robots.txt
See which AI crawlers other sites block →# Crawling and AI usage are welcome. Content Signals per https://contentsignals.org
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Googlebot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Bingbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: DuckDuckBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: YandexBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Applebot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Claude-Web
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Amazonbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
User-agent: Meta-ExternalAgent
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/
Sitemap: https://buildful.ai/sitemap.xml
llms.txt
Compare with other sites' llms.txt files →# Buildful
> The AI coding agent that builds your change, tests it in a real browser and opens a pull request. A Claude Code alternative for $10 a month.
Every page below is also served as Markdown to any request with `Accept: text/markdown`. The HTML pages at https://buildful.ai are the ones to cite.
## Pages
- [Buildful: AI coding agent, 1,000 tasks for $10 a month](https://buildful.ai/index.md): The AI coding agent that builds your change, tests it in a real browser and opens a pull request. A Claude Code alternative for $10 a month.
- [Pricing: an AI coding agent for $10 a month (1,000 tasks) · Buildful](https://buildful.ai/pricing.md): Pro is $10 a month for 1,000 Smart Mode tasks, about a cent a task, each on the open-weight model Buildful picks for it. Get access to Claude and GPT with prepaid credit, or on your own API key. Team is $40 a month for 3,000 Smart Mode tasks with unlimited teammates. Try 3 tasks free, no card needed.
- [About · Buildful](https://buildful.ai/about.md): Buildful is made by the team behind Hashnode and Bug0, so the next 100 million software creators can ship real software, tested and delivered as pull requests to their own GitHub.
- [Brand · Buildful](https://buildful.ai/brand.md): The Buildful logo, colors and type, with the rules for using them. Download the kit, or give your AI agent the Markdown version.
- [Terms of Service · Buildful](https://buildful.ai/terms.md): The terms that govern your use of Buildful: accounts, acceptable use, your repos and content, plans and payment, and liability.
- [Privacy Policy · Buildful](https://buildful.ai/privacy.md): What Buildful collects, why, who it is shared with, and the controls you have over your data.
- [Compare Buildful with Claude Code, Cursor, GitHub Copilot, Lovable and more](https://buildful.ai/compare.md): How Buildful compares with Claude Code, Cursor, GitHub Copilot, Codex, Lovable, Bolt, Base44, Replit and Emergent: what each one is, where you work, what you get back, and what a month costs.
- [Background Coding Agent on Open-Weight Models | Buildful](https://buildful.ai/background-coding-agent.md): Give Buildful a task, close the tab, and review a tested pull request on your GitHub repo. Runs on open-weight models in the cloud, from $10 a month.
- [Open-Weight Models for Coding, in the Cloud | Buildful](https://buildful.ai/open-weight-models.md): Open-weight models in the cloud, with no GPU or setup. Smart Mode is included. On Pro, pick Kimi K3, GLM 5.3 or DeepSeek too. Every change is a tested PR.
- [Blog · Buildful](https://buildful.ai/blog.md): Notes and updates from the team building Buildful, coding superintelligence for everyone: describe a change, get a tested pull request on your GitHub repo.
- [Changelog · Buildful](https://buildful.ai/changelog.md): What's new in Buildful, the AI coding agent that opens tested pull requests on your GitHub repo: new features, models and fixes, by date.
- [Knowledge base · Buildful](https://buildful.ai/knowledge-base.md): Plain answers about AI coding tools: what each plan costs, what the free plans include, and how the tools compare.
