Developer Tools

SUPERHANDS is a tool designed to bridge the gap between the web and your prototypes. It allows users to copy UI components directly from any webpage and paste them into prototyping tools such as Lovable, v0, or Bolt to prototype instantly. This process helps users build faster, skip rebuilds, and avoid wasting credits on mockups.

Markup is an open-source annotation tool that can be used to transform unstructured documents into structured formats for NLP and ML tasks, such as named-entity recognition. Markup learns as you annotate to predict and suggest complex annotations. It helps turn text into structured data without the hassle, rapidly building structured datasets from free-text for NLP and ML. Powered by GPT-4.

Relace provides an advanced platform for autonomous codegen, offering specialized AI models and infrastructure designed for coding workflows. It features source control with out-of-the-box codebase retrieval, fast utility SLMs (Small Language Models), and task-specific agents that can run on any repository. Relace's core offerings include high-performance code retrieval, a universal code merging model that applies file edits at 10,000 tokens/second, and state-of-the-art SLMs optimized for utility tasks like applying file edits and searching codebases quickly. The platform is built for reliability and scale, offering features like lightweight push/pull operations, fast branching, automatic indexing, and a simple API for integration into CI/CD pipelines and development workflows. Relace aims to outperform general-purpose LLMs in code-specific tasks, leading to faster, more reliable, and easier integration into engineering pipelines.

ZEGOCLOUD offers powerful SDKs and APIs for building real-time video, voice, and chat applications with ultra-low latency. It provides scalable infrastructure and 20+ prebuilt UIKits that let developers integrate video calls, live streaming, and AI-powered conversational experiences in minutes. With over 500 global edge nodes and intelligent network optimization, ZEGOCLOUD ensures seamless, high-quality communication for apps across web, mobile, and desktop.

MCP Playground is a web-based developer tool designed to inspect and test Model Context Protocol (MCP) servers. It provides an interactive environment for exploring tools, resources, and prompts exposed by MCP servers, making it easy to debug and develop MCP integrations.

Termdock is a terminal-centric AI development environment that unifies multi-workspace management, multi-terminal layouts, and Git visualization in one interface. It leverages AST search (Tree-sitter) for instant jumps to symbols and dependencies, supports up to 4 windows plus Picture-in-Picture (PiP) for side-by-side operations of tools like Docker, Redis, logs, tests, and AI tools. Termdock also features drag-and-paste images to CLI with auto-compression, built-in file trees, and prompt libraries to ensure fast, consistent, and scalable workflows. It aims to unify AI CLI tools, workspaces, and Git workflows to reduce switching and accelerate output for developers managing multiple projects and terminal environments simultaneously.

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.

Antigravity Google refers to a multifaceted concept encompassing playful browser Easter eggs like Google Gravity, Google Space, and Google Underwater, an advanced AI coding platform nicknamed Google Antigravity (paired with Gemini 3 Pro), and the clarification that real anti-gravity physics does not currently exist. The Easter eggs demonstrate physics-based UI interactions, while the AI platform enables agentic coding, workflow automation, and browser control for developers.

Agenta is an open-source LLMOps platform designed for building reliable and robust AI applications. It provides a comprehensive suite of tools for prompt management, prompt engineering, LLM evaluation, debugging, and monitoring of complex LLM applications. The platform aims to facilitate collaboration among developers and domain experts, enabling them to ship LLM applications faster and with confidence by moving from scattered workflows to structured processes.

Updated.dev transforms your Git commits into clean, ready-to-publish release notes in seconds. It allows users to connect their repository, select relevant commits, and leverage AI to draft the release notes. These published updates appear instantly in an in-app widget and on a public page. The service aims to simplify the process of publishing release notes, enabling users to stop wasting time on manual drafting by instantly generating a complete draft from selected key commits.

FlowLens is a Chrome extension and open-source MCP server designed to make sharing web-app bugs with AI coding agents and human developers ridiculously easy and efficient. It automatically captures comprehensive context, including video, logs, network requests, and user actions, with a single click. This provides AI agents with rich, ready-to-use information for autonomous debugging, while also keeping token usage super efficient. It aims to help users fix bugs 10x faster by giving AI agents complete browser context.

Dagster is a cloud-native orchestrator designed for the entire development lifecycle, offering integrated lineage and observability, a declarative programming model, and best-in-class testability. It serves as a modern data orchestrator platform that helps teams build, schedule, and monitor reliable data pipelines quickly and flexibly. Dagster acts as a unified control plane for building, scaling, and observing AI & data pipelines with confidence. It enables users to model various data assets like tables, files, and ML models, providing a built-in catalog, lineage, and cost insights from day one. The platform automatically tracks, documents, and audits every dataset to ensure data integrity, compliance, and transparency throughout its lifecycle. Dagster integrates with any stack, from S3 to Snowflake to PowerBI, and is built to provide an excellent developer experience while offering data leaders the transparency, control, and insights they need.

LLaMA-Factory Online is the official cloud-based LLM training and fine-tuning platform, developed in partnership with the renowned open-source project, LLaMA-Factory. We are dedicated to providing an out-of-the-box, low-code, and end-to-end solution for users seeking to streamline the fine-tuning process or those with limited engineering resources.

