Backengine

Announcing our $5.7m Seed RoundBuild anything with AI.Free forever.Build apps, agents and startups on the best AI models.No credit card or API key required.Build apps, agents and startups on the best AI models.No credit card or API key required.Claude Sonnet 4.6Web appSubmitTask managerPoll appRecipe collectionFinance trackerHabit trackerTrusted by teams atcto.new - Completely free AI code agent --- PricingDocsBlogContactcto benchSign up for freeSign InIt's freeGPT-5.2, Claude Sonnet 4.5, Gemini 3 Pro PreviewFreeToken usageUnlimitedAdditional team membersUnlimitedAll API and MCP IntegrationsFreeSOC2 ComplianceFreeTotal:$0.00Get started for FreeGet started today, no credit card required. Check our terms of service for more information.FAQsWhat models does cto.new use?Why is cto.new better than other AI software engineers?How can you offer cto.new completely for free?What tools does cto.new work with?What are the limitations of your free plan?Do I still own my own codebase?What does 'fair use' mean?Why should I trust cto.new with my work codebase?What's Premium?All rights reserved 2025,Era Technologies Holdings Inc.CompanyDocumentationBlogTrustSign inSocialGithubDiscordX (Twitter)LinkedInLegalPrivacyTermsCookiesPreferencesNotice at Collection × We use cookies or similar technologies for technical purposes and, with your consent, for other purposes as specified in the cookie policy. Use the “Accept” button to consent. Use the “Reject” button to continue without accepting.Press again to continue 0/1Learn more and customizeRejectAccept --- BlogAll CategoriesAINewsFeaturedMar 3, 2026Why we bet on ConvexWhen we were building the AI web app builder experience for cto.new, one question kept coming up: what backend should we bet our user experience on?Simon SpurrierLatestTechnologyAIFeb 26, 2026We Built an AI SRE Agent in Two DaysWe wanted a full-time SRE — but we're a small startup with limited resources. The ideal: a fully autonomous system that finds and fixes production issues without human involvement.Simon SpurrierAIFeb 4, 202650 days of cto benchWe shipped cto bench because our friends kept asking for it. They wanted to know which models our users preferred for real software engineering tasks. The results were often surprising.Simon SpurrierAIJan 30, 2026Choosing an AI sandbox provider in 2026Going into 2026, it’s time for an upgrade, and that means handing off our sandbox infrastructure to one of the many startups that have sprung up to specialise in this part of the stack.Simon SpurrierAIJan 11, 2026Making tokens affordableFor now, LLM inference is quite expensive. It’s getting cheaper, but your near unrestricted access to the frontier of AI on a daily basis costs someone, somewhere quite a lot of money.Simon SpurrierAIDec 31, 2025cto.new 2025 wrappedThanks for using cto.new in 2025! It’s been an incredible almost 3 months since we launched. We’re making thousands of PRs every day, we’ve used more than 300 billion frontier model tokens, shipped to over 10,000 codebases, and we’re just getting started.Michael LuddenAIDec 24, 202510 min readUsing Cursor IDE with cto.new as Your Background AgentCursor is an incredible IDE for local, AI-assisted development, but there's a pricing problem - especially when it comes to background agents. The solution? Connect cto.new via MCP server. This approach lets you offload heavy lifting to a free, world-class coding agent right from your primary, local IDE experience, without adding bloat.Michael LuddenAIDec 19, 2025Introducing cto bench: The ground truth code agent benchmarkMost AI benchmarks are built backwards. Someone sits down, dreams up hard problems, and then measures how well agents solve them. The results are interesting, sure. But they don't always tell you what matters: how agents perform on the actual work that's sitting in your queue. That's why we built cto.bench. Michael LuddenAIDec 11, 2025Introducing Live Preview - Vibe Code in cto.newWe’re excited to announce Live Preview, a new way to preview your apps directly within cto.new. Simon SpurrierAIDec 3, 2025From Idea to PR: Using cto.new to Plan and Execute TasksThe standard developer workflow often starts with friction: