Apps with 'DeepSeek' feature

Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, speech synthesis and recognition, web search, memory, presets, assistants and more.

RikkaHub is an Android APP that supports for multiple LLM providers.

Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer.

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model.

A config- and plugin-driven harness — a single static Go binary, tuned around DeepSeek's prefix cache so token costs stay low across long sessions.

Unified AI workspace for Mac (BYOK, on-device). Chat with OpenAI, Anthropic, Google, Nebius & Ollama. Features powerful system audio recording with near real-time transcription using on-device Apple Intelligence or OpenAI API.

Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024).

Free AI gateway allows your AI to work none stop: one endpoint, 350 providers (90+ free), 1200+ models Quota-aware, auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 450+ contributors.

Accelerate deployment and scaling of Qwen, Wan, and more leading models on one secure Alibaba Cloud platform.

An AI coding harness that dogfooded itself into shape: Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals.

Ask a question – 10+ AI models vote on best answer.

Witsy is a BYOK (Bring Your Own Keys) AI application: it means you need to have API keys for the LLM providers you want to use. Alternatively, you can use Ollama to run models locally on your machine for free and use them in Witsy.

SwitchAI lets you seamlessly choose your preferred AI assistant. With a single tap, access your selected AI or set a default assistant for your device’s digital assistant feature. Boost productivity by effortlessly switching between AI assistants for different tasks.

All-in-One AI Hub provides a single, centralized desktop workspace for ChatGPT, Claude, DeepSeek, Grok, Gemini, Perplexity, Manus, Meta AI, Mistral, Hugging Face Chat, and more. Say goodbye to browser bloat and tab fatigue.

Tired of paying $20/month to ChatGPT, another $20 to Claude, and $20 more to Gemini? We were too.

A collection of powerful language models that can run online or locally in your machine| o4, o3 and deepseek r1, gpt-5, veo, gemini 2.5, claude and many more!.

OfflineLLM is the fastest large language model (LLM) engine designed specifically for Apple devices, including iPhone, iPad, Mac and Vision Pro. With OfflineLLM, users can engage in private conversations with AI chatbots without the need for an internet connection, ensuring that...

HugstonOne Enterprise Edition — Awesome AI App with Code editor and Live Preview Create games, dashboards, maps, tables, charts, webpages, data analysis, converters etc in seconds.

Lexora is an AI infrastructure platform that provides hosted AI models, knowledge bases (RAG), image generation, and access to frontier AI models through a unified API. Developers can build AI assistants, chat with documents, and pay only for what they use instead of renting GPUs.

Pay-per-use AI workspace with the latest models from all major providers: Claude, GPT, Gemini, Grok, DeepSeek and Perplexity in one chat interface. No API keys and no subscription; you top up a wallet and pay per message. Includes image generation and voice input.

API for saving on AI spend while maintaining quality.

An AI-powered PHP script for creating news explanation and community discussion platforms with automated content generation and AI bots.

Joanium is a local-first AI desktop app that goes beyond chat. It reads your project files, runs automations on a schedule, operates background agents, and connects natively to GitHub, Gmail, Google Drive, and Calendar, all without sending your data to the cloud.

sllm provides access to a range of large language models at the cheapest possible price, in the most configurably relevant way, all securely and privately hosted on dedicated GPU infrastructure. No markup beyond cost. No tracking. Just the models you need.