## Comparisons
- [Claude Code alternative for $10: Buildful vs Claude Code](https://buildful.ai/compare/claude-code.md): Claude Code is an agent you steer, mostly on your own computer; Buildful takes a described change and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Cursor alternative: Buildful vs Cursor](https://buildful.ai/compare/cursor.md): Cursor helps you code in its editor, with cloud agents on the side; Buildful takes a described change and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Lovable alternative: Buildful vs Lovable](https://buildful.ai/compare/lovable.md): Lovable builds and hosts an app for you; Buildful works on your own GitHub repo and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Replit alternative: Buildful vs Replit](https://buildful.ai/compare/replit.md): Replit builds, runs and hosts in one workspace; Buildful works on your own GitHub repo and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Emergent alternative: Buildful vs Emergent](https://buildful.ai/compare/emergent.md): Emergent builds and deploys an app for you from a chat; Buildful works on your own GitHub repo and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Base44 alternative: Buildful vs Base44](https://buildful.ai/compare/base44.md): Base44 builds and hosts an app for you from a chat; Buildful works on your own GitHub repo and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Bolt alternative: Buildful vs Bolt](https://buildful.ai/compare/bolt.md): Bolt builds and hosts a site or app from a prompt; Buildful works on your own GitHub repo and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [GitHub Copilot alternative: Buildful vs GitHub Copilot](https://buildful.ai/compare/github-copilot.md): GitHub Copilot helps you code in your editor and on GitHub; Buildful takes a described change and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Codex alternative: Buildful vs OpenAI Codex](https://buildful.ai/compare/codex.md): Codex is OpenAI's coding agent in ChatGPT, on your computer or in the cloud; Buildful hands you a tested pull request for $10 a month. When to stay, when to switch, and what each costs.
- [v0 alternative: Buildful vs v0](https://buildful.ai/compare/v0.md): v0 builds apps in a chat, Next.js first, with a live preview, and publishes to Vercel; Buildful takes a described change on any repo, in any stack, and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Windsurf alternative: Buildful vs Windsurf](https://buildful.ai/compare/windsurf.md): Windsurf, now called Devin Desktop, is an AI code editor on your computer; Buildful takes a described change and hands you a tested pull request. When to stay, when to switch, and what each costs.
- [Devin AI alternative: Buildful vs Devin](https://buildful.ai/compare/devin.md): Devin and Buildful both take a task and open a pull request. Devin's plans give a usage quota; Buildful gives 1,000 tasks for $10 a month. When to stay, when to switch, and what each costs.
- [Conductor.build alternative: Buildful vs Conductor](https://buildful.ai/compare/conductor.md): Meta bought Conductor, and Conductor Cloud shuts down on November 20. Buildful runs coding tasks in cloud sandboxes and opens tested pull requests, $10 a month.
## Blog
- [HTML-in-Canvas in Chrome 157: how it works · Buildful](https://buildful.ai/blog/html-in-canvas.md): Chrome 157 ships HTML-in-Canvas: a canvas that draws live, accessible HTML. How it works, working code, what changed and which libraries broke.
- [Claude Code mobile and open-weight models · Buildful](https://buildful.ai/blog/open-weight-coding-agent-mobile.md): Use Claude Code, Codex or Cursor from your phone, or text Buildful a task. An open-weight model builds it in the cloud with your laptop off, for $10 a month.
- [Buildful Pass: a coding plan for Kimi K3, DeepSeek and GLM · Buildful](https://buildful.ai/blog/buildful-pass.md): Buildful Pass is a $30 coding plan with $80 a month of Kimi K3, DeepSeek V4.1 Flash, GLM 5.3 Flash and MiniMax M3.1 Flash, plus every model you can pick on Buildful.
- [Connect Linear to Claude Code, or run Claude in the cloud · Buildful](https://buildful.ai/blog/claude-code-linear-issues.md): Connect Linear to Claude Code with MCP, or run Claude Opus 5.5 on labeled Linear issues in the cloud and get a pull request with checks run and a QA recording.
- [AI coding agent for everyone: introducing Buildful · Buildful](https://buildful.ai/blog/introducing-buildful.md): Buildful is an AI coding agent: describe a change in plain words, get a tested pull request on your GitHub repo. 1,000 tasks for $10 a month.