setting up a repo by configuring the environment, establishing boilerplate, etcetera. By the time you're ready to write actual code, some of the initial momentum is gone. Cto.new streamlines this process by separating planning from execution, and taking care of the setup along the way. It does this through two distinct modes: Chat and Tasks. Michael LuddenAINov 25, 2025Working with background agentsI've spent the last month watching how teams use cto.new, and I've noticed a few patterns in what works and what doesn't. It's not really about the setup, most people figure that out fine. It's about how you think about delegating work to an AI agent.Michael LuddenNov 18, 2025How Jeremy King Uses cto.new with GitHub to Supercharge AI DevelopmentJeremy King, a veteran software architect near Raleigh, North Carolina, has turned solo development into a high-velocity operation through AI tools—particularly using cto.new via the GitHub interface. A longtime consultant and hands-on coder, Jeremy now builds full-stack projects like Leaderboard Fantasy and TutorPro by orchestrating a network of AI coding agents. His workflow runs almost entirely through GitHub: he uses Claude to write specs, breaks work into small issues, assigns tasks directly to cto.new for implementation, and uses Copilot for QA reviews. Michael LuddenAINov 11, 2025Alloyed Agents: Combining LLMs to Improve AI Code GenerationAn alloyed agent runs on more than one LLM in a single agentic loop with shared context.SImon SpurrierAINov 4, 2025Managing Long Contexts in Agentic Coding SystemsThere has been a lot of chatter in the coding agent world over the last few months about context engineering and managing long contexts. The defining work on this is probably...Sudhir BalajiAIOct 30, 2025Knife Juggling: How We’re Building a New Free AI NormalThe mission is straightforward: put our best in class coding agent behind a task orchestration agent we call cto.new, make it free and empower a generation of software engineers to break through the clouds and soar into wild new levels of productivity. Paul GrovesAIOct 29, 2025How Wequity uses Linear with cto.new to Accelerate DevelopmentWequity uses cto.new in their production codebase via the Linear interface. Learn how they have accelerated their development process using the two tools in tandem.Michael LuddenAIOct 16, 2025Getting Started with cto.newHow to get started with cto.newMichael LuddenNewsOct 14, 2025Why We Raised $5.7M to Launch cto.new Completely for Freecto.new is a leading AI code agent that also helps you get started, manage your work, plan, review, and ship.Simon SpurrierNewsJul 17, 2025Engine Labs Posts Leading Terminal Bench Score - Here's What We LearnedEngine Labs has posted a state of the art score on Terminal Bench - the top score with a Claude Sonnet 4 class model and #2 overall.Simon SpurrierAIJul 4, 2025Terminals for LLMs: a Halting ProblemResearching how best to give LLMs terminal access and address the halting problem.Simon SpurrierAll rights reserved 2025,Era Technologies Holdings Inc.CompanyDocumentationBlogTrustSign inSocialGithubDiscordX (Twitter)LinkedInLegalPrivacyTermsCookiesPreferencesNotice at CollectionPricingDocsBlogContactcto benchSign up for freeSign In --- cto benchModel success rates on real end-to-end coding tasks from cto.new usersLeaderboardMethodologyThe benchmark measures merged code as a percentage of completed tasksWe report a 4-day rolling success rate with a 1-day lag to allow for task resolutionWe exclude data from teams that have never merged any code using cto.newOnly models which meet a minimum usage threshold for statistical significance are includedThe leaderboard displays the most recently available measurements for models that meet the benchmark criteria within the last calendar monthToolsetReadFileReads text files from an absolute path.WriteFileWrites/overwrites a file at an absolute path.EditFileReplaces one uniquely identified text block in an existing file.GlobToolFinds files by glob patterns.GrepToolSearches file contents with regex.LsToolLists directories/files at an absolute path with pagination.TerminalToolRuns shell commands and interacts with processes in a VM terminal.