Llm apps on winget

Start building with open models.

Unleash Claude’s raw power directly in your terminal. Search million-line codebases instantly. Turn hours-long workflows into a single command. Your tools. Your workflow. Your codebase, evolving at thought speed.

Discover, download, and run local LLMs

Your AI partner on desktop. Fast, focused, and designed for deep work.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

A self-hosted, transparent proxy and debugging console for LLM APIs.

Codex CLI is an open‑source local coding agent that runs in your terminal, letting you write, edit, and understand code without leaving the command line.

All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI tools & agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

Chat about email, screenshots, files, and anything on your screen.

A Flutter LLM Chat Client. Support Android & iOS & Harmony Next.

Dola AI is your AI chat assistant for intelligent conversations, writing, translation and programming. Get answers, find inspiration, and discuss any topic with Dola AI.

A fast and minimal agent that lives both in your terminal and in the cloud.

Open CoreUI - A rewritten Open WebUI in Rust, significantly reducing memory and resource usage, requiring no dependency services, no Docker, with both a server version and a Tauri-based desktop client. (formerly Open WebUI Lite)

A Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.

Get up and running with large language models locally.

Z Code combines the best AI agents with your existing tools so you can plan, code, review, and deploy without friction.

The open-source alternative to Claude Design. Your existing coding agent — Claude · Codex · Cursor · Gemini · OpenCode · Qwen — becomes the design engine, driven by 31 composable skills and 72 brand-grade design systems.

An adaptive AI IDE that transforms how you work, collaborating with you to run faster.

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

Experience liftoffwith the next-gen agent platform

A personal knowledge base that builds itself. LLM reads your documents, builds a structured wiki, and keeps it current.

Work with Antigravity directly in your codebase. Build, debug, and ship from your terminal. Describe what you need, and Antigravity handles the rest.

Distribute and run LLMs with a single file.

A fast and minimal agent that lives both in your terminal and in the cloud.

An AI agent for working with open models locally and in the cloud.

Manage fleets of local and cloud agents from one surface. Plan, delegate, review, and ship without leaving your editor.

A personal AI agent with memory, personality, and autonomy.

千问是阿里通义千问大模型打造的 AI 对话助手，通义千问支持问答、写作、代码、翻译、录音、PPT 创作、文档处理、音视频速读。

Your versatile AI chat companion, compatible with leading LLMs.

Your Ultimate AI Partner

Ship 100x With The Agent IDE

Fast, small, and fully autonomous AI assistant framework — deploy anywhere, swap anything 🦀

Desktop Companion for Hermes Agent

More than Coding

More than Coding

An open-source, modern-design AI chat framework. Supports Multi AI Providers (OpenAI / Claude 4 / Gemini / Ollama / DeepSeek / Qwen), Knowledge Base (file upload / knowledge management / RAG), Multi-Modals (Plugins/Artifacts) and Thinking.

The simplest desktop client for OpenClaw 🦞 — bridge your Agent to WeChat, Feishu, Slack & Discord in one click. Works with Claude Code, Codex & any LLM. BYOK, Oauth, local-first, chat from your phone 24/7.

A beautiful desktop application that unifies your AI experience. Seamlessly switch between OpenAI, Anthropic, Google Gemini, and custom providers.

A DeepSeek-native coding agent, for your terminal.

Your AI, right on your desktop. Open WebUI as a native app. Run models locally or connect to any server. No Docker, no terminal, no setup. Download, launch, chat.

An open-source alternative to Claude Cowork, powered by OpenCode

More than Coding

A next-generation AI coding assistant for developers. Unlimited context lets you understand, build, and collaborate more efficiently.

A powerful tool for building and deploying AI-powered agents and workflows.

Bringing agentic capabilities beyond code. Describe what you need - QoderWork plans, executes, and delivers.

A DeepSeek-native coding agent, for your terminal.

Coding agent for DeepSeek models that runs in your terminal

Effortlessly run LLM backends, APIs, frontends, and services with one command.

An adaptive AI IDE that transforms how you work, collaborating with you to run faster.

Agentic Coding Platform for Real Software

An easy-mode runtime and UI layer built on top of OpenClaw, designed to turn long-lived AI agents into personal digital butlers.

Your AI Copilot on the Desktop

A desktop client that supports for multiple LLM providers

AI coding assistant with read, bash, edit, write tools

AstrBot GUI manager

Coding agent for DeepSeek models that runs in your terminal

Tencent Cloud Code Assistant

A powerful new coding agent and CLI for complex coding work.

