Alternatives to Cortex.cpp

Shortly AI is an all-in-one AI chatbot that runs 100+ models — Gemini, ChatGPT, Claude, Mistral, DeepSeek and more — on one subscription.

100+ AI models — Claude Opus 5, GPT-5.6, Gemini 3.1 Pro and more — behind one $12/mo subscription with side-by-side Compare Mode.

A mobile app that puts GPT, Gemini, Claude, Grok, DeepSeek and Qwen answers behind one chat box, no account required.

One $10-$20/month subscription that gives you GPT-5, Claude Opus 4.1, Gemini 2.5 Pro, DeepSeek, and Qwen in a single chat window.

Writingmate bundles 350+ chat, image, and video AI models behind one $19.99/month credit pool.

Paste one prompt, see how 40+ AI models answer it, then pick the one that's best, fastest, or cheapest.

Compare AI models side-by-side from one prompt — up to four answers in parallel columns.

Atomic Chat runs 1,000+ local LLMs offline on your own hardware — free, open-source, no account, no rate limits.

Free private AI chat from DuckDuckGo — anonymous AI chat with GPT-4o and Claude, no account required.

Ask once and see two answers from 400+ AI models side by side, then vote to rank which AI is best for the task.

Iris Android runs GGUF language models offline on your phone using llama.cpp — no server, no account, no data leaving the handset.

A single login that puts GPT, Claude Sonnet, DeepSeek V3/R1, GLM 5.2 and Qwen behind one chat window, with images, web search, PDFs and a live app builder.

Free, open-source Ctrl+K desktop assistant that talks to OpenAI, Claude, Google, Groq, OpenRouter or local Ollama models with voice and web search

PureChat is a desktop AI chat client that switches between OpenAI, Ollama and DeepSeek models inside one conversation thread.

OpenChat puts GPT, Claude, Gemini, Llama, DALL·E and Stable Diffusion behind one chat window, so you can compare models without switching apps.

Nova AI App is a multi-model chatbot for Web, iPhone, iPad, Apple Watch, macOS and Android, from $9.99/mo.

Askimo is a free, open-source desktop AI client that reads your local files with RAG and runs ChatGPT, Claude, Gemini and Ollama in one app.

A headless React hooks library that runs Vicuna-13B chat entirely in your browser via WebGPU, with no prompt or completion leaving the client.

Browser chat that runs GPT-5.6 and GPT-5.6-pro queries on a credit meter instead of a $200/mo ChatGPT Pro seat.

Free, open-source desktop app for running and fine-tuning RWKV RNN language models locally with effectively unbounded context.

One chat, 100+ AI models: discode.ai routes every task to the right model on a credit-based plan.

Mobile AI chat app that puts ChatGPT, DeepSeek, Claude, Gemini and Grok in one phone interface from AppNation.

Ollama runs open-weight LLMs locally or in the cloud with one command and an OpenAI-compatible API.

Chatbox is a multi-model AI chat client with a local knowledge base and a Work Mode desktop agent that runs code and finishes tasks.

Free, open-source Android AI chat client with a proot Linux agent workspace and MCP tool calling, using your own API keys.

Free, MIT-licensed local LLM inference for Apple Silicon Macs, with SSD-backed prefix caching and native OpenAI and Anthropic APIs.

Open-source, cross-platform AI assistant that generates full interactive screens and runs locally — with persistent memory and an autonomous heartbeat.

Fullmoon runs small Llama and DeepSeek models entirely on your Apple device — free, offline, open source.

Crowdsourced LLM leaderboard: vote on anonymous AI model battles and compare agents, code, and image models.

Multi-model AI chat: talk to GPT-5.6 Luna and other leading models from one login.