## Changelog
- [Text your tasks over iMessage, plus Particle-1 and a $10 Buildful Pass · Buildful](https://buildful.ai/changelog/imessage-particle-1-buildful-pass.md): Text tasks to Buildful over iMessage and get the pull request back by text. Also new: Particle-1, and Buildful Pass now costs $10 a month.
- [Repo skills as slash commands, a reasoning effort picker and GPT-6.1 Terra · Buildful](https://buildful.ai/changelog/repo-skills-slash-commands.md): Type / in Buildful's task box to run your repo's agent skills. Also new: a reasoning effort picker, GPT-6.1 Terra and drop-anywhere attachments.
- [Every pull request now links back to the task that made it · Buildful](https://buildful.ai/changelog/ai-pull-request-task-link.md): Every AI pull request Buildful opens now links to the task that made it, so your team can review the prompt, the conversation and the QA recording.
- [Introducing Buildful Pass for open-weight models · Buildful](https://buildful.ai/changelog/buildful-pass.md): Buildful Pass is a $10 a month add-on for Pro and Team that gives you $80 of usage a month on four open-weight coding models.
- [Kimi K3.1 Pro and its Highspeed version are now available · Buildful](https://buildful.ai/changelog/kimi-k3-1-pro.md): Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are in Buildful's model picker on Pro and Team, along with a new Settings page for your profile.
- [Pull requests and QA recordings now sit in one Results panel · Buildful](https://buildful.ai/changelog/results-panel-qa-recordings.md): Buildful's Results panel puts each task's pull requests, QA recordings of the browser test, models and Slack or Linear source in one place.
- [You can now start private tasks your team can't see · Buildful](https://buildful.ai/changelog/private-tasks.md): You can now start a private task in Buildful that only you can see, even in a team. It stays out of your team's task list, archive and search.
- [Test a task's pull request on your own machine with one command · Buildful](https://buildful.ai/changelog/checkout-pull-request-locally.md): Buildful now gives you one command to run a task's pull request on localhost, and a git command to check out its branch in your own clone.
- [AI code review now runs before every Smart Mode pull request · Buildful](https://buildful.ai/changelog/ai-code-review-before-pull-request.md): Buildful now runs AI code review on every Smart Mode task: a second, independent model checks the code before the pull request opens.
- [DeepSeek V4.1 Flash now works, and we redact your env vars · Buildful](https://buildful.ai/changelog/deepseek-v4-1-flash.md): Run coding tasks on DeepSeek V4.1 Flash in Buildful on Pro or Team. Your repo's env var values are now redacted from the agent's replies and PRs.
- [Added support for Grok 4.7 and your own Google API key · Buildful](https://buildful.ai/changelog/grok-4-7.md): Run coding tasks on xAI's Grok 4.7 in Buildful on Pro or Team. Also new: your own Google API key for Gemini, and Linear issues routed by label.
- [The model picker now has search · Buildful](https://buildful.ai/changelog/model-picker-search.md): Type to find a model in Buildful's task composer. Enter now sends your message, and a starting task shows each setup step and the memory it loaded.
- [Meta's Muse Spark Open is now available in Buildful · Buildful](https://buildful.ai/changelog/muse-spark-open.md): Run coding tasks on Meta's Muse Spark Open, the open-weight model, in Buildful on Pro or Team. You can also archive finished tasks now.
- [Pasted screenshots now show as thumbnails before you send · Buildful](https://buildful.ai/changelog/paste-screenshots-into-a-task.md): Paste or drop a screenshot into a Buildful task and it shows as a thumbnail before you send. Screenshot to code: show the bug, describe the fix.
- [Tasks now take PDFs, logs and code files, along with images · Buildful](https://buildful.ai/changelog/attach-pdfs-and-files.md): Attach PDFs, logs, code and data files to a Buildful task, along with images. The coding agent reads a PDF spec before it writes code.
- [Quick Mode is here for small, fast fixes · Buildful](https://buildful.ai/changelog/quick-mode.md): Quick Mode is Buildful's fast mode for small fixes: it runs your repo's own checks and skips the browser test. Teams in India can now pay in rupees.
