Tensorflow Nodejs

n8n is an open‑source workflow automation platform with a visual canvas and custom JavaScript/Python support. It connects to 500+ integrations, enables AI agents and RAG, offers audit logs, real‑time alerts, and can be self‑hosted on Docker or Kubernetes.

EnergeticAI is an open‑source TensorFlow.js library for Node.js, offering fast pre‑trained embeddings, text classifiers, and semantic search. It delivers sub‑4‑second cold starts and 67× faster inference in serverless functions for developers and performance.

The AI tool offers serverless, scalable, and pay-as-you-go features with AI-generated SQL and HTAP functionalities through various sign-up options.

tensor.art is an AI art platform that enforces real-time human verification and connection reviews (Cloudflare-backed) to block automated access, requiring JavaScript-enabled browsers and offering verification status and access-control integrations for developer workflows and APIs.

Pi.dev is a terminal-based coding agent for developers and teams, offering TUI, RPC/SDK modes, extensible TypeScript modules and packages, multi-provider model authentication, session/context management, RAG/memory primitives, and CLI tooling for automation and integration.

Convex is a TypeScript backend platform that syncs app data in real time across frontend, backend, and database. It offers authentication, cron jobs, AI code generation, modular components, and integrates with React, Next.js, Remix, Vue, and Svelte, a developer portal.

VModel provides a unified REST API that lets developers deploy and run custom or community‑built models with a single line of code. It supports Node.js, Python, and cURL for image, text, and video tasks, automatically scaling for production workloads.

Teachable Machine lets users build TensorFlow.js image, audio, or pose classifiers through a browser interface without coding. Collect, label, and train data in‑browser, evaluate accuracy, then export models to web, Node.js, Coral, or Arduino for rapid prototyping and educational projects.

NodeCodeStudio is a workflow automation tool that simplifies task management across platforms. It allows users to create AI agent workflows, publish content, coordinate tasks, and generate insights, enhancing efficiency with integrations like Google Analytics and Gmail.

Tambo is an open-source AI orchestration framework for React applications, enabling easy integration of AI features, live streaming of UI components, efficient state management, and secure user sessions, with robust support for various AI models through the Model Context Protocol.

ChatNode transforms website and knowledge‑base content into autonomous support agents that learn continuously, handle tasks like bookings and invoicing, integrate with WordPress, Slack, Notion, Zapier, and provide analytics for satisfaction and flow refinement, all via no‑code setup.

Neoteric delivers end‑to‑end software and AI solutions for startups and enterprises, covering digital product design, web and progressive web app development, generative AI, GPT‑based chatbots, predictive modeling, Node.js custom development, and continuous maintenance.

Full Stack AI is an AI‑driven CLI that generates fully configured Next.js applications from a text prompt, automatically adding TypeScript, Tailwind, Prisma/PostgreSQL, tRPC, authentication, Stripe, and Resend. Run with `npx fsai gen` and deploy locally or to your host.

Flowith is a canvas-based agentic workspace which offers free 🍌Nano Banana Pro and other effective models.

fal.ai offers a unified API for generating images, videos, audio, and 3D models from a library of over 1,000 production‑ready assets. It provides serverless GPU inference, private deployment options, NVIDIA‑cluster fine‑tuning, SOC 2 compliance, and enterprise‑grade support.

ComfyOnline lets users run ComfyUI workflows online, automatically installing dependencies and models. It auto‑generates APIs for image, video, audio, and text generation, supports advanced services, LLMs, custom nodes, and scales with traffic.

RunningHub is a cloud IDE for ComfyUI workflows, enabling in‑browser design, editing, and GPU‑accelerated execution. It offers pre‑installed nodes, access to major diffusion and video models, training tools, API integration, and real‑time collaboration.

The AI content checking tool uses image recognition technology with 93% accuracy rate to classify potentially indecent content and offers camera and blur protection. It can be accessed through GitHub and has a mobile demo available.

Unsloth Studio is a no-code web UI enabling local training, running, and exporting of open AI models like Qwen3.5 and NVIDIA Nemotron 3, simplifying experimentation for users without extensive technical expertise.

OpenRouter gives one API key to access 300+ models from 60+ providers, SDK‑compatible, with visual routing, automated fall‑back, edge hosting, data‑policy controls, and agentic tools for building efficient autonomous workflows.

AskCodi accelerates backend and frontend development by generating REST/GraphQL APIs, UI components, and production‑ready agents. It offers an AI gateway, IDE/CLI integration, and a marketplace for ready‑to‑run templates, cutting boilerplate and speeding prototyping.

Koxy AI is a no‑code, serverless backend platform that deploys services globally with low latency. It offers a distributed NoSQL database, edge‑running JavaScript functions, real‑time sync, encryption, and a flow builder to integrate over 80 000 AI models.

Contember is a TypeScript full‑stack framework that auto‑generates GraphQL APIs, authentication, and admin UIs from schemas. It provides AI tools for site editing, SSO, role permissions, and rapid prototyping in weeks.

Softgen transforms natural‑language specs into Next.js apps, integrating Supabase, Vercel, and GitHub for database, deployment, and version control. It supports multiple AI models and one‑click payment, email, and analytics services, while preserving code ownership and standard workflows.

Floyo is a browser-based platform for running and building ComfyUI node workflows without local installation, enabling text/image/video pipelines (including ControlNet, inpainting/outpainting), LoRA dataset generation/training, multi-frame video processing, and workflow automation APIs.

Emergent generates full‑stack, production‑ready web applications from natural language prompts. It auto‑creates APIs, UI, and deployment scripts for React, Node.js, Django, etc., with built‑in version control, testing, and CI/CD for rapid prototyping.

