Browsing Artificial Intelligence and Machine Learning



Processed through Paypal
No account required.



Buy our over-priced crap to help pay the bills.
OlderGeeks 2025


Follow us on BlueskyFollow us on XJoin our Facebook groupFollow us on InstagramOur RSS FeedJoin us on TikTokJoin us on LinkedIn


 Home » OlderGeeks.com Freeware Downloads » Artificial Intelligence and Machine Learning   
Files
  File Name Rating Downloads
Last Update/Developer
BingGPT v0.3.4
BingGPT v0.3.4 Desktop application of Bing's AI-powered chat (Windows, Mac, Linux) 1. Get access to the early preview of new Bing 2. Sign in to your Microsoft account 3. Start chatting Features • Chat with new Bing without installing Microsoft Edge or browser plugins • Export full conversation to Markdown, PNG or PDF • Customize appearance (theme & font size) • Keyboard shortcuts • Multi-platform Warning: Avoid direct eye contact. This download is for the Windows installer version. All other download assets are below: Windows: BingGPT-0.3.4-win32-x64.zip BingGPT-0.3.4-win32-arm64-Setup.exe BingGPT-0.3.4-win32-arm64.zip macOS: BingGPT-0.3.4-darwin-x64.dmg BingGPT-0.3.4-darwin-arm64.dmg Linux: BingGPT-0.3.4-linux-x64.deb BingGPT-0.3.4-linux-x64.rpm BingGPT-0.3.4-linux-arm64.deb BingGPT-0.3.4-linux-arm64.rpm Click here to visit the author's website.
5/5 1,954 Apr 26, 2023
Microsoft Corporation
Clippy v0.4.3
Clippy v0.4.3 👉 A retro-style local AI chat app that runs GGUF large language models on your computer. Clippy lets you run a variety of large language models locally on your computer while using a nostalgic 1990s-style interface. It supports GGUF models through llama.cpp, includes one-click installation support for select models, and is designed as both a fun homage to Microsoft Office’s classic Clippy assistant and a reference implementation for Electron-based local LLM apps. Features: • Simple, familiar, and classic chat interface for chatting with local models. • Runs a variety of GGUF large language models locally on your computer. • Uses llama.cpp and node-llama-cpp to automatically discover the most efficient runtime path, such as Metal, CUDA, or Vulkan. • Includes one-click installation support for Google Gemma3, Meta Llama 3.2, Microsoft Phi-4, and Qwen Qwen3. • Lets you load your own downloaded models. • Allows custom prompts and parameter adjustments. • Works offline and locally, with the only network request being update checks, which can be disabled. • Styled as a love letter and homage to the late, great Clippy and 1990s Microsoft visual design. • Intended as a reference implementation of @electron/llm for developers building Electron apps with local language models. Supported operating systems: • Windows • macOS (Apple Silicon), macOS (Intel) • Linux (RPM, x64), Linux (Debian, x64) Supported languages: English Changes: v0.4.3 05-08-25 We still had issues with the incorrect native binaries making it into the build, breaking Clippy for Macs with Intel processors. This should finally be fixed. We figured it out! To move the Clippy icon to another position on your desktop: Left click on the icon, hold and drag it like normal but you have to hover your cursor over a part of Clippy that doesn't show a question mark. Like this: This download is for the Windows 64bit installer version (very bottom of page). All other download assets are below: Other Windows: Clippy-win32-x64-0.4.3.zip macOS: Clippy-darwin-arm64-0.4.3.zip Clippy-darwin-x64-0.4.3.zip Linux: clippy_0.4.3_amd64.deb Clippy-0.4.3-1.x86_64.rpm Click here to visit the author's ...
5/5 534 Mar 25, 2026
Felix Rieseberg
KoboldCpp v1.87.4
