--- type: "firecrawl-provider" description: "DEV Community (dev.to), the developer blogging community run on Forem: read any article by URL as Markdown with author, organization, dates, tags, reading time and reaction and comment counts; list articles by tag, author or organization, optionally the top posts of the last N days; and read an article's comment threads. Uses the public, keyless Forem API." use_when: "DEV Community (dev.to), the developer blogging community run on Forem: read any article by URL as Markdown with author, organization, dates, tags, reading time and reaction and comment counts; list articles by tag, author or organization, optionally the top posts of the last N days; and read an article's comment threads. Uses the public, keyless Forem API." categories: "Social" capabilities: 3 credits_per_call: 5 --- # DEV Community on Firecrawl Alexandria DEV Community (dev.to), the developer blogging community run on Forem: read any article by URL as Markdown with author, organization, dates, tags, reading time and reaction and comment counts; list articles by tag, author or organization, optionally the top posts of the last N days; and read an article's comment threads. Uses the public, keyless Forem API. - Categories: Social - Category index: [Social category](https://alexandria.firecrawl.dev/agents/categories/social) - Provider key: `dev-to` - Access: Firecrawl credits - Cost: 5 credits per call ## More - [Human guide](https://www.firecrawl.dev/app/alexandria/dev-to) - [OpenAPI spec](https://alexandria.firecrawl.dev/agents/providers/dev-to/openapi.json) ## Capabilities - [Get article](https://alexandria.firecrawl.dev/agents/providers/dev-to/articles/get_article): One dev.to article by URL (or username and slug): id, title, teaser, author, organization, publication and edit times, tags, reading time, reaction and comment counts, canonical URL, cover image and the full body as the author's Markdown. max_chars truncates the body. - [Get comments](https://alexandria.firecrawl.dev/agents/providers/dev-to/articles/get_comments): The comment threads of one dev.to article, by article URL, username and slug, or article_id: each comment's id, parent id, depth, author, creation time, permalink and body as light Markdown, flattened in thread order (a parent before its replies). Comments from deleted accounts have a null author. - [List articles](https://alexandria.firecrawl.dev/agents/providers/dev-to/articles/list_articles): Published dev.to articles, newest first, filtered by tag, by author or organization handle, or both; with top=N, the most-reacted articles of the last N days instead. Rows carry id, URL, title, teaser, author, organization, publication time, tags, reading time and reaction and comment counts (no body; read one with get_article). page and per_page (up to 100) paginate; next_page is set while a full page came back. An unknown handle or an unused tag returns no rows. ## 1. Choose this provider when DEV Community (dev.to), the developer blogging community run on Forem: read any article by URL as Markdown with author, organization, dates, tags, reading time and reaction and comment counts; list articles by tag, author or organization, optionally the top posts of the last N days; and read an article's comment threads. Uses the public, keyless Forem API. ## 2. Minimal request Call `POST https://api.firecrawl.dev/v2/scrape` with `{ alexandria: { provider, capability, options } }`. For a batch, send `{ alexandria: [...] }` with up to 10 calls. ```json { "provider": "dev-to", "capability": "articles/get_article", "options": { "max_chars": 1200, "url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n" } } ``` ## 3. Add provider options Use only the options needed for the task: - `max_chars` (number): Truncate content to this many characters; the full body is returned when omitted. Example: `200` - `slug` (string): Article slug (the URL's second segment); use with username instead of url. Example: `` - `url` (string): Article URL, e.g. https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n. Organization URLs (https://dev.to/aws-builders/...) work the same way. Pattern: ^https?://. Example: `` - `username` (string): User or organization handle (the URL's first segment); use with slug instead of url. Example: `` ## 4. Request through your preferred interface ### JavaScript ```javascript const result = await firecrawl.scrape({ alexandria: { provider: "dev-to", capability: "articles/get_article", options: { max_chars: 1200, url: "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n", }, }, }); ``` ### Python ```python result = firecrawl.scrape_alexandria({ "provider": "dev-to", "capability": "articles/get_article", "options": { "max_chars": 1200, "url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n" } }) ``` ### cURL ```sh curl https://api.firecrawl.dev/v2/scrape \ -H "Authorization: Bearer $FIRECRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "alexandria": { "provider": "dev-to", "capability": "articles/get_article", "options": { "max_chars": 1200, "url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n" } } }' ``` ### CLI ```sh firecrawl scrape 'dev-to/articles/get_article' \ --options '{"max_chars":1200,"url":"https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n"}' ``` ### MCP Call the FCX MCP retrieve tool with this object: ```json { "provider": "dev-to", "capability": "articles/get_article", "options": { "max_chars": 1200, "url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n" } } ``` Ask for only the returned fields needed by the task. ## 5. Full request shape ```json { "provider": "dev-to", "capability": "articles/get_article", "options": { "max_chars": 1200, "url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n" } } ``` ## 6. Response data The response includes `success`, `provider`, `capability`, `creditsCost` and `data`. This example shows the provider payload in `data`: ```json { "author": { "name": "ArshTechPro", "username": "arshtechpro" }, "canonical_url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n", "chars": 7802, "comments_count": 2, "content": "If you use Claude Code, Codex, or another AI coding agent in your terminal, you have probably hit this wall: the agent is busy on one task, you want to start a second one, and now you are juggling branches, stashing changes, and opening five terminal windows that all look the same.\n\nOrca is a desktop app built to solve exactly that. This article explains what it is, how it differs from Cursor, what it costs, and where it falls short.\n\n## What is Orca?\n\nOrca calls itself an **ADE**, an Agent Development Environment. The idea is simple:\n\n- A traditional **IDE** is built around one human typing code.\n- An **ADE** is built around you *supervising several AI agents* that write code at the same time.\n\nIn practice, Orca is a desktop app (macOS, Windows, Linux) where every task you start gets:\n\n1. Its own **git worktree** (an isolated copy of your repo on its own branch)\n2. Its own **agent terminal** (Claude Code, Codex, Gemini, Cursor CLI, and so on)\n3. Its own **browser tab** for previewing the app\n\n\n## A quick primer on git worktrees\n\nWorktrees are the core idea behind Orca, so it is worth a 30-second refresher.\n\nNormally, one repo folder has one checked-out branch. A worktree lets you ", "cover_image": "https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fy45mqxyofz0hyp0wscvw.png", "description": "If you use Claude Code, Codex, or another AI coding agent in your terminal, you have probably hit...", "edited_at": "2026-09-20T06:04:46Z", "id": 4697838, "language": "en", "observed_at_ms": 1794100000000, "organization": null, "published_at": "2026-09-20T06:00:36Z", "reactions_count": 20, "reading_time_minutes": 5, "tags": [ "ai", "productivity", "tooling", "agents" ], "title": "Orca: The Agent Development Environment for Running AI Coding Agents in Parallel", "truncated": true, "url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n" } ``` ## API reference-derived contract The following capability contract is generated from the same normalized Alexandria API reference exposed in the API spec. ### Get article - Capability: `articles/get_article` - Description: One dev.to article by URL (or username and slug): id, title, teaser, author, organization, publication and edit times, tags, reading time, reaction and comment counts, canonical URL, cover image and the full body as the author's Markdown. max_chars truncates the body. - Instructions: When given a dev.to article link (https://dev.to/{user}/{slug}, including organization paths like https://dev.to/aws-builders/...) and you need its text or metadata. - Cost: 5 credits per call - Capability file: [Get article](https://alexandria.firecrawl.dev/agents/providers/dev-to/articles/get_article) Accepted options: - `max_chars` (number): Truncate content to this many characters; the full body is returned when omitted. Example: `200` - `slug` (string): Article slug (the URL's second segment); use with username instead of