Cerebras provides a wafer-scale AI accelerator and software stack that enables single-node training of very large LLMs, high-throughput low-latency inference (GLM-4.6 at 1,000 TPS), PyTorch SDK, deployment options, and MLOps tooling.

NinjaChat consolidates dozens of large language models (GPT‑5, Claude, Gemini, etc.) into a single interface, offering text, image, and video creation, live web search, finance data, and document intelligence for creators and developers.

CodeAI turns plain‑English app concepts into editable code for frameworks like Next.js, auto‑generating components, routing, and deployment scripts. It integrates with GitHub and offers one‑click hosting on Vercel, Netlify, and Supabase, plus a template library.

Solid generates production-ready full-stack web apps (Node.js, React, TypeScript, Docker) with templates for e-commerce, admin panels, portfolios and more, offering a no-code web builder, extensible codebase, IDE integration, deployment, security, and scaling tooling.

Evolink is a unified API gateway providing single-key access to multimodal text, image and video models, with smart routing, automatic failover, low-latency provider switching, OpenAI/Anthropic/Google-compatible integration, SDKs, and real-time monitoring for scalable model orchestration.

Substrate builds compound AI systems by linking modular nodes into directed‑acyclic‑graph workflows. It auto‑merges compatible steps for parallelism, bundles a vector search DB, code interpreter, and model router, and provides a lightweight Python/TS SDK for rapid prototyping without infrastructure.

Streamdown is a drop-in react-markdown replacement for AI-powered streaming Markdown rendering, supporting GFM, Shiki-highlighted code with copy/download, KaTeX math, Mermaid diagrams, CJK emphasis, Tailwind styling, streaming parsing and security filtering.

TemplateAI is a Next.js 13 full‑stack starter for AI apps, offering App Router, Tailwind styling, prebuilt landing page and dashboard, Supabase integration, Stripe payments, LangChain vector search, Replicate image generation, and multi‑model text chat. It cuts boilerplate, enabling rapid developmen

Vast.ai supplies on‑demand GPU instances, including NVIDIA RTX, H100, and Blackwell models, deployable in seconds. Developers can programmatically provision resources via CLI, SDK or API, and scale workloads with autoscaling, serverless inference, and dedicated InfiniBand clusters.

XState is a JS/TS library that models logic as finite state machines and statecharts. It offers a drag‑and‑drop editor, auto‑generates React, Vue, or Svelte code, syncs with VS Code, and supports testing, debugging, and diagram export.

A web‑based Microsoft AI TTS tool offering 330+ neural voices in 129 languages. Users can adjust rate, pitch, pauses, and style for news, scripts, or narration. Works across Chrome, Firefox, Edge, with an API for web integration.

Weavy is an AI-powered design platform that streamlines creative workflows for professionals. It offers integrated tools for image manipulation, compositing, and collaboration, enhancing project refinement through features like inpainting and z-depth extraction within a user-friendly interface.

SiliconFlow is an AI infrastructure platform enabling high-speed inference for LLMs and multimodal applications, supporting serverless, reserved, and private-cloud deployments. It offers low-latency processing, elastic compute, and built-in monitoring for scalable, cost-efficient AI workloads.

SpeechGen.io converts up to 2 million characters into high‑quality neural‑voice audio across 150 languages with 5,000 models. It allows voice, speed, pitch, volume control, SSML tags, background music, multi‑speaker tagging, downloadable formats, and a REST API.

Open-source, fast, network-connected, differentiable tensor library for TypeScript (and JavaScript).

AdminForth is an open‑source admin framework built on Node.js, Vue 3, and Tailwind CSS. It delivers a ready‑made back‑office with built‑in auth, role‑based access, OAuth2 SSO, AI autocomplete, audit logs, 2FA, S3 uploads, CSV import/export, and a database‑driven CRUD interface.

Open SaaS is an open-source framework for building scalable applications with React and Node.js, offering features like pre-configured authentication, payment integrations, TypeScript support, an admin dashboard, and easy deployment without vendor lock-in.

HyperMink AI is an open‑source, privacy‑centric platform offering a modular Node.js inference server, Inferenceable, powered by llama.cpp/llamafile. It supports local model deployment, plug‑in extensions, and community contributions via GitHub for developers.

BuilderKit is a TypeScript Next.js SaaS boilerplate and AI starter kit that bundles modular code, prebuilt apps, AI modules (chat, text/image/speech), model integrations, Supabase/Postgres auth/storage, payments, SEO-ready UI, demos and deployment support.

MyShell AI enables developers and non‑developers to build, share, and own AI agents using a no‑code visual editor, exportable JSON, and over 1,200 widgets, plus a marketplace that supports blockchain‑based ownership and investment via the $SHELL token.

Modal is a cloud‑native platform that lets developers run inference, training, batch jobs, sandboxes, and notebooks with sub‑second cold starts and instant autoscaling. It’s Python‑centric, offers elastic multi‑cloud GPU scaling, zero‑idle scaling, unified observability, and high‑throughput AI‑nativ

Provides API access to pretrained image generation models for text‑to‑image, image‑to‑image, and inpainting, with real‑time editing. Supports single‑call Dreambooth/LoRA training without local GPU, plus voice cloning, text‑to‑3D, interior design, and video creation.

ModelsLab offers API‑based generative AI for image, video, audio, and language tasks, including editing, generation, and voice synthesis. It supports GPU server deployment, custom workflows, fine‑tuning, and LoRA adaptation for creators and developers.

Pixel Dojo consolidates 70+ AI models—Flux 2, Nano Banana 2, Veo 3.1, WAN—into one workspace for instant image and video creation, real‑time animation, 16× upscaling, one‑click background removal, character consistency, virtual try‑on, and API access for developers.