KoboldCpp v1.87.4 Run GGUF models easily with a KoboldAI UI. One File. Zero Install. KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable from Concedo, that builds off llama.cpp and adds many additional powerful features. Features: • Single file executable, with no installation required and no external dependencies • Runs on CPU or GPU, supports full or partial offloaded • LLM text generation (Supports all GGML and GGUF models, backwards compatibility with ALL past models) • Image Generation (Stable Diffusion 1.5, SDXL, SD3, Flux) • Speech-To-Text (Voice Recognition) via Whisper • Text-To-Speech (Voice Generation) via OuteTTS • Provides many compatible APIs endpoints for many popular webservices (KoboldCppApi OpenAiApi OllamaApi A1111ForgeApi ComfyUiApi WhisperTranscribeApi XttsApi OpenAiSpeechApi) • Bundled KoboldAI Lite UI with editing tools, save formats, memory, world info, author's note, characters, scenarios. • Includes multiple modes (chat, adventure, instruct, storywriter) and UI Themes (aesthetic roleplay, classic writer, corporate assistant, messsenger) • Supports loading Tavern Character Cards, importing many different data formats from various sites, reading or exporting JSON savefiles and persistent stories. • Many other features including new samplers, regex support, websearch, RAG via TextDB and more. • Ready-to-use binaries for Windows, MacOS, Linux, Android (via Termux), Colab, Docker, also supports other platforms if self-compiled (like Raspberry PI). • Need help finding a model? Read this! This download is for the Windows version (very bottom of page). All other download assets are below: Windows (other): koboldcpp_cu12.exe koboldcpp_nocuda.exe koboldcpp_oldcpu.exe macOS: koboldcpp-mac-arm64 Linux: koboldcpp-linux-x64-cuda1150 koboldcpp-linux-x64-cuda1210 koboldcpp-linux-x64-nocuda Click here to visit the author's website.
5/5 750 Apr 07, 2025
LostRuins
LM Studio v0.3.36
LM Studio v0.3.36 Your free, local AI toolkit. Run gpt-oss, Qwen, Gemma, DeepSeek on your Windows, Mac or Linux computer. Discover and download open source models, use them in chats or run a local server. LM Studio is free for home and work use. Terms Features: Run LLMs on Your Laptop or PC: Easily run LLMs like Llama and DeepSeek on your computer. No expertise required. Discover New and Noteworthy LLMs: Download and run any compatible llama.cpp or MLX model from Hugging Face. Power Apps Using the Local LLM Server: LM Studio comes with a built-in local server. You can use our SDKs or the OpenAI compatibility API. Chat with Your Local Documents (RAG): Attach PDFs, .docx and other files and process them locally and securely. Cross-platform local AI SDK: LM Studio SDK: Build local AI apps without dealing with dependencies. Changes: v0.3.36 12-18-25 Build 1 Support for Google's FunctionGemma (270M) This download is for the Windows 64bit version (very bottom of page). All other download assets are below: Windows: LM-Studio-0.3.36-1-arm64.exe (Windows ARM64) macOS: LM-Studio-0.3.36-1-arm64.dmg (Mac ARM64) Linux: LM-Studio-0.3.36-1-x64.AppImage (Linux 64bit) LM-Studio-0.3.36-1-arm64.AppImage Click here to visit the author's website.
5/5 1,121 Dec 30, 2025
Element Labs, Inc.
OpenNN v5.0.5
OpenNN v5.0.5 OpenNN is a software library written in C++ for advanced analytics. It implements neural networks, the most successful machine learning method. The main advantage of OpenNN is its high performance. This library outstands in terms of execution speed and memory allocation. It is constantly optimized and parallelized in order to maximize its efficiency. Some typical applications of OpenNN are business intelligence (customer segmentation, churn prevention...), health care (early diagnosis, microarray analysis,...) and engineering (performance optimization, predictive maintenance...). The documentation can be found at the official OpenNN site. CMakeLists.txt are build files for CMake, it is also used by the CLion IDE. The .pro files are project files for the Qt Creator IDE, which can be downloaded from its site. Note that OpenNN does not make use of the Qt library. This download is for the Windows version. If you need the Linux version, download here. Click here to visit the author's website.
5/5 3,467 Apr 22, 2021
Artelnics
Sherlock AI Detector v1.0