url. Example: `` - `url` (string): Article URL, e.g. https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n. Organization URLs (https://dev.to/aws-builders/...) work the same way. Pattern: ^https?://. Example: `` - `username` (string): User or organization handle (the URL's first segment); use with slug instead of url. Example: `` Response schema example: ```json { "author": { "name": "ArshTechPro", "username": "arshtechpro" }, "canonical_url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n", "chars": 7802, "comments_count": 2, "content": "If you use Claude Code, Codex, or another AI coding agent in your terminal, you have probably hit this wall: the agent is busy on one task, you want to start a second one, and now you are juggling branches, stashing changes, and opening five terminal windows that all look the same.\n\nOrca is a desktop app built to solve exactly that. This article explains what it is, how it differs from Cursor, what it costs, and where it falls short.\n\n## What is Orca?\n\nOrca calls itself an **ADE**, an Agent Development Environment. The idea is simple:\n\n- A traditional **IDE** is built around one human typing code.\n- An **ADE** is built around you *supervising several AI agents* that write code at the same time.\n\nIn practice, Orca is a desktop app (macOS, Windows, Linux) where every task you start gets:\n\n1. Its own **git worktree** (an isolated copy of your repo on its own branch)\n2. Its own **agent terminal** (Claude Code, Codex, Gemini, Cursor CLI, and so on)\n3. Its own **browser tab** for previewing the app\n\n\n## A quick primer on git worktrees\n\nWorktrees are the core idea behind Orca, so it is worth a 30-second refresher.\n\nNormally, one repo folder has one checked-out branch. A worktree lets you ", "cover_image": "https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fy45mqxyofz0hyp0wscvw.png", "description": "If you use Claude Code, Codex, or another AI coding agent in your terminal, you have probably hit...", "edited_at": "2026-09-20T06:04:46Z", "id": 4697838, "language": "en", "observed_at_ms": 1794100000000, "organization": null, "published_at": "2026-09-20T06:00:36Z", "reactions_count": 20, "reading_time_minutes": 5, "tags": [ "ai", "productivity", "tooling", "agents" ], "title": "Orca: The Agent Development Environment for Running AI Coding Agents in Parallel", "truncated": true, "url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n" } ``` ### Get comments - Capability: `articles/get_comments` - Description: The comment threads of one dev.to article, by article URL, username and slug, or article_id: each comment's id, parent id, depth, author, creation time, permalink and body as light Markdown, flattened in thread order (a parent before its replies). Comments from deleted accounts have a null author. - Instructions: To read the discussion under a dev.to article, e.g. reader questions and the author's replies. - Cost: 5 credits per call - Capability file: [Get comments](https://alexandria.firecrawl.dev/agents/providers/dev-to/articles/get_comments) Accepted options: - `article_id` (number): Forem article id (get_article's or list_articles' id); saves one request. Example: `10` - `slug` (string): Article slug (the URL's second segment); use with username instead of url. Example: `` - `url` (string): Article URL, e.g. https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n. Organization URLs (https://dev.to/aws-builders/...) work the same way. Pattern: ^https?://. Example: `` - `username` (string): User or organization handle (the URL's first segment); use with slug instead of url. Example: `` Response schema example: ```json { "article_id": 4697838, "article_url": "https://dev.to/arshtechpro/orca-explained-the-agent-development-environment-for-running-ai-coding-agents-in-parallel-440n", "comments": [ { "author": { "name": "Minh Tran", "username": "minhtran83" }, "body": "Orca won't solve it. That is normal git conflict problem. You need to split your tasks independent enough to run in parallel, otherwise it is a critical task", "created_at": "2026-09-27T00:40:29Z", "depth": 0, "id": "3fmfh", "parent_id": null, "url": "https://dev.to/minhtran83/comment/3fmfh" } ], "count": 1, "observed_at_ms": 1794100000000 } ``` ### List articles - Capability: `articles/list_articles` - Description: Published dev.to articles, newest first, filtered by tag, by author or organization handle, or both; with top=N, the most-reacted articles of the last N days instead. Rows carry