When To Use What
+
+- **`search`** — Use when you start with a query and need to discover relevant pages. Returns structured results grouped by source type (web, news, images). Optionally scrapes each result.
+- **`scrape`** — Use when you already have a URL and want page content in one or more formats (markdown, HTML, JSON extraction, screenshots, etc.).
+- **`interact`** — Use when the page needs post-scrape browser actions: clicking buttons, filling forms, running code in a live browser session, or sending a natural-language prompt to a browser agent.
+
+## Search
+
+### Why use it
+
+Search the web for a query and optionally scrape each result. Returns results grouped by source type. Use this as the starting point when you do not yet have a specific URL.
+
+### Preferred SDK method
+
+```
+client.search(query, options)
+```
+
+A convenience wrapper is also available:
+
+```
+client.search_and_scrape(query, limit) -> Vec<Document>
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, SearchOptions, ScrapeOptions};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+let results = client.search("firecrawl web scraping API", SearchOptions {
+    limit: Some(5),
+    scrape_options: Some(ScrapeOptions::default()),
+    ..Default::default()
+})?;
+
+if let Some(web) = results.data.web {
+    for item in web {
+        println!("{:?}", item);
+    }
+}
+```
+
+### Parameters
+
+All fields on `SearchOptions` are `Option` and default to `None`. Use `..Default::default()` for unset fields.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `impl AsRef<str>` | **Required** (method argument). The search query. |
+| `limit` | `Option<u32>` | Max number of results. Default: `5`, max: `20`. |
+| `sources` | `Option<Vec<SearchSource>>` | Sources to query: `SearchSource::Web`, `News`, `Images`. Default: `[Web]`. |
+| `categories` | `Option<Vec<SearchCategory>>` | Categories: `SearchCategory::Github`, `Research`, `Pdf`. |
+| `include_domains` | `Option<Vec<String>>` | Restrict results to these domains. |
+| `exclude_domains` | `Option<Vec<String>>` | Exclude results from these domains. |
+| `tbs` | `Option<String>` | Time-based search filter (e.g. `"qdr:d"` for past day). |
+| `location` | `Option<String>` | Location for search results. |
+| `ignore_invalid_urls` | `Option<bool>` | Exclude URLs invalid for other Firecrawl endpoints. |
+| `timeout` | `Option<u32>` | Timeout in milliseconds. |
+| `highlights` | `Option<bool>` | Generate query-relevant highlights. Default: `true` (server-side). |
+| `scrape_options` | `Option<ScrapeOptions>` | Options applied when scraping each result. |
+| `integration` | `Option<String>` | Integration identifier. |
+| `origin` | `Option<String>` | Origin label. Auto-set to `"rust-sdk@{version}"`. |
+
+### Return shape
+
+```rust
+SearchResponse {
+    success: bool,
+    data: SearchData {
+        web: Option<Vec<SearchResultOrDocument>>,
+        news: Option<Vec<SearchResultNews>>,
+        images: Option<Vec<SearchResultImage>>,
+    },
+    warning: Option<String>,
+}
+```
+
+`SearchResultOrDocument` is an enum: `WebResult(SearchResultWeb)` or `Document(Document)`.
+
+## Scrape
+
+### Why use it
+
+Scrape a single URL and get its content in one or more formats. Use this when you have the exact URL you want content from.
+
+### Preferred SDK method
+
+```
+client.scrape(url, options)
+```
+
+A convenience wrapper for JSON extraction:
+
+```
+client.scrape_with_schema(url, schema, prompt)
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, Format};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+let doc = client.scrape("https://example.com", ScrapeOptions {
+    formats: Some(vec![Format::Markdown, Format::Html]),
+    only_main_content: Some(true),
+    ..Default::default()
+})?;
+
+println!("{}", doc.markdown.unwrap_or_default());
+```
+
+### Parameters
+
+All fields on `ScrapeOptions` are `Option` and default to `None`. Use `..Default::default()` for unset fields.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `impl AsRef<str>` | **Required** (method argument). The URL to scrape. |
+| `formats` | `Option<Vec<Format>>` | Output formats: `Markdown`, `Html`, `RawHtml`, `Links`, `Images`, `Screenshot`, `Summary`, `Json`, `ChangeTracking`, `Attributes`, `Branding`, `Product`, `Menu`, `Audio`, `Video`, `Question(QuestionFormat)`, `Highlights(HighlightsFormat)`. Default: `[Markdown]`. |
+| `only_main_content` | `Option<bool>` | Only return main content. Default: `true`. |
+| `include_tags` | `Option<Vec<String>>` | HTML tags to include. |
+| `exclude_tags` | `Option<Vec<String>>` | HTML tags to exclude. |
+| `headers` | `Option<HashMap<String, String>>` | Custom HTTP headers. |
+| `timeout` | `Option<u32>` | Timeout in ms. Default: `60000`. |