- [New accounts now get a guide to their first task · Buildful](https://buildful.ai/changelog/welcome-guide.md): New Buildful accounts get a short welcome guide to their first task, from connecting GitHub to merging the pull request. Reopen it from the help menu.
- [GitHub sign-in is now available · Buildful](https://buildful.ai/changelog/sign-in-with-github.md): You can now sign in to Buildful, the GitHub coding agent, with your GitHub account. Repo access is a separate step through the GitHub App.
- [You can now steer the agent while it works · Buildful](https://buildful.ai/changelog/steer-coding-agent-while-it-works.md): You can now steer the Buildful coding agent mid-task: add a note to a running task and the agent reads it at its next step, without starting over.
- [We doubled every task's sandbox to 4 vCPUs and 8 GB of RAM · Buildful](https://buildful.ai/changelog/ai-agent-sandbox-4-vcpus-8gb.md): Every Buildful task now runs in an AI agent sandbox with 4 vCPUs and 8 GB of RAM, twice the earlier size. Plus a two-column sidebar.
- [You can now try Buildful without a card · Buildful](https://buildful.ai/changelog/free-ai-coding-agent-trial.md): Buildful's first 3 tasks are free, with no card. A free AI coding agent to try on your own GitHub repo before you pick a plan.
- [Claude Opus 5.5 is now available in Buildful · Buildful](https://buildful.ai/changelog/claude-opus-5-5.md): Run coding tasks on Claude Opus 5.5 in Buildful on Pro or Team, paid with prepaid credit or your own Anthropic key. Linear automations can use it too.
- [Team is now $40 a month flat, with unlimited members · Buildful](https://buildful.ai/changelog/team-plan-pricing.md): Buildful's Team plan is now $40 a month in total with unlimited members, instead of a price per seat. Every member shares 3,000 tasks a month.
- [Team tasks now show who started them · Buildful](https://buildful.ai/changelog/see-who-started-a-task.md): Team tasks in Buildful now show the name and avatar of the person who started them, and of whoever sent each follow-up message.
- [Task search is here, and Pro can now add 1,000 more tasks · Buildful](https://buildful.ai/changelog/task-search-and-filters.md): Search your Buildful tasks and filter them by status or repo. On Pro, add 1,000 tasks for $10 instead of waiting out your monthly usage limit.
## Knowledge base
- [Conductor vs Claude Code: parallel agents, worktrees, price](https://buildful.ai/knowledge-base/conductor-vs-claude-code.md): Conductor was a Mac app that ran Claude Code in parallel worktrees. Claude Code now does most of that itself. What each did, how sign-in worked, what to use.
- [Claude Code worktrees: run agents in parallel](https://buildful.ai/knowledge-base/claude-code-worktrees.md): Run Claude Code agents in parallel with git worktrees: the --worktree flag, the desktop app's Worktree mode, Codex worktrees, setup gotchas and cleanup.
- [Migrate from Conductor Cloud: export and move your setup](https://buildful.ai/knowledge-base/conductor-cloud-migration.md): Conductor Cloud goes read-only November 13 and shuts down November 20. How to export your workspaces, and move your setup scripts and env vars somewhere else.
- [Conductor pricing: Free, Pro $50 and Teams $60 a user](https://buildful.ai/knowledge-base/conductor-pricing.md): Conductor (conductor.build) had Free, Pro at $50 a month and Teams at $60 a user. Since Meta bought it, none is sold. What each plan included, and refunds.
- [Conductor alternatives: local apps and cloud agents compared](https://buildful.ai/knowledge-base/conductor-alternatives.md): Conductor alternatives for both kinds of user: desktop apps that run agents in parallel worktrees, and cloud agents to replace Conductor Cloud by November 20.
