Github Top Repositories
Photo
🔥 cactus-compute/needle is trending — and it deserves your attention.
🔗 https://github.com/cactus-compute/needle
📝 14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
──────────────────────────────
The Needle repository on GitHub is home to an open 45M-parameter model designed for tool calling, device use, and structured extraction. This model is unique in that it's a single 14MB binary that requires approximately 28MB of RAM to run a full session. Key features of the Needle model include its self-contained nature, with weights baked into the engine, a simple contract for tool calls, confidence-gated responses, and bounded memory usage.
To use the Needle model, you can install it via pip with
Technical highlights of the Needle model include its use of a Simple Attention Network architecture, which is a dense small-model recipe that incorporates a Hadamard MLP, GQA attention, and engram key-value memory. The model is also compressed using CQ2-bit with Cactus Quants, which reduces its size while maintaining its performance.
The Needle model is suitable for a wide range of audiences, including developers, researchers, and anyone interested in natural language processing and tool calling. With its unique combination of features and technical advancements, the Needle model is a valuable resource for anyone looking to explore the possibilities of AI-powered tool calling and extraction.
In summary, the Needle model is a powerful and efficient tool for natural language processing and tool calling, with a unique combination of features and technical advancements that make it an exciting and valuable resource - and with Needle, you can have the power of a large language model in the palm of your hand.
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔗 https://github.com/cactus-compute/needle
📝 14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
──────────────────────────────
The Needle repository on GitHub is home to an open 45M-parameter model designed for tool calling, device use, and structured extraction. This model is unique in that it's a single 14MB binary that requires approximately 28MB of RAM to run a full session. Key features of the Needle model include its self-contained nature, with weights baked into the engine, a simple contract for tool calls, confidence-gated responses, and bounded memory usage.
To use the Needle model, you can install it via pip with
pip install cactus-needle and then describe your tools to interact with the model. The model supports tool retrieval, where it can select the most relevant tools based on the input query, and confidence-gated responses, where the model returns a confidence score with each response.Technical highlights of the Needle model include its use of a Simple Attention Network architecture, which is a dense small-model recipe that incorporates a Hadamard MLP, GQA attention, and engram key-value memory. The model is also compressed using CQ2-bit with Cactus Quants, which reduces its size while maintaining its performance.
The Needle model is suitable for a wide range of audiences, including developers, researchers, and anyone interested in natural language processing and tool calling. With its unique combination of features and technical advancements, the Needle model is a valuable resource for anyone looking to explore the possibilities of AI-powered tool calling and extraction.
In summary, the Needle model is a powerful and efficient tool for natural language processing and tool calling, with a unique combination of features and technical advancements that make it an exciting and valuable resource - and with Needle, you can have the power of a large language model in the palm of your hand.
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
❤1
🔥 altic-dev/FluidVoice is trending — and it deserves your attention.
🔗 https://github.com/altic-dev/FluidVoice
📝 Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a ton :) Windows & iOS waitlist open. Linux soon.
──────────────────────────────
FluidVoice is an open-source, on-device AI-enhanced voice-to-text dictation app for macOS. It features
To get started,
Key Features:
- On-device AI enhancement with
- Multiple speech models for different languages and latency needs
-
- Live preview with notch support and adaptive theming
Technical Highlights:
- Built with Swift and Swift Package Manager
- Supports Apple Silicon and Intel Macs (via Whisper models)
- Requires macOS 15.0 or later and ~1 GB disk space for a voice model
Audience:
- Individuals looking for a free, open-source dictation app with on-device AI enhancement
- Developers interested in contributing to the project or building from source
Get started with
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔗 https://github.com/altic-dev/FluidVoice
📝 Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a ton :) Windows & iOS waitlist open. Linux soon.
──────────────────────────────
FluidVoice is an open-source, on-device AI-enhanced voice-to-text dictation app for macOS. It features
Fluid Intelligence, a local AI model for smart formatting and context-aware capitalization, and supports various speech models like Nemotron, Parakeet, and Whisper. To get started,
brew install --cask fluidvoice or download the latest release. Grant microphone and accessibility permissions, set your hotkey, and go through onboarding to choose your voice model. Key Features:
- On-device AI enhancement with
Fluid Intelligence- Multiple speech models for different languages and latency needs
-
Command Mode for voice control and Write Mode for dictation in any text field- Live preview with notch support and adaptive theming
Technical Highlights:
- Built with Swift and Swift Package Manager
- Supports Apple Silicon and Intel Macs (via Whisper models)
- Requires macOS 15.0 or later and ~1 GB disk space for a voice model
Audience:
- Individuals looking for a free, open-source dictation app with on-device AI enhancement
- Developers interested in contributing to the project or building from source
Get started with
FluidVoice today and experience fast, accurate, and private dictation on your Mac - your voice, your words, your way.──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
Github Top Repositories
Photo
🔍 Deep-diving into unslothai/unsloth — fresh off the trending list.
