AI coding agent 13

Skillry is a growing library of Agent Skills for AI coding agents. Every Skill carries a specific visual point of view, and you can see exactly what it makes before you install it — so what your agent ships is something you'd actually show. Web pages, slide decks, images and video. Install from the web or your CLI and use it inside Claude Code, Codex, Cursor and more. The taste is ours. The work is your agent's. Your agent can build a site, a deck, a video, an image. It just has no taste. Skillry is a growing library of Agent Skills that do. Each Skill carries a specific visual point of view, and you can see exactly what it makes before you install it — you are not buying a description. Install from the web, or authorize your browser once and run a single command in your CLI. Then invoke a Skill by name inside your agent and get a finished piece of work: a landing page that looks art-directed, a deck you would actually present, an image that stops the scroll, a short film that moves. Four kinds of work today — web pages, slide decks, images and video — with new Skills added every week. No API key required. It is not a marketplace. There is no community upload and no race to ten thousand listings. The library is deliberately small and grows one Skill at a time, which is the whole point: everything in it has a look worth keeping. Works with Claude Code, Codex, Cursor and more. The taste is ours. The work is your agent's.

An all-in-one AI platform for building apps and creating marketing content Converge AI is an AI-native business platform that brings specialized AI products and models together across shared workflows. Its products include Enter Pro, an AI coding agent for planning, building, and deploying applications, and Framia Pro, a creative and marketing studio for generating and editing videos, images, and other branded content. The platform also offers tools for business workflows and shared team workspaces.

On-device voice assistant for conversational AI coding SKI is an on-device voice assistant for AI coding agents such as Claude Code, Cursor, Codex, Gemini CLI, Windsurf, and OpenClaw. It lets developers speak naturally to their coding agent, have the agent build and manage code, and hear its responses aloud. Unlike dictation tools, SKI provides a full two-way voice conversation with local speech-to-text, neural voice synthesis, full-duplex interruption, agent status updates, multi-project support, and optional meeting participation. Voice data, transcripts, and local meeting recordings remain on the user's computer and are not uploaded.

AI-powered website generator that builds websites from text descriptions without coding. DeepSite is an AI coding tool powered by Deepseek V3 that allows users to create websites and web applications without coding knowledge. It offers real-time previews, SEO optimization, and rapid deployment through its platform. DeepSite generates production-ready websites from simple descriptions, featuring clean code and professional design.

AI platform for building and deploying full-stack web and native iOS apps. Botflow is an AI-powered development platform for building and shipping full-stack web applications by chatting with an AI agent. It runs a real Node.js development environment in the browser and can generate frontend code, backend services, databases, authentication, and deployment configurations. Each project can include a Convex backend with real-time synchronization, serverless functions, scheduled jobs, and database management. Botflow also supports native iOS development with Swift, AI model selection, GitHub integration, live previews, and one-click deployment to Cloudflare.

Enterprise platform for building and governing AI-powered internal applications. Superblocks is an enterprise AI application development platform that enables business teams to build production-ready internal apps using natural language and company data. IT and security teams centrally manage authentication, integrations, permissions, secrets, auditing, deployment, and governance. The platform supports AI-generated apps, governed agents, business system integrations, private cloud and VPC deployments, source control, and enterprise security controls.

JACoB is an open-source AI coding agent that automates tasks and enhances code quality. JACoB is a secure and private open source AI-powered coding agent that extends your capabilities and boosts efficiency by completing mundane tasks and proactively addressing concerns while maintaining existing workflows and coding standards. JACoB integrates seamlessly with your existing GitHub repos and Figma designs, automating mundane tasks so you can concentrate on innovation. JACoB maps your full codebase, learning your patterns to generate consistent, high-quality code customized to your use cases and standards. JACoB intelligently reviews code, proactively identifying bugs, security risks, and areas for improvement - decreasing review time.

Background coding agents running in sandboxed dev environments Replicas is a platform that allows engineering teams to run background coding agents like Claude Code or Codex from anywhere. It spawns these agents inside isolated, sandboxed development environments (virtual machines) equipped with the necessary code and tooling. Teams can hand off coding tasks directly through integrations with Slack, Linear, or GitHub, allowing agents to automate code changes, install dependencies, run databases, and verify changes locally, ultimately returning a pull request ready for human review.

Multi-agent engineering system and AI coding agent for high-performing developer teams. AdaL is a multi-agent engineering system designed for high-performing software development teams. It shifts focus from simple code generation to comprehensive agentic engineering by operationalizing the entire software development lifecycle. AdaL combines high-precision, specialized Worker Agents—which handle coding, deep research, browser testing, and code review—with an overarching Engineer Agent that automates workflows, manages long-term memory, and coordinates tasks. It integrates smoothly with developers' environments through a CLI tool and a dedicated Agentic IDE workspace available on browser and desktop.

Cloud Linux VMs for developers, AI agents, and production workloads exe.dev is a cloud platform for developers and AI agents that provides instant, persistent, disposable, and shareable Linux virtual machines. Users can launch VMs through SSH, access them through HTTPS, install software with apt, manage services with systemd, and run coding agents such as Shelley. The platform supports development environments, AI agent sandboxes, data analysis, VPS hosting, team collaboration, and production infrastructure. VMs include configurable CPU, memory, and disk resources, with private-by-default access and IAM-based sharing.

Open-source terminal AI coding agent with memory, swarms, and background tasks Jcode is an open-source AI coding agent for the terminal, written in Rust. It helps developers complete software tasks with durable memory, background tasks, agent swarms, automatic task continuation, confidence checking, benchmark-driven optimization, and semantic memory retrieval. Jcode can be used free with personal API keys, supported OAuth subscriptions, or local models through Ollama and LM Studio. Users can also subscribe to hosted model inference or contact the company for enterprise deployment, billing, security, and support.

No-code platform to build and deploy web applications from English prompts. vly.ai is a platform that enables users to build and launch fully functional web applications without writing code. It leverages a powerful coding agent that lives completely on the browser, allowing users to turn simple English prompts into platforms in minutes. It offers state-of-the-art code generation, configuration, and deployment, all in one click. The agent can edit files, run commands, scrape websites, and run tests automatically.

AI coding agent that learns your coding taste Command Code is an AI coding agent that learns your coding taste, ships code, fixes bugs, tests, and refactors while remembering your preferences locally.