Loading...
Claude Mythos 5 is Anthropic’s model for cybersecurity and biology research, available only to vetted partners under strict safety and data-retention requirements.
NVIDIA Nemotron 3 Ultra is an open 550B-parameter Mixture-of-Experts model for long-running agent workflows, with reasoning, context retention, and open weights.
Gemma 4 12B is a multimodal AI model from Google DeepMind for local laptop inference, with vision, audio, and text in one architecture.
EchoFlow is an Android chat app for OpenRouter with your own API key, model switching, and local chat history on your phone.
Tokenwise is an LLM observability and cost optimization platform that tracks API calls, flags waste, and suggests model swaps, caching, and prompt trims.
MiniCPM5-1B is an open-source 1B language model for local assistants, coding agents, tool use, and reasoning with long-context and chat modes.
Command A+ is Cohere’s open-source enterprise language model for complex reasoning, multimodal and multilingual workflows, and tool use, with private deployment support.
MashuPack is a browser-based tool for selecting local code files and exporting them as one clean text file for ChatGPT, Claude, and similar AI chats.
Krater is an AI workspace with ChatGPT, Claude, Gemini and 350+ AI models in one subscription for text, image, video, audio, music and code.
Harbor is a CLI and companion app for launching a pre-wired local LLM stack with chat, search, voice, image, and coding tools.
Perceptron Mk1 is a closed-source multimodal model for video understanding, image reasoning, and robotics workflows with structured visual outputs.
MiniMax M3 is an open-weight AI model for coding and agentic workflows, with native multimodal understanding and a 1M-token context window.
Edgee Fallback Models keeps Claude Code sessions running with automatic failover to other models when Anthropic is down or limits are reached.
SemanticGuard is an AI gateway with a self-validating cache for OpenAI, Anthropic, and Google LLM APIs. Measure savings, cache similar responses, keep requests flowing.
Gello is an Android app that runs a Hugging Face language model locally and exposes it as a Discord bot for always-on on-device AI chats.
TrackNotch is a native macOS app for real-time LLM usage in the notch or menu bar, with local data, Keychain-stored keys, and budget tracking.
Token Monitor — AI Context Tracker is a Chrome extension for Claude.ai with real-time context and quota monitoring, truncation warnings, and token cost badges.
PromptQuorum dispatches one prompt to 25+ AI models at once, then scores consensus and hallucination risk to help compare consistent answers.
Franz is a functional, prototype-oriented language with terse syntax, lexical scoping, and native compilation via LLVM IR for effect control and predictable closures.
Gemini 3.1 Flash-Lite is a Gemini 3-series AI model optimized for ultra-low latency, high-volume tasks, and cost-efficient production on Google’s Gemini Enterprise Agent Platform.