Sherlock AI Detector v1.0 Your Powerful Ally Against AI-Generated Texts. Introducing Sherlock AI Detector, an innovative tool employing cutting-edge technology to fight against one of the most pressing modern threats to academic integrity and business authenticity: AI-generated text fraud. Protect your institution, organization, or business from AI-produced texts, ensuring human authenticity and safeguarding your trustworthiness. Essential for the Modern Digital Landscape The rise of advanced artificial intelligence has brought along the challenge of distinguishing between human-written and AI-generated texts. AI-produced content can infringe upon academic integrity, mislead business communication, or even manipulate public perception. The Sherlock AI Detector is your defence in this high-tech era, providing a robust, easy-to-use solution. Promote Academic Integrity Sherlock AI Detector is an indispensable tool for educators seeking to maintain academic integrity. It helps detect and deter the use of AI-generated texts in academic submissions, promoting honesty and fairness in educational institutions. Preserving the integrity of academia is essential in the face of evolving technological landscapes. The rise of AI-generated text presents a new challenge to educators worldwide, but with Sherlock AI Detector, maintaining academic integrity just got easier. Features • Adaptive Learning Algorithms – Sherlock AI Detector uses human-built algorithms that are constantly adjusted and improved with each new piece of AI data, enhancing increased accuracy over time with multiple AI text generators. • Real-time AI Detection – The software performs real-time analysis of text files to immediately find patterns and other markers to detect that the text or part of it was created by artificial intelligence. • Secure and Compliant – We ensure that Sherlock AI Detector complies with all industry standards and regulations to guarantee your data’s privacy and security. To use... • Simply copy and paste text into the programs window or open an existing .txt file from your computer. • Click Start and let the program finish scanning. • Text highlighted ...
5/5 3,655 Sep 01, 2023
essayrewriteai.com
Thoth v3.2.0
Thoth v3.2.0 👉 A local-first AI assistant focused on privacy, autonomy, and on-device intelligence. Thoth is a free and open source local-first AI assistant designed to keep your models, data, and workflows on your own machine instead of in the cloud. It combines autonomous tool use, long-term memory, voice input and text-to-speech, vision and screen capture, health and habit tracking, workflows and scheduling, messaging channels, and file and data handling into a native desktop app. Thoth is built to give users personal AI sovereignty with local inference, local storage, opt-in online tools, and no subscriptions or telemetry. Features: • Local-first AI assistant with on-device inference, storage, and privacy-focused design • Autonomous ReAct agent with 20 integrated tools and 45 operations • Long-term memory with semantic recall across conversations • Voice input and offline text-to-speech with multiple English voice options • Vision support for webcam capture, screenshots, and image analysis • Habit and health tracking for medications, symptoms, exercise, mood, sleep, and more • Workflows and scheduling for reusable multi-step prompt sequences • Messaging channel support through Telegram bot and email integration • Gmail and Google Calendar integration with permission controls • File, chart, and structured data support including PDF, CSV, Excel, JSON, and Plotly charts • Native desktop app with first-run setup wizard, system tray support, and model selection • Supports curated local models including Qwen, Llama, Gemma, Mistral, DeepSeek, Phi, and more Supported operating systems: • Windows 10, Windows 11 • macOS 12 or higher Supported languages: Not Found Changes: v3.2.0 03-16-26 Automatic conversation summarization for effectively unlimited conversation length. Complete rewrite of the memory deduplication system to prevent duplicates and incorrect updates. Added deterministic deduplication using exact normalized-subject SQL lookups. Added cross-category deduplication for background extraction. Added source tracking for memories with live and extraction tagging. Added active thread exclusion to avoid race conditions during background extraction. Extended update_memory() to accept optional subject, tags, category, and source arguments. Added duplicate consolidation utility for near-duplicate memories. Added memory IDs ...
0/5 479 Mar 17, 2026
Siddharth Sachar
   
 
Showing rows 1 to 7 of 7 Showing Page 1 of 1  1 


OlderGeeks.com Copyright (c) 2026