Wrap Gemini CLI, ChatGPT Codex as an OpenAI/Gemini/Claude compatible API service, allowing you to enjoy the free Gemini 2.5 Pro, GPT 5 model through API

The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

Open-source desktop platform for multi-agent collaboration. Empowering AI agents with local tools, parallel teamwork, and seamless workplace integration.

A new CLI agent that can help you with your software development tasks and terminal operations.

Ask questions, get instant answers with sources. The AI search engine that understands what you’re actually looking for.

The simplest way to run Alpaca (and other LLaMA-based local LLMs) on your own computer

Open CoreUI - A rewritten Open WebUI in Rust, significantly reducing memory and resource usage, requiring no dependency services, no Docker, with both a server version and a Tauri-based desktop client. (formerly Open WebUI Lite)

A DeepSeek-native coding agent, for your terminal.

AI coding assistant with read, bash, edit, write tools

Remembers your habits, builds Agent teams, automates the repetitive work

AI-powered research assistant for your Zotero library

An AI assistant that reasons and interprets, and thinks in depth

Refreshingly fast LLMs on GPUs and NPUs

Local voice dictation for Windows with global hotkey — Whisper STT + multi-provider LLM (Anthropic / OpenAI-compatible / Ollama).

DevProjex turns folders and Git repositories into clean, AI-ready context for ChatGPT, Claude, and other AI tools. Smart Ignore, .gitignore, and Git-tracked mode. GUI, TUI, and CLI. Export to ASCII, Markdown, JSON, XML, folder, or ZIP. Local and read-only.

Your own multimodal Agent team

Make your own story. User-friendly software for LLM roleplaying

LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

Code Editor for the AI Agents Era. Run multiple Claude Code and Codex agents across projects on your machine.

智能 AI 办公工具

Chat with ALL AI Bots Concurrently, Discover the Best

Free, local, open-source GUI app for Gemini CLI — Enhance Chat Experience, Multi-tasking, Code Diff View, File & Project Management, and more

Aggregate and browse AI coding agent sessions (Claude Code, Codex, Gemini CLI, etc.) in one place. Desktop app, self-hosted server, or Docker.

An AI assistant for work that turns questions into answers, answers into actions, and actions into outcomes—for you and your entire team.

An agentic AI assistant that lives in your chats, inspired by nanoclaw and incorporating some of its design ideas. Built with Rust

The Open Source Cowork Desktop to Unlock Your Exceptional Productivity.

Foundry Local enables local execution of Small Language Models using the hardware on your device.

An interactive shell to work with AI-powered assistance providers

A modern AI gateway system that provides a unified OpenAI (Chat Completion, Responses), Anthropic, Gemini and AI SDK compatible API

Turn your computer into an AI computer

A desktop app that turns Coding Agents into reliable teammates — by splitting every change into Task → Proposal → Apply → Archive, with you reviewing the plan before any code is written.

An easy-mode runtime and UI layer built on top of OpenClaw, designed to turn long-lived AI agents into personal digital butlers.

MindOS is where you think, and where your AI agents act — a local-first knowledge base shared between you and every AI you use. Share your brain with every AI — every thought grows.

The Open-Source Agentic Browser.

DeepChat 是一个多平台 AI 客户端，致力于让更多人享受 AI 带来的便利。

Open-source Agent Operating System

Your universal AI text processor, powered by local and cloud LLMs. Edit, refactor, and transform text in any application on Windows, macOS, and Linux.

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral).

All in Done Hub service for OpenAI API.

An infinite canvas desktop app for visually managing terminals

Run AI models locally. One-click install w/ zero configuration.

A terminal-based AI research assistant built for academic researchers

More than Coding

The frontier coding agent for your terminal and editor.

The AI Assistant That Just Works. Based on the OpenClaw framework. One-click install. Zero configuration. No API key required.

A ready-to-use self-growing desktop AI assistant for long-running tasks, memory, agents, tool reviews, MCP, and high-concurrency workspace automation.

AI-first IDE — a Visual Studio Code fork with custom LLM providers, a coding agent and autopilot. No subscriptions, no telemetry, bring your own API key.

Cross-platform desktop log analyzer with LILA, an AI assistant for log triage

Your personal smart assistant, here to answer questions and unleash creativity.

A next-generation AI coding assistant for developers. Unlimited context lets you understand, build, and collaborate more efficiently.