- [Conductor.build shutdown: Meta deal, dates and what to do](https://buildful.ai/knowledge-base/conductor-shutdown.md): Meta bought Conductor on November 4, 2026. Its cloud goes read-only November 13 and shuts down November 20. Every date, how to export, and what replaces it.
- [Devin alternatives 2026: Codex, Copilot, Cursor and more](https://buildful.ai/knowledge-base/devin-alternatives.md): Devin alternatives that take a task and open a pull request: Codex, Copilot, Cursor Cloud Agents, Claude Code, Factory and Buildful. Where each runs and costs.
- [Devin Review: Cognition's AI code review tool explained](https://buildful.ai/knowledge-base/devin-review.md): Devin Review is Cognition's AI code review tool for pull requests. How to open a PR in it, what Bug Catcher and Auto-Review do, where it works, what it costs.
- [Devin vs Cursor: cloud agents, editors and pricing](https://buildful.ai/knowledge-base/devin-vs-cursor.md): Devin's cloud agent comes with Pro at $20 a month. Cursor's Cloud Agents start at Premium, $30. Where each runs, models, pricing, Slack, Linear and GitHub.
- [Devin CLI: install it, main commands, local vs cloud](https://buildful.ai/knowledge-base/devin-cli.md): The Devin CLI is Cognition's terminal coding agent. How to install it on macOS, Linux and Windows, its main commands, and how it hands work to Devin Cloud.
- [Devin Desktop: what it is and what happened to Windsurf](https://buildful.ai/knowledge-base/devin-desktop.md): Devin Desktop is Windsurf's new name since June 2, 2026. What changed, how Devin Local replaced Cascade, which plans include it, and how to install it.
- [Cursor pricing 2026: Free, Plus $8, Premium $30, Ultra $200](https://buildful.ai/knowledge-base/cursor-pricing.md): Cursor pricing moved to The X Subscription: Free, Plus $8, Premium $30, Super $100, Ultra $200. What happened to Cursor Pro and the ₹649 Start plan in India.
- [Is Cursor free? Cursor free plan and its limits](https://buildful.ai/knowledge-base/is-cursor-free.md): Cursor has a $0 free plan with Agent, Chat and Tab on Cursor's own models. What the Cursor free plan leaves out, how its limits work, and the lowest paid plan.
- [OpenCode Go pricing: $10 a month, models and limits](https://buildful.ai/knowledge-base/opencode-go.md): OpenCode Go costs $10 a month, or $40 for Go Plus, for 30 coding models. Which models it includes, the per-model monthly limits, and how the 5-hour cap works.
- [Claude Pro vs Max: price, limits and Fable compared](https://buildful.ai/knowledge-base/claude-pro-vs-max.md): Claude Pro is $20 a month; Max is $100 or $200 for 5x or 20x Pro's usage. How the limits, Fable access and API credits differ, and when to upgrade.
- [Claude Max plan 2026: price, limits and who it's for](https://buildful.ai/knowledge-base/claude-max-plan.md): Claude Max costs $100 a month for 5x Pro's usage or $200 for 20x. What each tier includes, how the weekly and Fable limits work, and who should pay for it.
- [OpenCode vs Claude Code: models, price and license](https://buildful.ai/knowledge-base/opencode-vs-claude-code.md): OpenCode is a free, MIT-licensed agent for any model. Claude Code is Anthropic's, from $20 a month with Claude Pro. Models, price and cloud sessions compared.
- [What is Devin AI? Cognition's autonomous coding agent](https://buildful.ai/knowledge-base/what-is-devin-ai.md): Devin AI is Cognition's autonomous coding agent. It plans, codes, tests and opens pull requests in its own cloud machine. Who makes it, how it works, its price.
- [Factory Droid: install the CLI, custom droids and models](https://buildful.ai/knowledge-base/factory-droid.md): Droid is Factory AI's coding agent. How to install the Droid CLI, the built-in and custom droids, droid exec, which models it runs, and how it's billed.
- [Devin vs Claude Code: where they run, models and price](https://b