id, URL, title, teaser, author, organization, publication time, tags, reading time and reaction and comment counts (no body; read one with get_article). page and per_page (up to 100) paginate; next_page is set while a full page came back. An unknown handle or an unused tag returns no rows. - Instructions: To find recent or top dev.to posts on a topic (tag=rust), everything a writer or organization (username=aws-builders) published, or to page through them before reading one with get_article. - Cost: 5 credits per call - Capability file: [List articles](https://alexandria.firecrawl.dev/agents/providers/dev-to/articles/list_articles) Accepted options: - `page` (number): Page number, from 1 (default 1). Example: `10` - `per_page` (number): Articles per page (default 30). Example: `10` - `tag` (string): Tag without #, e.g. rust, webdev, ai. Example: `` - `top` (number): Return the most popular articles published in the last N days instead of the newest. Example: `10` - `username` (string): User or organization handle, e.g. ben or aws-builders. Example: `` Response schema example: ```json { "articles": [ { "author": { "name": "Jesus Aguirre", "username": "jeaguirre" }, "comments_count": 0, "description": "A Pod can remain Pending even when an Amazon EKS cluster has healthy nodes. One common reason is that...", "id": 4994090, "organization": { "name": "AWS Community Builders", "username": "aws-builders" }, "published_at": "2026-11-07T15:51:40Z", "reactions_count": 6, "reading_time_minutes": 11, "tags": [ "containers", "kubernetes", "aws", "architecture" ], "title": "Kubernetes CPU Requests in Amazon EKS Auto Mode", "url": "https://dev.to/aws-builders/kubernetes-cpu-requests-in-amazon-eks-auto-mode-421" }, { "author": { "name": "Anirban Das", "username": "dasanirban834" }, "comments_count": 0, "description": "Overview of NexOps NexOps is a cloud operations assistant that lets users ask questions...", "id": 4964424, "organization": { "name": "AWS Community Builders", "username": "aws-builders" }, "published_at": "2026-11-07T12:26:15Z", "reactions_count": 4, "reading_time_minutes": 11, "tags": [ "ai", "aws", "cloud", "devops" ], "title": "NexOps: Build CloudOps Agent Using Strands+Bedrock+Terraform", "url": "https://dev.to/aws-builders/nexops-an-ai-assistant-for-aws-cloud-operations-37i4" }, { "author": { "name": "Mursal Furqan Kumbhar", "username": "mursalfk" }, "comments_count": 2, "description": "Ciao Amici 👋 Every hiking trail in the Alps has a map at the trailhead. A good one shows you the...", "id": 4993366, "organization": { "name": "AWS Community Builders", "username": "aws-builders" }, "published_at": "2026-11-07T11:48:28Z", "reactions_count": 11, "reading_time_minutes": 30, "tags": [ "machinelearning", "aws", "ai", "beginners" ], "title": "How to Master AWS for AI?", "url": "https://dev.to/aws-builders/how-to-master-aws-for-ai-3la4" }, { "author": { "name": "Pin Xiong", "username": "pinxiongcn" }, "comments_count": 5, "description": "Session files stored fourteen messages while the model saw six. A restart keeps your name, and seven turns later the same conversation forgets it.", "id": 4991329, "organization": { "name": "AWS Community Builders", "username": "aws-builders" }, "published_at": "2026-11-07T01:50:54Z", "reactions_count": 4, "reading_time_minutes": 13, "tags": [ "ai", "agents", "strands", "aws" ], "title": "It Remembers Across Restarts — and Forgets Mid-Conversation", "url": "https://dev.to/aws-builders/it-remembers-across-restarts-and-forgets-mid-conversation-1ehh" }, { "author": { "name": "xbill", "username": "xbill" }, "comments_count": 0, "description": "llama.cpp, vLLM, SGLang, mistral.rs, a plain PyTorch engine and LiteRT-LM serve the same 4-bit Gemma 4 E2B on one g6.4xlarge, measured with the same prompts, the same 1-to-64-request sweep and the same GSM8K and BFCL questions. Answers are level on every engine; vLLM with Google's drafter is the fastest at every load, up to 4,516 output tokens per second.", "id": 4990070, "organization": { "name": "AWS Community Builders", "username": "aws-builders" }, "published_at": "2026-11-06T18:41:59Z", "reactions_count": 3, "reading_time_minutes": 13, "tags": [ "aws", "ec2", "vllm", "nvidia" ], "title": "Six Serving Engines on One EC2 G6: Gemma 4 E2B on an NVIDIA L4", "url": "https://dev.to/aws-builders/six-serving-engines-on-one-ec2-g6-gemma-4-e2b-on-an-nvidia-l4-3ff3" } ], "count": 5, "next_page": 2, "observed_at_ms": 1794100000000, "page": 1, "per_page": 5, "tag": null, "top": null, "username": "aws-builders" } ```