🔗 https://github.com/unslothai/unsloth
📝 Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
──────────────────────────────
Unsloth is a cutting-edge desktop app that allows users to run and train AI models locally, with support for various types of models. It features a user-friendly interface, native support for CPU, NVIDIA, AMD, and Intel hardware, and multi-GPU setups. Users can
The app offers a range of features, including model training, fine-tuning, and deployment, as well as private and unlimited web search, deep research, and RAG. It also supports
Unsloth is designed for developers, researchers, and AI enthusiasts who want to work with AI models locally, without relying on cloud services. The app is free to use and offers a range of community resources, including documentation, tutorials, and forums.
To get started with Unsloth, users can simply
One of the key benefits of Unsloth is its ability to run AI models locally, which provides a high level of security and control for users. The app also offers
Overall, Unsloth is a powerful and flexible tool for working with AI models locally, and it offers a range of features and benefits that make it an attractive choice for developers, researchers, and AI enthusiasts.
Takeaway: Unsloth is the ultimate tool for running and training AI models locally, offering a unique combination of power, flexibility, and security.
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔗 https://github.com/unslothai/unsloth
📝 Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
──────────────────────────────
Unsloth is a cutting-edge desktop app that allows users to run and train AI models locally, with support for various types of models. It features a user-friendly interface, native support for CPU, NVIDIA, AMD, and Intel hardware, and multi-GPU setups. Users can
download the app for Windows, macOS, or Linux, and start using it right away. The app offers a range of features, including model training, fine-tuning, and deployment, as well as private and unlimited web search, deep research, and RAG. It also supports
image and video diffusion, audio models, and reinforcement learning. Unsloth is designed for developers, researchers, and AI enthusiasts who want to work with AI models locally, without relying on cloud services. The app is free to use and offers a range of community resources, including documentation, tutorials, and forums.
To get started with Unsloth, users can simply
download the app and follow the installation instructions. The app also offers a web-based interface and a command-line interface for more advanced users. One of the key benefits of Unsloth is its ability to run AI models locally, which provides a high level of security and control for users. The app also offers
remote access capabilities, allowing users to access their models from anywhere. Overall, Unsloth is a powerful and flexible tool for working with AI models locally, and it offers a range of features and benefits that make it an attractive choice for developers, researchers, and AI enthusiasts.
Takeaway: Unsloth is the ultimate tool for running and training AI models locally, offering a unique combination of power, flexibility, and security.
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
Github Top Repositories
Photo
⚡ macro-inc/macro is making waves. Here's the full picture.
🔗 https://github.com/macro-inc/macro
📝 Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.
──────────────────────────────
Hey there, let's check out the Macro GitHub repo. Macro is an all-in-one workspace that combines email, messages, docs, tasks, agents, and CRM into a single, fast interface with shared team-level memory. It's designed to be a single operating system for your team, eliminating the need for multiple tools.
The key features of Macro include:
-
-
-
In terms of technical highlights, Macro is built with
Macro is suitable for small companies or teams within larger companies, looking for an all-in-one workspace solution. The ideal audience includes teams seeking to streamline their workflow, reduce tool clutter, and improve collaboration.
One-liner takeaway: Simplify your team's workflow with Macro, the all-in-one workspace that's about to revolutionize how you get things done!
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔗 https://github.com/macro-inc/macro
📝 Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory.
──────────────────────────────
Hey there, let's check out the Macro GitHub repo. Macro is an all-in-one workspace that combines email, messages, docs, tasks, agents, and CRM into a single, fast interface with shared team-level memory. It's designed to be a single operating system for your team, eliminating the need for multiple tools.
The key features of Macro include:
-
Modular blocks that work together like Lego, allowing for customization and extensibility-
Bidirectional graph for cross-references between different surfaces, such as docs and tasks-
Real-time collaborative editing with CRDTs, making it feel like you're editing on the same computerIn terms of technical highlights, Macro is built with
SolidJS and Rust for speed and reliability. The CRDT collaboration system allows for seamless editing and conflict resolution, even with multiple agents operating simultaneously.Macro is suitable for small companies or teams within larger companies, looking for an all-in-one workspace solution. The ideal audience includes teams seeking to streamline their workflow, reduce tool clutter, and improve collaboration.
One-liner takeaway: Simplify your team's workflow with Macro, the all-in-one workspace that's about to revolutionize how you get things done!
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
Github Top Repositories
Photo
📌 Spotted on GitHub Trending: megadose/holehe — let's break it down.
🔗 https://github.com/megadose/holehe
📝 holehe allows you to check if the mail is used on different sites like twitter, instagram and will retrieve information on sites with the forgotten password function.
──────────────────────────────
Holehe is an Open-Source Intelligence (OSINT) tool that efficiently finds registered accounts from emails. It checks if an email is attached to an account on over 120 sites like Twitter, Instagram, and Imgur.
Key features include:
- retrieving information using the forgotten password function
- not alerting the target email
- running on
To use Holehe, you can install it via
The output is a dictionary with information like rate limits, account existence, and sometimes partially obfuscated recovery emails and phone numbers.
This tool is perfect for security researchers, OSINT investigators, and anyone interested in email reconnaissance.
One-liner takeaway: Holehe is a must-have OSINT tool that helps you uncover hidden email accounts without alerting the target.