GPU Per Hour is a real-time cloud GPU pricing aggregator and comparison platform designed for AI researchers, developers, and data scientists. It tracks over 10,000 GPUs across 25+ cloud providers, including AWS, Lambda Labs, RunPod, and Vast.ai. The platform allows users to compare hourly rates for high-performance hardware like the NVIDIA H100, A100, and RTX 4090. It features advanced filtering options for VRAM, NVLink, security tiers, and deployment types, alongside a cost calculator and head-to-head provider comparisons to help users find the most cost-effective compute resources for machine learning and rendering tasks.

Agentset is an open-source RAG (Retrieval-Augmented Generation) infrastructure designed to help developers build production-grade AI chat and search applications. It handles the complex aspects of RAG, including document extraction, chunking, hybrid search, and agentic reasoning, ensuring that AI apps remain reliable even with large-scale data and high user traffic. The platform is model-agnostic, allowing users to choose their own LLMs, vector databases, and embedding models. It supports over 22 file formats and multimodal data like images and tables, providing cited answers out of the box for sectors like medical AI, legal tech, and enterprise search.

Multitui is a macOS app factory designed to convert Terminal User Interface (TUI) programs into dedicated, native macOS applications. It allows users to wrap command-line tools like Claude Code, lazygit, htop, and vim into individual .app bundles with their own dock icons and window management. A standout feature is its integrated sandboxing, which leverages macOS's built-in sandbox-exec to provide fine-grained filesystem protection. This ensures that CLI tools or AI agents can run with restricted permissions, preventing them from deleting or modifying sensitive data unless explicitly allowed. Each app maintains its own shell history, snippets, and visual themes, providing a first-class macOS experience for power users.

SessionCast is a remote terminal streaming platform designed for developers to access and monitor their local terminal sessions from any device, including smartphones and tablets. It is specifically built to support the 'AI coding era,' allowing users to keep track of long-running tasks from tools like Claude Code, Cursor, and GitHub Copilot CLI without being tethered to a desk. By using a lightweight local agent and a secure relay server, it eliminates the need for complex VPN setups, SSH configurations, or port forwarding. It features low-latency bidirectional communication, allowing users to not only monitor progress but also enter commands remotely through a mobile-optimized interface.

Claudebin is an open-source tool designed for users of Claude Code (Anthropic's terminal-based AI). Since Claude Code stores session data locally in a non-human-readable format, Claudebin allows users to export these sessions into shareable, navigable, and embeddable web artifacts. It captures the complete context of a session, including message threads, file reads and writes, bash commands, and MCP calls, providing a structured viewer via a unique URL. This makes it possible to share terminal interactions in pull requests, documentation, or to resume them on different local machines.

Cencurity is an enterprise-grade security gateway designed to proxy LLM and agent traffic. It functions by detecting, masking, and blocking sensitive data, PII, and risky code patterns in both requests and responses. The platform provides a centralized dashboard for real-time monitoring and recording of all interactions as audit logs. It is designed to be compatible with any LLM agent or IDE without requiring code rewrites, ensuring safe and governed AI integration for development teams.

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.

Krira Labs provides enterprise-grade AI infrastructure designed for scale and performance. Their flagship product, Krira Augment, is a production-ready integration layer for RAG (Retrieval-Augmented Generation) pipelines and agentic systems. A standout component is the Krira Chunker, a Rust-core tool with Python bindings that is 40x faster than LangChain's chunker, offering O(1) memory usage that remains flat at any scale. The platform supports end-to-end ingestion engines, specialized model fine-tuning using low-rank adaptation (LoRA), and autonomous multi-agent architectures with first-class support for the Model Context Protocol (MCP).

RoxyBrowser is the world's first AI-native anti-detect browser designed to bridge the gap between AI logic and web execution. While LLMs provide the "brain," RoxyBrowser provides the secure "body" needed to interact with the web without being detected as a bot.

Design In The Browser is an AI-powered visual frontend development tool that bridges visual design and AI development. It allows users to point and click at any element on a website in their browser, describe the desired edit in plain language, and send the instruction (with a screenshot) directly to integrated AI models (Claude Code, Cursor, or Gemini CLI) running in a built-in terminal. This process eliminates the need to copy selectors or describe layouts manually, allowing developers to see, describe, and change elements quickly while the AI handles the code.

For many builders using Cursor, the frontend feels intuitive and productive. You can design pages, click buttons, and interact with components easily. Behind the UI, however, data models, business logic, authentication, AI workflows, and payments are handled in backend code that can be difficult to visualize and reason about — especially if you’re not a backend specialist. Vibe Architect connects your Cursor project to Momen, a visual no-code backend that makes these core systems easy to see and manage. With Momen, you can: - Visually design your database and relationships - Build backend workflows as clear, step-by-step action flows - Configure AI agents with structured input and output - Manage authentication, permissions, and payments without backend code Cursor continues to generate fast, high-quality frontend code. Momen makes everything behind the scenes visible, structured, and controllable. Together, they form a practical, production-ready full-stack workflow — without requiring deep backend expertise.