developer tools 25

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.

Unified API for LLMs and AI monetization platform. Sudo is a unified API for Large Language Models (LLMs), designed to provide a faster, cheaper way to route across various providers like OpenAI, Anthropic, and Gemini through a single endpoint. It aims to deliver lower latency, higher throughput, and reduced costs compared to alternatives, enabling developers to build smarter and scale faster with zero lock-in. Beyond routing, Sudo also functions as a one-stop monetization platform for AI developers, allowing them to generate revenue from every API call, AI generation, or user interaction without extensive effort.

Specialized AI model hosting for open, proprietary, and custom stacks EmpirioLabs AI is a low-cost AI infrastructure platform for developers. We host open-source models on our own infrastructure, run optimized proprietary endpoints, and bring model APIs, a browser playground, Hosted Agents, GPU Cloud, and generation templates into one place. Browse production-ready text, image, video, audio, 3D, search, and reasoning models, compare live pricing, test models in the playground, or launch video workflows from ready-made templates. Hosted Agents start at $5/month, GPU Cloud is billed by the second, and select models are discounted up to 90%.

Independent guide to Meta's terminal coding agent and coding model Muse Code is an independent reference guide to Meta's beta terminal coding agent and Muse Spark 1.2 model. The website explains the distinction between the agent runtime and its underlying model, including persistent agents, local event logs, restart recovery, isolated worktrees, installation, pricing, model limits, evaluation claims, and community feedback. It also provides source-linked information about Meta's launch announcements, API access, model IDs, context limits, and reported benchmarks.

CurateClick is a curated collection of the best developer tools and products. It helps developers discover amazing resources and lets makers share their own products with the community.

Open-source SDK to run coding agents in secure sandboxes. VibeKit is an open-source SDK designed to run coding agents like OpenAI Codex and Claude in secure sandboxes. It enables agents to write code, install packages, or open PRs safely, with built-in streaming, async tasks, and telemetry. MIT licensed and built with TypeScript, it offers zero lock-in. VibeKit allows developers to embed coding agents into their applications or workflows, supporting various sandbox providers such as E2B, Daytona, Modal, and Fly.io. It is ideal for creating internal tools, adding AI-powered features to apps, and streamlining prototyping workflows.

Your own team of AI agents. Built to deliver. Hezo is a self-hosted AI agent team platform: one command gives you an entire AI workforce organized like a company. Your team of AI agents — CEO, Coach, Captain, engineers, designers, researchers — ships the work on a real task board. Your API keys stay yours: agents reference them by placeholder only. Budget caps keep spending in check. Every project runs in its own isolated container. Supports Claude, GPT, Gemini, and local models via Ollama and LM Studio.

Speclint scores your specs 0-100 across 5 dimensions before any AI agent touches them. Deterministic regex scoring — no AI hallucination in the diagnosis. CLI, GitHub Action, and MCP Server. Speclint is an open-source spec linter that scores user stories and requirements on a 0-100 scale across 5 dimensions: Measurable Outcomes (20pts), Testable Criteria (25pts), Constraints (20pts), No Vague Verbs (20pts), and Verification Steps (15pts). The scoring is fully deterministic — pure regex pattern matching, no LLM involved. AI is only used for the optional rewrite feature, which rewrites failing specs to pass all checks. Available as: CLI (npx speclint lint), GitHub Action, MCP Server (3 tools), and REST API. Free tier: 5 lints/day. Paid plans start at $9/mo for unlimited linting and rewrites. Open source (MIT). Built for teams shipping to AI coding agents — if your spec scores below 70, the agent will hallucinate. Fix the spec first.

AI-powered tool for instant generation of professional README.md files. ReadmeChef is an AI-powered tool designed to generate professional README.md files instantly. It simplifies the process of creating comprehensive READMEs for GitHub repositories, saving time and improving project visibility. By connecting to GitHub or GitLab, users can have ReadmeChef analyze their code and automatically generate a tailored README without manual input.

cubic: AI code reviews for complex codebases. Used by n8n, Cal.com, and hundreds more. cubic is an AI code reviewer for complex codebases. It’s used by top engineering teams at n8n, Cal.com, Resend, and more. Code review is a major bottleneck for software teams, and the rise of AI-generated code is making the problem worse. Reviewing large volumes of code slows devs down, and increases the chances of bugs slipping through. That's why we're building cubic: an AI code reviewer designed for complex codebases. Teams who adopt cubic merge merge PRs 48% faster. How? When you open a PR, cubic automatically reviews it. It learns from your codebase's patterns, points out bugs, suggesting fixes, and frees you from low-level review tasks.

