Llm apps on winget

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.

Start building with open models.

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

Discover, download, and run local LLMs

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

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.

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

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.

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

Get up and running with large language models locally.

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

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

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)

AstrBot GUI manager

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.

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.

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

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

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

Experience liftoff with the next-gen agent platform.

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

AI teammates that use your tools, learn your workflows, and get real work done 24/7.

Ship 100x With The Agent IDE

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

Desktop Companion for Hermes Agent

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。

Distribute and run LLMs with a single file.

More than Coding

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.

Your Ultimate AI Partner

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

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

Your AI Copilot on the Desktop

A DeepSeek-native coding agent, for your terminal.

Your versatile AI chat companion, compatible with leading LLMs.

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

More than Coding

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

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

Agentic Coding Platform for Real Software

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

A desktop client that supports for multiple LLM providers

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.

More than Coding

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

Native desktop client for DeepSeek Chat and DeepSeek Harness.

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

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

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

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

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

Coding agent for DeepSeek models that runs in your terminal

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

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

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

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

Refreshingly fast LLMs on GPUs and NPUs.

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.

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

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

A DeepSeek-native coding agent, for your terminal.

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

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

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

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.

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。

Your own multimodal Agent team

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

智能 AI 办公工具

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

Turn your computer into an AI computer

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

RAG tooling, reimagined with researchers in mind: literature discovery and review via semantic search of your Zotero PDF collection

Desktop AI Assistant / Universal MCP Client

A DeepSeek-native coding agent, for your terminal.

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

Your own multimodal Agent team

Chat with ALL AI Bots Concurrently, Discover the Best

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

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

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

Coding agent for DeepSeek models that runs in your terminal

Tencent Cloud Code Assistant

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)

One desktop to manage your agent skills

More than Coding

The frontier coding agent for your terminal and editor.

Agent-Native Software Development

An interactive shell to work with AI-powered assistance providers.

The Open-Source Agentic Browser.

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

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

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

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

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

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

The Starting Point for Next-Gen Agents

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

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

The memory-first coding agent

100% 中文关键字的原生编译语言（LLVM 后端，内置 AI 原语）

DevProjex is a code-to-prompt app: it turns any folder or Git repository into clean context for ChatGPT, Claude, and AI agents — with a token counter, secret masking, and an MCP server where the agent follows your tree checkboxes. Local, no telemetry.

The Open Source Cowork Desktop to Unlock Your Exceptional Productivity.

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

Private & local AI personal knowledge management app.

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).

Electron desktop shell for DeepSeek Harness (DSH).

Your Intelligent Assistant for AI PC

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.

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

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

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

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

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

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

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

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

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.

Open-source Agent Operating System

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

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

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 infinite canvas desktop app for visually managing terminals

Your AI Copilot on the Desktop

Modern native desktop client for Gemini CLI via Agent Client Protocol (ACP)

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

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

An agentic development environment for multitasking with coding agents.

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.

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

Your All-In-One AI Platform.

AI that gets your everyday tasks done.

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

Stay connected and chat seamlessly across all of your devices

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

The easiest way to use local and online AI models

Run AI models on your desktop with one click.

A native AI assistant with global shortcuts and automation to help you research, write and summarise files.

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

All in Done Hub service for OpenAI API.

A terminal-based AI research assistant built for academic researchers

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.

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

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 Ultimate Chatbot Experience

The easiest way to use local and online AI models

A portable terminal AI interface

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

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

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

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.

Unleash Your AI Agent, With Peace of Mind

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

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.

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

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

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

Control BrowserOS from the terminal or AI coding agents

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

The open source agentic coding CLI from the Kilo engineering platform.

A memory upgrade for your coding agent

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

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

A TRPG game master that never forgets or contradicts - an LLM narrates while a deterministic Rust engine owns the game state.

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

The official command-line interface for A2A-compatible agents.

Generate a brain map of your codebase for LLM context

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

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

A Sleek AI Assistant & MCP Client

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

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

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

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

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

Bring ChatGPT to your desktop with ChatGPT Work and Codex, plus context from your email, screenshots, files, and anything on your screen.