+| `wait_for` | `Option<u32>` | Delay in ms before fetching content. |
+| `mobile` | `Option<bool>` | Emulate a mobile device. |
+| `parsers` | `Option<Vec<ParserConfig>>` | File parser config. Default: `["pdf"]`. |
+| `actions` | `Option<Vec<Action>>` | Browser automation actions (Wait, Click, Write, Press, Scroll, Screenshot, Scrape, ExecuteJavascript, Pdf). |
+| `location` | `Option<LocationConfig>` | Location and language settings (`country`, `languages`). |
+| `skip_tls_verification` | `Option<bool>` | Skip TLS certificate verification. |
+| `remove_base64_images` | `Option<bool>` | Remove base64 images from markdown. Default: `true`. |
+| `fast_mode` | `Option<bool>` | Enable fast mode. |
+| `block_ads` | `Option<bool>` | Block ads. Default: `true`. |
+| `proxy` | `Option<ProxyType>` | Proxy type: `Basic`, `Stealth`, `Enhanced`, `Auto`. Default: `Auto`. |
+| `max_age` | `Option<u32>` | Max cache age in seconds. |
+| `min_age` | `Option<u32>` | Cache-only mode, min age in seconds. |
+| `store_in_cache` | `Option<bool>` | Store result in cache. Default: `true`. |
+| `lockdown` | `Option<bool>` | Only serve cached results. |
+| `redact_pii` | `Option<bool>` | Redact PII from content. |
+| `profile` | `Option<ProfileConfig>` | Persistent browser profile (`name`, `save_changes`). |
+| `audit_metadata` | `Option<AuditMetadata>` | SIEM logging attribution (`username`). |
+| `integration` | `Option<String>` | Integration identifier. |
+| `json_options` | `Option<JsonOptions>` | JSON extraction options (`schema`, `system_prompt`, `prompt`). Used with `Format::Json`. |
+| `screenshot_options` | `Option<ScreenshotOptions>` | Screenshot options (`full_page`, `quality`, `viewport`). |
+| `change_tracking_options` | `Option<ChangeTrackingOptions>` | Change tracking options (`modes`, `schema`, `prompt`, `tag`). |
+| `attribute_selectors` | `Option<Vec<AttributeSelector>>` | Attribute extraction selectors (`selector`, `attribute`). |
+| `origin` | `Option<String>` | Origin label. Auto-set to `"rust-sdk@{version}"`. |
+
+## Interact
+
+### Why use it
+
+Execute code or send a natural-language prompt in a live browser session tied to a previous scrape job. Use this for post-scrape interactions like clicking buttons, filling forms, or navigating multi-step flows.
+
+### Preferred SDK method
+
+```
+client.interact(job_id, options)
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, ScrapeExecuteOptions, ScrapeExecuteLanguage};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+let doc = client.scrape("https://example.com", ScrapeOptions::default())?;
+let job_id = doc.metadata.as_ref()
+    .and_then(|m| m.get("jobId"))
+    .and_then(|v| v.as_str())
+    .unwrap();
+
+let response = client.interact(job_id, ScrapeExecuteOptions {
+    code: Some("document.querySelector('button#submit').click();".into()),
+    language: Some(ScrapeExecuteLanguage::Node),
+    timeout: Some(30),
+    ..Default::default()
+})?;
+
+println!("{}", response.stdout.unwrap_or_default());
+```
+
+### Parameters
+
+All fields on `ScrapeExecuteOptions` are `Option` and default to `None`.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `impl AsRef<str>` | **Required** (method argument). The scrape job ID. |
+| `code` | `Option<String>` | Code to execute in the browser session. One of `code` or `prompt` is required. |
+| `prompt` | `Option<String>` | Natural-language instruction for the browser agent. One of `code` or `prompt` is required. |
+| `language` | `Option<ScrapeExecuteLanguage>` | Execution language: `Python`, `Node`, `Bash`. Default: `Node`. |
+| `timeout` | `Option<u32>` | Execution timeout in seconds. |
+| `origin` | `Option<String>` | Origin label. Auto-set to `"rust-sdk@{version}"`. |
+
+### Related methods
+
+- `client.stop_interaction(job_id)` — Stop the browser session and release resources.
+
+## Notes
+
+- The SDK uses **snake_case** for struct fields. Serialization to the API uses camelCase via `#[serde(rename_all = "camelCase")]`.
+- Options structs use `#[derive(Default)]` — construct with `..Default::default()` for unset fields.
+- Method signatures accept `impl Into<Option<T>>`, so you can pass the options struct directly without wrapping in `Some()`.
+- All public types are re-exported from the crate root (`use firecrawl::*`).
+- **Deprecated aliases** (do not use in new code):
+  - `scrape_execute()` → use `interact()`
+  - `stop_interactive_browser()` / `delete_scrape_browser()` → use `stop_interaction()`
+
+## Source Of Truth
+
+- SDK: `firecrawl/apps/rust-sdk/src/v2/client.rs`, `firecrawl/apps/rust-sdk/src/v2/scrape.rs`, `firecrawl/apps/rust-sdk/src/v2/search.rs`
+- OpenAPI: `firecrawl-docs/api-reference/v2-openapi.json`