Libreware

I Built a Safer #OpenClaw Alternative Using #Claude#AI Code OpenClaw is the fastest-growing open-source AI project in recent memory - 185,000 GitHub stars already! A legitimately impressive personal AI assistant that can manage your life and you can talk to it anywhere. But it has serious security issues - the docs literally say "there is no perfectly secure setup." So I took the core genius ideas from OpenClaw - the memory system, the proactive heartbeat, the multi-platform adapters, the extensibility through skills - and I built my own version using just Claude Code. It took me two days. The result is simpler, more secure, and tailored exactly to what I need. I'll introduce you to how I did this now and more content on this coming soon! https://youtu.be/XmweZ4fLkcI #assistant#agent

Dicio assistant Dicio is a free and open source#voice#assistant running on #Android. It supports many different skills and input/output methods, and it provides both speech and graphical feedback to a question. It interprets user input and (when possible) generates user output entirely on-device, providing privacy by design. It has multilanguage support, and is currently available in these languages: Czech, English, French, German, Greek, Italian, Polish, Russian, Slovenian, Spanish, Swedish and Ukrainian. Open to contributions :-D https://github.com/Stypox/dicio-android Download https://f-droid.org/packages/org.stypox.dicio https://github.com/Stypox/dicio-android/releases https://play.google.com/store/apps/details?id=org.stypox.dicio Skills Currently Dicio answers questions about: search: looks up information on DuckDuckGo (and in the future more engines) - Search for Dicio weather: collects weather information from OpenWeatherMap - What's the weather like? lyrics: shows Genius lyrics for songs - What's the song that goes we will we will rock you? open: opens an app on your device - Open NewPipe calculator: evaluates basic calculations - What is four thousand and two times three minus a million divided by three hundred? telephone: view and call contacts - Call Tom timer: set, query and cancel timers - Set a timer for five minutes current time: query current time - What time is it? navigation: opens the navigation app at the requested position - Take me to New York, fifteenth avenue media: play, pause, previous, next song Speech to text Dicio uses Vosk as its speech to text (#STT) engine. In order to be able to run on every phone small models are employed, weighing ~50MB. The download from here starts automatically whenever needed, so the app language can be changed seamlessly.

WhisperTux Simple #voice#dictation application for #Linux. Uses whisper.cpp for offline speech-to-text transcription. No fancy GPUs are required although whisper.cpp is capable of using them if available. Once your speech is transcribed, it is sent to a ydotool daemon that will write the text into the focused application. Features Local speech-to-text processing via whisper.cpp (no cloud dependencies) No expensive hardware required (works well on a plain x86 laptop with AVX instructions) Global keyboard shortcuts for system-wide operation Automatic text injection into focused applications Configurable whisper models and shortcuts https://github.com/cjams/whispertux #assistant#speech#stt

Home Assistant Voice Preview Edition Open, local, and private #voice#assistant https://www.home-assistant.io/voice-pe/ Resources https://voice-pe.home-assistant.io/resources/ https://github.com/esphome/home-assistant-voice-pe Community https://community.home-assistant.io/ Specs SoC ESP32-S3 SoC with 16 MB of FLASH storage 8 MB octal PSRAM Audio Processing XMOS XU316 Featuring: Echo cancellation Stationary noise removal Auto gain control Dedicated I2S lines for audio in and out Power / data USB-C, 5 V DC, 2 A Radios 2.4 GHz Wi-Fi Bluetooth 5.0 Audio output 3.5 mm (⅛”) stereo headphone jack Digital to analog converter (DAC): TI AIC3202 48 kHz sampling rate Software ESPHome preloaded Fully open-source firmware for both the ESP32 and XMOS chip #iot#homeassistant

Project Bringing Hardware Accelerated Language Models to Android Devices We introduce MLC LLM for Android – a solution that allows large language models to be deployed natively on Android devices, plus a productive framework for everyone to further optimize model performance for their use cases. Everything runs locally and accelerated with native GPU on the phone. We can run Vicuña-7b on Android Samsung Galaxy S23. Github https://github.com/mlc-ai/mlc-llm/tree/main/android Demo: https://mlc.ai/mlc-llm/#android #ai#assistant#gpt#android

OpenAssistant Open-source Chat AI https://www.youtube.com/watch?v=ddG2fM9i4Kk Try the chat: https://open-assistant.io/chat Homepage: https://open-assistant.io Dataset: https://huggingface.co/datasets/OpenAssistant/oasst1 Code: https://github.com/LAION-AI/Open-Assistant Paper (temporary): https://ykilcher.com/oa-paper #openassistant#chatgpt#ai#assistant

Ultimate #ai#assistant #ChatGPT with a voice interface https://github.com/lspahija/ultimate-ai-assistant https://ultimate-ai-assistant.up.railway.app/

Awesome-totally-open-ChatGPT A list of open alternatives to ChatGPT ChatGPT is GPT-3.5 with RLHF (Reinforcement Learning with Human Feedback) for chat system. By alternative, I mean projects feature different language model for chat system. Projects are not counted if they are: • alternative frontend projects because they just call the API from OpenAI. • alternative transformer decoder • models to GPT 3.5 either because the training data of them are (mostly) not for chat system. https://github.com/nichtdax/awesome-totally-open-chatgpt #ai#chatgpt#assistant

Project Alice Project Alice is a smart #voice home #assistant that is completely modular and extensible. It was first built around Snips therefore runs entirely offline and never sends or shares your voice interactions with anyone, Project Alice guarantees your privacy in your home or wherever you’re using Project Alice. However, as an option, since we've built Project Alice on top of Snips, Project Alice can be configured to use some online alternatives and fall backs (for example, using Amazon or Google’s Text to Speech engines), just like Snips. Since Snips (and the Project Alice team) strongly believe that decisions about your privacy should be made by you and you alone, these options are all disabled by default. https://github.com/project-alice-assistant/ProjectAlice Comments https://news.ycombinator.com/item?id=31227488 #voice#assistant#home

Dicio Voice assistant app for Android Dicio is a free and open source voice assistant running on Android. It supports many different skills and input/output methods, and it provides both speech and graphical feedback to a question. It uses Vosk for speech to text. It has multilanguage support, and is currently available in these languages: English, French, German, Greek, Italian, Russian and Spanish. Features: Search: looks up information on DuckDuckGo. Weather: weather information from OpenWeatherMap Lyrics: shows Genius lyrics for songs. Open: open an app on your device. Telephone: view and call contacts Timer: set, query and cancel timers Download: https://f-droid.org/packages/org.dicio.dicio_android https://github.com/Stypox/dicio-android/releases #New#Assistant#Voice @foss_Android