Your Desktop AI Staffs.

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

Desktop shell for the pi coding agent.

Natural language to shell commands using LLMs

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

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

Local-first document anonymization for AI workflows

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.

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

Go wrapper for Codex CLI

Standalone command-line client for Tinyrack Coder

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

Assemble a team of AI agents that grows together

The Cline coding agent as a native desktop application.

High Performance LLM Reverse Proxy

Dagger is an integrated platform to orchestrate the delivery of applications

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

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

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

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

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

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

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

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

A desktop LLM client with magical MCP support

The best way to use pi agent.

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

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

A minimal LLM chat app that runs entirely in your browser

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.

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

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

Native agent CLIs manager with Ghostty terminals, an embedded browser, and an IDE.

AI on the command line

Simple, powerful and privacy-friendly AI chat application for GPT-4, Claude, Gemini, DeepSeek and other LLMs.

A notch for Windows 11 showing how much of your Claude, ChatGPT and Gemini usage is left.

A local-first desktop client for AI coding agents.

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

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

A native desktop app for Pi Coding Agent — chat with your coding agent, watch its tools work, manage sessions, models, and packages in one visual workspace.

Instant documentation structure for LLMs and humans

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

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

Natural-language command assistant for PowerShell.

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

AI-powered command line assistant

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

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

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

LLM agent framework with natural language agent creation

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

A terminal coding agent powered by multi-model orchestration.

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

An always-on desktop app of autonomous AI employees that work inside your IM chats

Desktop app of the Kimi Code AI coding agent

Multi-agent coding with specialized agents orchestrated in a high-performance Rust runtime

Xiaomi MiMo AI desktop client

An AI coding agent for the terminal.

A native Windows LLM client with multi-provider switching for conversations.

A CLI-only coordinator/executor collaboration tool for AI coding agents

Agent harness to run an office of your clones

Probe an LLM and return host policy

Agent harness to run an office of your clones

Autonomous command-line AI coding assistant that interacts with LLMs to inspect, modify, and manage codebases.

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

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

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

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

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

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

Command-line interface for the Altoviz invoicing app

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

A team of long-lived bots for DeepSeek Harness.

An IDE designed for agentic AI research.

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

siGit Code, an AI coding agent that runs on your machine.

Roslyn-backed code context for AI coding agents - MCP server, CLI and Windows app.

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

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.

Universal provider proxy for OpenAI Codex and Claude Code.

Agentic Coding Platform for Real Software

Turn plain text into editable mind maps and flowcharts with an AI model that runs fully offline.

A from-scratch, GPU-accelerated local inference engine and TUI chat client for the LFM2.5 model family.

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Standalone A2A CLI client (Rust implementation)

Agent Supervisor & Model Dispatcher for coding agents (spicebox.dev/nacho-flow).

A local-first desktop workspace for coordinating AI coding agents.

Self-hosted proxy that routes each coding-agent request to the cheapest capable model, with local budget caps and a kill-switch.

Open-source visual AI agent app built on Pi, no terminal required.

Same AI. Way better answers. Improve any AI prompt with one hotkey, from any app.

Desktop companion for managing Oh My Pi model providers

A desktop launcher for running several AI coding agents side by side.

Hundreds of models & providers. One command to find what runs on your hardware.

Desktop client for DeepSeek Harness.

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

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

Desktop AI agent with plugins, an embedded browser, workspace files, and local model support.

A local-first workspace for teams of AI agents.

The visual workspace for the Command Code coding agent.

A platform for AI-powered software engineers.

Local, offline RAG assistant that searches your own documents and answers questions with sources - no cloud.

A self-hosted CLIProxyAPI management panel and AI gateway observability dashboard

Share the traces your coding agents produce, on your terms, and earn credits.

Provider-neutral reasoning CLI with evidence-bound verification

A local-first dashboard that turns AI CLI session logs into tokens, cost, and trends

On-ramp CLI that points Claude Code, Codex, and other AI coding tools at an Anyray gateway.

Visual multi-agent AI orchestration that runs on your Claude subscription.

A local, explainable context compiler for AI coding agents