Open Source AI Runtime

OpenCode.ai is an open-source AI coding agent that runs directly in your terminal, IDE, or desktop. It connects to 75+ LLM providers, supports offline use, and enables multi-session collaboration for code review and debugging.

OpenArt is an AI art generator that provides powerful tools for you to generate and edit images, especially artist assets, that you can directly use and edit to improve.

Nebius AI Studio offers efficient model deployment with hosted open-source models, ultra-low latency, and scalable processing options. It simplifies AI model exploration through an intuitive interface while ensuring verified quality and performance for diverse applications.

Openfabric is a decentralized layer‑one blockchain that lets AI developers, data providers, and infrastructure partners build, train, and deploy algorithms on a permissionless network. Its marketplace offers ready‑made tools, and token holders can stake for governance and liquidity.

Learn AI, ML, and data science through free tutorials, live coding playgrounds, and 100+ hands‑on projects. The curriculum covers core machine learning, regression, and deep learning, with specialized projects and a 3,958‑question quiz to reinforce knowledge.

OpenCraft AI is a secure, multi‑model copilot that unifies GPT‑4, Claude, and Gemini. It preserves context across model switches, keeps uploaded files accessible, auto‑formats chats into reports or decks, and generates images with consistent voice tone for streamlined workflows.

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.

OpenAgents is an open-source framework for building and operating scalable, interoperable AI agent networks. It provides tools to launch, connect, and orchestrate agents with live monitoring, enabling collaborative applications and workflows.

AI-Flow is a no‑code platform enabling creators to build and run AI workflows via drag‑and‑drop, integrating models from OpenAI, StabilityAI, Anthropic, and Replicate for batch image, video, and content summarization.

Mistral AI offers developers a platform for building cutting-edge generative AI models with a focus on performance and customization. Their models excel in reasoning tasks and benchmarks, providing flexible deployment options across infrastructures.

EmpirioLabs AI is a platform for hosting, deploying, and scaling open-source and proprietary AI models via API or web playground. It supports multimodal, long-context models with optimized endpoints, creative templates, and high-throughput rate limits for production workloads.

Venice is a private on‑device AI platform that offers a broad array of open‑source models for text, image, code, and character creation. It includes a chat interface, an agent‑building API, watermark removal, upscaling, and batch image generation.

Open Operator is a user-friendly AI tool that allows users to view, run, and browse AI models directly in their web browser. Powered by Stagehand and BrowserBase, it offers a seamless experience for exploring AI predictions effortlessly.

Bind AI IDE is a code editor that runs 15+ AI models for automated generation and refinement of Python, React, Next.js, and Node.js. It offers GitHub sync, instant preview, Vercel deployment, and AI‑driven website building for rapid prototyping.

SmythOS is an open‑source Agent Operating System that manages the AI agent lifecycle—from design to production—via visual studio, SDK, CLI, and secure sandboxed runtime. It supports multi‑platform deployment, orchestration, and enterprise‑grade security.

DeepSeek-V3 is an advanced AI model offering leading performance in open source LLM, enhanced speed, and global language support. It sets new benchmarks for inference speed among open-source models.

gpt-oss playground provides open-weight demos of gpt-oss-120b and 20b for infrastructure testing, distributed and on-device inference, benchmarking, API integration, and reproducible research, with adjustable reasoning levels and visible-reasoning for diagnostics. Demo-only; validate outputs.

Use.ai is an AI Workspace platform unifying access to over 25 AI models including ChatGPT, Claude, and Gemini, offering a single interface for versatile AI applications and seamless model switching.

Open‑Chat is a self‑hostable, decentralized chat platform that supports both proprietary and open‑source AI models. It provides a full chat API, runs LLMs on local GPUs, lowers latency, enhances privacy, and deploys easily on personal or cloud servers.

FreedomGPT unifies access to 400+ AI models, showing side‑by‑side answers for voting and auto‑selection via leaderboard. It keeps privacy safe, runs on Windows/macOS, and is open‑source for community contribution and collaboration.

OpenRead centralizes research by letting users upload documents, search 20,000+ journals, compare papers, generate Q&A, graphs, notes, and chat with AI models. It also offers diagram creation, image editing, and homework help, with frequent model updates.

Kortix Suna is an open-source AI agent designed for personal and professional use, supporting TypeScript and Python. Users can opt for self-hosted or cloud-managed deployment, benefiting from community-driven development and an auditable codebase.

CrewAI is an advanced open source AI agent framework that simplifies creation of complex automations using pre-built models and agents, or custom development with open source tools. Engaged community for sharing and support.

LM Studio runs open‑source large language models locally on Mac (M‑series), Windows, and Linux, enabling private, offline inference. It offers command‑line and headless deployment, server‑side API, SDKs, a model hub, and LM Link for remote model access.

Uncensored AI delivers a chat platform featuring Claude Opus, Gemini, Grok, and MiniMax M2‑Her. It supports text, audio, image, and code interactions, including image‑to‑video via Image Studio. API beta and usage stats benefit developers, writers, educators, and researchers.