Private & local AI personal knowledge management app.

A lightweight, container-first AI coding assistant accessible through Telegram.

Desktop AI Assistant / Universal MCP Client

Your Intelligent Assistant for AI PC

The easiest way to use local and online AI models

Run AI models on your desktop with one click.

Agent-Native Software Development

Dyad is a free, local, open-source AI app builder

Open-source, model-agnostic AI pair programmer for the terminal.

A cross-platform AI note-taking application focused on recording and writing.

The Starting Point for Next-Gen Agents

The memory-first coding agent

Generate a brain map of your codebase for LLM context

Build Your Agent Team for Real-World AI Development - Workspace-first multi-agent coordination platform for AI development, with shared Specs, Kanban orchestration, and MCP/ACP/A2A support across web and desktop.

Your own multimodal Agent team

An extension for PowerToys Command Palette that allows you to chat with a large language model (LLM) directly.

Local Search Engine Built for AI Agents

Your All-In-One AI Platform.

Desktop GUI for BitLlama LLM inference engine with Soul learning and model management

CLI for running large numbers of coding agents in parallel with git worktrees

Your Ultimate Chatbot Experience

The easiest way to use local and online AI models

Connect ClawWork to your own OpenClaw and unlock 10x multi-session productivity.

Control BrowserOS from the terminal or AI coding agents

Your AI Copilot on the Desktop

100% Open Source Toolkit for Large Language Models: Train, Tune, Chat on your own Machine

Your Personal AI super intelligence. Private, Simple and extremely powerful.

One desktop to manage your agent skills

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

Pure Rust LLM inference engine with 1.58-bit ternary support and Test-Time Training

GitLab MCP server exposing the REST v4 and GraphQL APIs as tools for AI assistants.

The first desktop app to run and train AI models locally.

Your Desktop AI Staffs.

The runtime your coding agents live on. It holds real terminals open on your laptop, your desktop or a box you rent, so the work survives the lid closing and you can attach again from anything with a keyboard.

100% 中文关键字的原生编译语言（LLVM 后端，内置 AI 原语）

A better AI (LLM) client. Full-featured, lightweight. Support multiple workspaces, plugin system, cross-platform, local first + real-time cloud sync, Artifacts, MCP

Unleash Your AI Agent, With Peace of Mind

Win every argument

An AI-enhanced desktop app for a tighter, more focused browsing loop. Less chaos. More flow.

A Go-based proxy server that provides OpenAI-compatible API endpoints for Any AI website using browser automation.

A memory upgrade for your coding agent

Natural language to shell commands using LLMs

Next-generation AI Code Agent, empowering developers with efficient programming, automated code generation and intelligent optimization

A portable terminal AI interface

Standalone A2A CLI client

Lightweight coding agent that runs in your terminal (agentserver fork of OpenAI Codex).

Deploy your private Gemini application for free with one click, supporting Gemini 1.5, Gemini 2.0 models.

You describe. AI delivers. Documents, slides, analysis, research, and beyond — done locally, fully private.

A team workspace for running AI coding agents in parallel with isolated Git worktrees, live diff review, GitHub integration, and mobile access.

MCP server connecting intervals.icu training data to AI assistants.

A lightweight desktop AI client and screen-level agent: chat, tools, translation, OCR, and visual Q&A in one small app.

Deterministic execution layer for AI agents (CLI + server).

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

A multi-agent engineering workflow that plans, delegates, reviews, revises, and delivers.

Tray sidekick for Claude Code — usage tracking, session browser, quick launchers, prompt library.

Stay connected and chat seamlessly across all of your devices

A Windows desktop app that refines rough prompts into comprehensive, precise prompts using the GitHub Copilot SDK.

A headless terminal CLI + daemon for driving, asserting on, and recording shells

Sovereign AI agents that run 100% on your own machine.

Apps which allows to chat with AI (local Ollama, network service).

A minimal LLM chat app that runs entirely in your browser

Lean-context AI-native desktop IDE. Describe your intent; the agent plans, executes with your approval, and delivers reviewable diffs with a full execution trace.

Go wrapper for Codex CLI

Work with most powerful agents in the world, with the UX they deserve

AI that gets your everyday tasks done.

A distributed agentic AI platform to run all your AI agents everwhere on every device.

Native desktop client for DeepSeek Chat and DeepSeek Harness.

A lightweight CLI tool to interact with the Gemini API from the terminal.

NeatChat: A simplified and optimized fork of NextChat

A local-first CLI and TUI that profiles where your AI coding agent's tokens went.

Your Private Sanctum for AI

Local hardware-accelerated AI desktop assistant (CPU inference build)

Instant documentation structure for LLMs and humans

A tray-resident local proxy that owns the OAuth2 flow for the APIs and MCP servers you use, pools several servers behind one endpoint, and exposes only the tools each AI agent is allowed.

Logivore plus Advanced Veeam Mode — collects, normalizes, and analyzes Veeam Backup and Replication logs end-to-end

Desktop shell for the pi coding agent.

Rovo Desktop is the best way to access Rovo from your Windows or macOS device. It's a dedicated spot to chat, manage agents, and complete tasks while staying connected to your workplace knowledge.

High Performance LLM Reverse Proxy

A desktop LLM client with magical MCP support

AI on the command line

Natural-language command assistant for PowerShell.

Local-first AI coding assistant that runs models on your own machine.

A .NET-native codebase context optimizer for AI-assisted development.

Electron desktop shell for DeepSeek Harness (DSH).

A network diagnostics and TCP optimization tool with MCP (Model Context Protocol) integration for AI-assisted configuration.

Native desktop client for InferenceHub chat — frontier and open-weight models with web search and deep research.

Pick a local LLM (Ollama / Foundry Local / LM Studio) from a TUI and launch GitHub Copilot CLI against it.

Standalone Docker Model Runner - run local AI models with no Docker Desktop or Engine required.

Dagger is an integrated platform to orchestrate the delivery of applications

Floating typing assistant for Windows. Sits as a transparent overlay above your active window, listens via UI Automation, and serves up smart suggestions — spelling corrections, AI next-word predictions, translation, and text actions.

LLM agent framework with natural language agent creation

Standalone command-line client for Tinyrack Coder

The trustworthy personal AI agent that measurably knows you — first-class on Windows.

Local hardware-accelerated AI desktop assistant (Vulkan GPU offload build for AMD/Intel GPUs)

Private, local AI desktop app — run open LLMs fully offline with a coding agent, knowledge base and voice.

Desktop workbench for Grok Build CLI — sessions, projects, media, automations (Tauri 2 · unofficial).

Interactive terminal for AitherOS — chat with AI agents from your shell

Modular meta-harness — compile a single spec into multiple agent runtimes.

Local-first document anonymization for AI workflows

A Windows desktop home for local AI coding - run models on your own machine through Ollama, with no API keys.

A blazing-fast CLI for creating LLM context from your entire codebase

Provider-agnostic pull request reviewer for hosted, local, and OpenAI-compatible models.

Free, local, open-source GUI app for Gemini CLI — Enhance Chat Experience, Multi-tasking, Code Diff View, File & Project Management, and more

AI-powered command line assistant

A persistent, private, on-device memory for your AI clients.

ClassIsland的CLI客户端，方便Openclaw接入控制ClassIsland

Command-line interface for the Altoviz invoicing app

A local-first AI agent desktop client that deeply integrates large language model reasoning with local system tools.

An open-source AI agent that works out of the box. Consider it done.

Desktop companion for managing Oh My Pi model providers

A lightweight selection assistant that brings copy, search, translate, summarize, explain, polish, and AI actions to any text you select.

A coding agent that lives on your computer — and can actually run it.

Governed, sovereign AI workstation — local-first, cites its sources, abstains instead of guessing.

An open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities.

The best way to use pi agent.

A local-first Agent workspace where tools, permissions, artifacts, and durable progress stay visible.

A Sleek AI Assistant & MCP Client

A local-first desktop client for coordinating AI agents with your own API keys.

Mission control for Claude Code — browse, search, and drive your Claude Code sessions from a native desktop app.

Self-hosted daemon for Claude Code, Codex, Copilot, OpenCode, and Pi. Agents run on your machine with your full dev environment. Connect from phone, desktop, or web.

You describe. AI delivers. Documents, slides, analysis, research, and beyond — done locally, fully private.

Local-first MCP gateway. One port for every tool and every AI client.

Desktop multi-agent AI orchestration - connect agents into workflows, delegate tasks in parallel, and integrate MCP tools.

Architecture-driven modernization — decompose legacy codebases into ADRs, recompose to modern stacks.

Local-first personal AI assistant — your data stays on your machine.

System-tray Git assistant powered by a local LLM served by LM Studio

Local-first AI coding agent with an always-on daemon