A code snippet manager that integrates with GitHub Gists for streamlined workflows. Zist is a platform designed to help developers easily organize, access, and manage their code snippets and GitHub Gists. It offers AI-based auto-tagging, advanced search capabilities, and a user-friendly editor to streamline the coding workflow. Zist integrates with GitHub Gists and provides extensions for VS Code and browsers, enabling code reuse and collaboration.

Shiplight is an AI-powered QA platform that automatically creates tests and keeps them up to date, with near-zero maintenance. Shiplight AI is an autonomous QA testing platform designed for modern product teams. It enables both no-code and developer-centric workflows, allowing tests to be created through a visual interface or directly within agentic development environments. Shiplight verifies UI changes in real browsers during development and automatically converts those interactions into reliable regression tests. Its AI-powered system continuously updates and stabilizes tests as the product evolves, eliminating brittle scripts and drastically reducing maintenance overhead. By combining real-time verification with automatic test generation and self-healing, Shiplight helps teams ship faster while maintaining high confidence in their user experience.

AI-powered project management for product teams. Atono unifies planning, deployment, and measurement for product teams in one workflow intelligence platform. Its MCP server lets developers stay in Cursor or other AI dev tools while accessing stories, acceptance criteria, bugs, and feature flags — helping teams stay in context and move faster.

A reviewed directory for discovering and submitting DeepSeek Harness plugins.

Documentation platform with AI, beautiful design, and developer-friendly features. Mintlify is a documentation platform designed to help developers build and maintain modern, engaging documentation. It offers features like AI-native capabilities, out-of-the-box beautiful design, codebase syncing, web editing, API playground, visitor authentication, user feedback, automatic translations, and integrations with popular tools. Mintlify aims to streamline the documentation process, making it easier for teams to create and optimize their documentation for user engagement and conversion.

Gologin Cloud Browser is a web browser for AI and automation that allows teams and developers to run, control, and scale real browser sessions in the cloud via UI or API. Gologin Cloud Browser is a web browser for AI and automation that enables reliable interaction with real websites through cloud-based browser sessions. Instead of running browsers on local machines, teams can launch and manage isolated browser instances via web interface or API, making automation easier to scale and maintain. Each browser session runs independently and preserves state, cookies, and context across multiple steps. This allows AI systems and automated workflows to perform complex, multi-stage actions on modern websites more consistently. The browser can be controlled programmatically and integrated into automation scripts and AI workflows, supporting long-running tasks and parallel execution. Gologin Cloud Browser is designed for teams that need stable browser automation without managing infrastructure. It reduces operational overhead while providing a practical foundation for AI-driven web tasks, automation pipelines, and browser-based workflows that require predictability, control, and scalability.

Cortex is Modern Marketing. AI powered, expert managed. Cortex is AI-powered, expert-managed search marketing intelligence: an optimization engine trained on a 1.5M-passage corpus of platform-published best practices, refined by 50,000+ decisions and their attributed outcomes. It runs a continuous retrieve, analyze, decide, act, and measure loop across SEO, GEO, CRO, and PPC, covering Google Ads, Meta, Amazon, Microsoft, TikTok, and the AI channels (ChatGPT, Gemini, Perplexity, Claude), and every recommendation traces back to a documented source.

AI-friendly web crawling and content extraction platform for structured data. WaterCrawl is a powerful, AI-friendly web crawling and content extraction platform that helps you turn websites into structured, usable knowledge. Whether you're building datasets for LLMs, researching competitors, or documenting online content, WaterCrawl makes it easy to discover, extract, and organize data in clean Markdown format. It offers smart website crawling, LLM-ready export, fast & scalable performance, AI tool integration, and can be self-hosted or used in the cloud.

AI-powered testing solution for automated, self-maintaining software tests. Bugster is an AI-powered testing solution designed to transform user flows into automated tests instantly. It helps developers ship bug-free software faster by deploying an autonomous agent that captures user flows and maintains the test suite. Bugster eliminates flaky tests and adapts to UI changes automatically, reducing the time spent on test maintenance. It integrates with GitHub and offers features like flow-based test agents, advanced debugging, and natural language test creation.