MindSpore is a comprehensive AI framework designed for algorithm engineers and data scientists, facilitating the development, deployment, and management of AI models across various platforms. Its key features include built-in support for distributed training and hardware optimization, ensuring scala

All‑in‑one platform integrating GPT‑4o, Claude, Gemini, and others for unified text, image, video, and document AI. Offers summarizing, translation, prompt templates, workflow tools, quiz creation, SCORM export, web search, subtitles, dubbing. SOC II‑compliant with field‑level encryption and data is

OpenDream is a web‑based AI art generator that turns text prompts into images using models such as Dreamlike, Stable Diffusion, and Deliberate. It offers templates for logos, anime characters, and 3D objects, enabling rapid high‑resolution creations for commercial use.

DeepSeek API, available via Kie.ai, provides access to DeepSeek models R1 and V3 for complex reasoning and natural language processing.

Fireworks AI is a cloud‑hosted inference platform supporting code, conversational, agentic, and search workflows across text, vision, audio, and image modalities. It delivers scalable, low‑latency inference with secure RAG and serverless GPU options.

SmythOS is an open‑source agent operating system that lets engineering teams build, test, and deploy AI agents on cloud and edge. It provides a unified visual workflow, SDK, CLI, and sandboxed runtimes with ACLs and encrypted storage for HIPAA compliance.

LLMWare AI installs a lightweight client on PCs, providing instant access to 100+ AI models optimized for Intel and Qualcomm hardware. It supports RAG, auto‑tunes weights, runs locally without Wi‑Fi, and offers an admin console for monitoring, scaling, and audit logs.

Kiro AI is an AI-powered IDE that transforms user prompts into specifications and structured tasks to accelerate prototype development and collaboration. It automates repetitive coding tasks with AI agents, supports multimodal input, and integrates with VS Code while ensuring security and privacy.

Open-claw.org is a premium, subscription-based AI deployment platform that lets you launch powerful AI agents in one click

Refact.ai is an autonomous AI agent for IDEs (VS Code, JetBrains, Neovim) that analyzes entire projects, generates code, completes, debugs, and runs end‑to‑end tasks. It supports multiple LLMs, on‑prem or cloud hosting, and builds a knowledge base from interactions.

apex.ai is a comprehensive platform providing safety-certified software tools and services for autonomous systems. Its modular products enable deterministic execution, high-speed data routing, repeatable testing, and automated deployment for robotics and embedded applications.

OpenManus is an open-source framework for building AI agents, offering flexibility and ease of use. It supports RL-based tuning methods like GRPO, allows LLM API configuration, and enables customizable AI-driven workflows with minimal setup, fostering community contributions.

Release.ai deploys LLM, computer‑vision, and multimodal models with sub‑100 ms latency. It auto‑scales from zero to thousands of concurrent requests, provides enterprise‑grade security (SOC 2 Type II, private networking, end‑to‑end encryption), and offers SDKs, APIs, and real‑time monitoring.

AIMLAPI.com offers a unified API endpoint for over 400 AI models spanning chat, image, video, audio, voice, text, 3D, and OCR. It supports sandbox testing, granular access control, batch requests, and an OpenClaw runtime for secure, human‑in‑the‑loop workflows.

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.

HumanLayer is an open-source IDE and orchestration layer for AI coding agents, managing parallel Claude Code sessions, multiclaude workflows, worktrees and remote workers, with context-engineering tools, session replay, workflow templates and GitHub-integrated code-review automation.

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.

local.ai runs language models locally without GPUs. Its Rust backend keeps the binary under 10 MB and performs CPU inference with GGML quantization. A single‑click interface streams responses to a UI, while a model manager tracks, verifies, and resumes downloads.

OpenAssistantGPT is an open‑source SaaS that lets you build no‑code AI chatbots for websites. It auto‑crawls a URL, supports GPT‑4/3.5, handles file attachments, SAML/SSO, API calls, and web search, with GitHub source and Vercel SDK.

DeepSense.ai provides end‑to‑end AI solutions for enterprises, integrating large language models, retrieval‑augmented generation, MLOps, advanced computer‑vision, edge inference, and predictive analytics to deliver scalable, real‑time AI agents, co‑pilots, and maintenance optimization.

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.

OpenServ allows users to create and manage custom AI agent teams for various roles, enhancing productivity with pre-configured teams. Its integration with popular apps and built-in project management fosters real-time collaboration and workflow efficiency.

H2O.ai delivers an end‑to‑end AI platform that automates feature engineering, model selection, and explainability through AutoML, offers no‑code LLM training, supports enterprise multi‑model orchestration, and includes MLOps and a feature store, all compliant with strict data security standards.

Kimi.ai provides free access to the K2.5 is a multi-modal AI model. It excels in reasoning tasks, supports large context windows, and integrates text and vision data, making it suitable for developers seeking robust AI solutions with enterprise security.