RouteMux is an AI gateway for models from multiple providers through one API key and base URL, with centralized billing and redundant routing.
SandBase gives developers one API key for AI models, live data APIs, runtimes, and sandbox-enabled agent workflows. Test tools or connect AI dev tools.
Boltbar is a native macOS chat bar for GPT and Claude. Open it with Option-Space over any app, or use Claude Code and Codex agent mode in project folders.
Liquid Foundation Models: open-weight, API-accessible text, vision-language, audio, omni, nano, and decision models for local, edge, and cloud deployment.
NINX is a private desktop AI workspace for Mac and Windows with local chat, file work, voice dictation, and approved browser, Gmail, shell, code, and automation workflows.
Off Grid AI is a local AI assistant for Android, iOS, macOS, Windows, and Linux, with offline chat, memory, Sync, and approved actions in Pro.
Overmind is a model training and agent development platform for AI teams. Prepare datasets, evaluate changes, fine-tune open models, and deploy or export results.
Abliterated Model Router offers one OpenAI-compatible API to route abliterated language models across providers, compare models, select by modality, and use fallback.
MiniMax M3.1 Flash is a language model for multi-step agents, coding, computer use, enterprise automation, and cybersecurity. Access it via API, M Plan, or MiniMax Code.
Gerty is a private local AI assistant for Apple silicon Macs, handling chat, writing, documents and voice offline without an account or subscription.
Mercury 3 is Inception’s flagship diffusion-based large language model for fast, reasoned responses and long-context processing in production applications and AI agents.
Step 5 Preview is StepFun’s flagship AI model for agentic software engineering, professional knowledge work, and finance tasks, with vision input, a 1M-token context window, and API access.
NVIDIA Nemotron 3.5 Super VL is an open, customizable multimodal model for specialized AI agents, combining reasoning, tool use, and NVIDIA NeMo support.
Muse Spark Open is a Meta vision-language model on Hugging Face for image-text prompts, visual question answering, image descriptions, and licensed model adaptation.
Navige is an AI agent and LLM cost-optimization layer that reduces unnecessary model spend without changing prompts, workflows, or tool schemas, with free weekly Watchtower reports.
KernelAI runs 53 open-weight AI models locally on iPhone, iPad, and Android. Chat, work with documents and images, code, and use AI offline without an account or subscription.
Microsoft-Decision-1 is Microsoft’s AI model for structured decision scoring in routing, classification, prioritization, verification, and workflow control.
iwant is an open-source CLI for launching open-weight language models on bare-metal GPUs in your Google Cloud account, with an OpenAI-compatible API endpoint.
Gemini platform is Google Cloud’s platform to build, customize, deploy, govern, and optimize enterprise AI agents and generative AI applications with MLOps services.
Liquid Inference routes each LLM request to the lowest-priced provider meeting your model, region, speed, and quality rules via compatible APIs.