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔗 https://github.com/megadose/holehe
📝 holehe allows you to check if the mail is used on different sites like twitter, instagram and will retrieve information on sites with the forgotten password function.
──────────────────────────────
Holehe is an Open-Source Intelligence (OSINT) tool that efficiently finds registered accounts from emails. It checks if an email is attached to an account on over 120 sites like Twitter, Instagram, and Imgur.
Key features include:
- retrieving information using the forgotten password function
- not alerting the target email
- running on
Python 3To use Holehe, you can install it via
pip3 install holehe, git clone, or docker. holehe [email protected] is a simple command to run the tool. For more complex usage, you can integrate it into your Python applications.The output is a dictionary with information like rate limits, account existence, and sometimes partially obfuscated recovery emails and phone numbers.
This tool is perfect for security researchers, OSINT investigators, and anyone interested in email reconnaissance.
One-liner takeaway: Holehe is a must-have OSINT tool that helps you uncover hidden email accounts without alerting the target.
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔥 smicallef/spiderfoot is trending — and it deserves your attention.
🔗 https://github.com/smicallef/spiderfoot
📝 SpiderFoot automates OSINT for threat intelligence and mapping your attack surface.
──────────────────────────────
SpiderFoot is an open-source intelligence (OSINT) automation tool that integrates with numerous data sources and utilizes various methods for data analysis. It offers a web-based interface and command-line functionality, all written in
Key features include over 200 modules, a
This tool can be used for both offensive and defensive purposes, such as reconnaissance or gathering information about exposed internet assets. It's highly configurable, fully documented, and has a visual interface.
The target audience includes security professionals, developers, and anyone interested in OSINT and data analysis.
Overall, SpiderFoot is a powerful tool for automating OSINT tasks and analyzing large amounts of data. With its extensive features and customization options, it's an essential tool for anyone looking to streamline their OSINT workflow: SpiderFoot is your ultimate OSINT sidekick!
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔗 https://github.com/smicallef/spiderfoot
📝 SpiderFoot automates OSINT for threat intelligence and mapping your attack surface.
──────────────────────────────
SpiderFoot is an open-source intelligence (OSINT) automation tool that integrates with numerous data sources and utilizes various methods for data analysis. It offers a web-based interface and command-line functionality, all written in
Python 3 and MIT-licensed. Key features include over 200 modules, a
YAML-configurable correlation engine, and support for CSV/JSON/GEXF export. It also has TOR integration for dark web searches and a Dockerfile for Docker-based deployments. This tool can be used for both offensive and defensive purposes, such as reconnaissance or gathering information about exposed internet assets. It's highly configurable, fully documented, and has a visual interface.
The target audience includes security professionals, developers, and anyone interested in OSINT and data analysis.
Overall, SpiderFoot is a powerful tool for automating OSINT tasks and analyzing large amounts of data. With its extensive features and customization options, it's an essential tool for anyone looking to streamline their OSINT workflow: SpiderFoot is your ultimate OSINT sidekick!
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
⚡ NVIDIA-NeMo/Switchyard is making waves. Here's the full picture.
🔗 https://github.com/NVIDIA-NeMo/Switchyard
📝 No description.
──────────────────────────────
Introducing Switchyard, a Rust proxy and library designed for Large Language Model (LLM) traffic management. It routes requests across multiple providers, translates between OpenAI and Anthropic APIs, records operational metrics, and provides typed, composable routing algorithms.
Main features include protocol translation, multi-backend routing, and operational metrics. You can use Switchyard as a launcher, server, or library, making it a versatile tool for managing LLM traffic.
To get started, you can choose the
Technical highlights include support for various routing strategies, such as LLM classifier, stage router, escalation router, and random routing. Switchyard also provides a simple architecture for routing and translation.
Switchyard is designed for developers and researchers working with LLMs, especially those who need to manage traffic across multiple models and providers.
In a nutshell, Switchyard is your one-stop solution for LLM traffic management - route, translate, and optimize your way to AI efficiency.
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔗 https://github.com/NVIDIA-NeMo/Switchyard
📝 No description.
──────────────────────────────
Introducing Switchyard, a Rust proxy and library designed for Large Language Model (LLM) traffic management. It routes requests across multiple providers, translates between OpenAI and Anthropic APIs, records operational metrics, and provides typed, composable routing algorithms.
Main features include protocol translation, multi-backend routing, and operational metrics. You can use Switchyard as a launcher, server, or library, making it a versatile tool for managing LLM traffic.
To get started, you can choose the
launcher path to run coding agents like Claude Code or Codex through Switchyard, the server path to run Switchyard as a standalone proxy, or the library path to embed routing algorithms in your own Rust application.Technical highlights include support for various routing strategies, such as LLM classifier, stage router, escalation router, and random routing. Switchyard also provides a simple architecture for routing and translation.
Switchyard is designed for developers and researchers working with LLMs, especially those who need to manage traffic across multiple models and providers.
In a nutshell, Switchyard is your one-stop solution for LLM traffic management - route, translate, and optimize your way to AI efficiency.
──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe