✨ RLinf | Python
🎯 Primary Use Case:
Post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.
✨ Key Features:
• Macro-to-Micro Flow (M2Flow)
• Flexible Execution Modes (Collocated, Disaggregated, Hybrid)
• Auto-scheduling Strategy
• Embodied Agent Support
• Online Reinforcement Learning Support
📖 Summary:
RLinf is an open-source infrastructure for post-training foundation models using reinforcement learning. It provides a flexible and scalable framework with features like macro-to-micro flow, flexible execution modes (collocated, disaggregated, hybrid), and auto-scheduling, supporting embodied agent development and integration with various VLA models and simulators.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.
✨ Key Features:
• Macro-to-Micro Flow (M2Flow)
• Flexible Execution Modes (Collocated, Disaggregated, Hybrid)
• Auto-scheduling Strategy
• Embodied Agent Support
• Online Reinforcement Learning Support
📖 Summary:
RLinf is an open-source infrastructure for post-training foundation models using reinforcement learning. It provides a flexible and scalable framework with features like macro-to-micro flow, flexible execution modes (collocated, disaggregated, hybrid), and auto-scheduling, supporting embodied agent development and integration with various VLA models and simulators.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
💡 Paper2Video | Python
🎯 Primary Use Case:
Generating presentation videos from scientific papers
✨ Key Features:
• Automatic video generation from scientific papers
• PaperTalker agent for presentation creation (slides, subtitling, cursor grounding, speech synthesis, talking-head video rendering)
📖 Summary:
Paper2Video automatically generates presentation videos from scientific papers. It addresses two main problems: creating a presentation video from a paper using PaperTalker (integrating slides, subtitling, cursor grounding, speech synthesis, and talking-head video rendering) and evaluating presentation video quality using the Paper2Video benchmark with designed metrics.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Generating presentation videos from scientific papers
✨ Key Features:
• Automatic video generation from scientific papers
• PaperTalker agent for presentation creation (slides, subtitling, cursor grounding, speech synthesis, talking-head video rendering)
📖 Summary:
Paper2Video automatically generates presentation videos from scientific papers. It addresses two main problems: creating a presentation video from a paper using PaperTalker (integrating slides, subtitling, cursor grounding, speech synthesis, and talking-head video rendering) and evaluating presentation video quality using the Paper2Video benchmark with designed metrics.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🌟 server | TypeScript
🎯 Primary Use Case:
Secure, self-hosted file storage, sharing, and collaboration with a focus on data ownership and control.
✨ Key Features:
• Modern, Fast, and High-Performance Interface
• Security & Data Ownership
• Advanced User Access Control
• Collaboration & Integration (OnlyOffice)
• Powerful Full-Text Search
📖 Summary:
The Sync-in Server is a self-hosted, open-source platform for file storage, sharing, collaboration, and synchronization. It emphasizes data ownership and control, offering features like collaborative spaces, secure file sharing, and granular permission management for various environments.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Secure, self-hosted file storage, sharing, and collaboration with a focus on data ownership and control.
✨ Key Features:
• Modern, Fast, and High-Performance Interface
• Security & Data Ownership
• Advanced User Access Control
• Collaboration & Integration (OnlyOffice)
• Powerful Full-Text Search
📖 Summary:
The Sync-in Server is a self-hosted, open-source platform for file storage, sharing, collaboration, and synchronization. It emphasizes data ownership and control, offering features like collaborative spaces, secure file sharing, and granular permission management for various environments.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🔥1
✨ SummaryYou | Kotlin
🎯 Primary Use Case:
Summarizing various forms of digital content (YouTube videos, articles, images, and documents) using AI.
✨ Key Features:
• Summarize YouTube-Videos, Articles, Images and Documents with AI
• Set length of summary
• Read-Out the summaries
• History-Section
• Intelligent paywall detection
📖 Summary:
SummaryYou is an Android application that leverages AI to summarize various types of content, including YouTube videos, articles, images, and documents. It offers features like adjustable summary length, text-to-speech functionality, history tracking, intelligent paywall detection, and a Material Design 3-based user interface.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Summarizing various forms of digital content (YouTube videos, articles, images, and documents) using AI.
✨ Key Features:
• Summarize YouTube-Videos, Articles, Images and Documents with AI
• Set length of summary
• Read-Out the summaries
• History-Section
• Intelligent paywall detection
📖 Summary:
SummaryYou is an Android application that leverages AI to summarize various types of content, including YouTube videos, articles, images, and documents. It offers features like adjustable summary length, text-to-speech functionality, history tracking, intelligent paywall detection, and a Material Design 3-based user interface.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🔥 MediaInfo | C++
🎯 Primary Use Case:
Analyzing video and audio files to extract and display their technical metadata and tags.
✨ Key Features:
• CLI for various desktop operating systems
• Qt GUI for Windows and Linux
• UWP GUI for Windows
• VCL GUI for Windows
• wxWidgets GUI for Windows and Linux
📖 Summary:
The MediaInfo repository provides a command-line interface (CLI) and graphical user interfaces (GUIs) for displaying technical and tag data extracted from video and audio files. It supports various operating systems, including Windows, macOS, Linux, Android, and Apple's operating systems, and offers different GUI options based on the platform.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Analyzing video and audio files to extract and display their technical metadata and tags.
✨ Key Features:
• CLI for various desktop operating systems
• Qt GUI for Windows and Linux
• UWP GUI for Windows
• VCL GUI for Windows
• wxWidgets GUI for Windows and Linux
📖 Summary:
The MediaInfo repository provides a command-line interface (CLI) and graphical user interfaces (GUIs) for displaying technical and tag data extracted from video and audio files. It supports various operating systems, including Windows, macOS, Linux, Android, and Apple's operating systems, and offers different GUI options based on the platform.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
✨ dyad | TypeScript
🎯 Primary Use Case:
Building AI applications locally with user-provided API keys.
✨ Key Features:
• Local execution
• Bring your own keys
• Cross-platform compatibility
📖 Summary:
Dyad is a local, open-source AI app builder that allows users to create AI applications directly on their machines. It emphasizes speed, privacy, and user control, differentiating itself by allowing users to bring their own API keys and offering cross-platform compatibility.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Building AI applications locally with user-provided API keys.
✨ Key Features:
• Local execution
• Bring your own keys
• Cross-platform compatibility
📖 Summary:
Dyad is a local, open-source AI app builder that allows users to create AI applications directly on their machines. It emphasizes speed, privacy, and user control, differentiating itself by allowing users to bring their own API keys and offering cross-platform compatibility.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🌟 waha | TypeScript
🎯 Primary Use Case:
Automating WhatsApp interactions via HTTP API for tasks such as sending notifications, building chatbots, and integrating WhatsApp with other systems.
✨ Key Features:
• REST API for WhatsApp automation
• Session management
• Sending text messages
• Receiving messages (implicit)
• QR code scanning for authentication
📖 Summary:
WAHA is a WhatsApp HTTP API (REST API) that allows users to automate WhatsApp interactions through HTTP requests. It provides a simple way to send and receive messages, manage sessions, and integrate WhatsApp functionality into other applications. The API supports multiple engines, including browser-based (WEBJS), WebSocket Node.js (NOWEB), and WebSocket Go (GOWS).
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Automating WhatsApp interactions via HTTP API for tasks such as sending notifications, building chatbots, and integrating WhatsApp with other systems.
✨ Key Features:
• REST API for WhatsApp automation
• Session management
• Sending text messages
• Receiving messages (implicit)
• QR code scanning for authentication
📖 Summary:
WAHA is a WhatsApp HTTP API (REST API) that allows users to automate WhatsApp interactions through HTTP requests. It provides a simple way to send and receive messages, manage sessions, and integrate WhatsApp functionality into other applications. The API supports multiple engines, including browser-based (WEBJS), WebSocket Node.js (NOWEB), and WebSocket Go (GOWS).
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🔥 zuse | Go
🎯 Primary Use Case:
Chatting on IRC from the terminal.
✨ Key Features:
• Terminal-based IRC client
• Built with Go and Bubble Tea
• Minimal and distraction-free interface
• Keybindings for navigation (scrolling, switching panes, quitting)
📖 Summary:
ZUSE is a terminal-based IRC client written in Go using the Bubble Tea framework. It aims to provide a clean and distraction-free IRC experience directly within the terminal, allowing users to chat efficiently.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Chatting on IRC from the terminal.
✨ Key Features:
• Terminal-based IRC client
• Built with Go and Bubble Tea
• Minimal and distraction-free interface
• Keybindings for navigation (scrolling, switching panes, quitting)
📖 Summary:
ZUSE is a terminal-based IRC client written in Go using the Bubble Tea framework. It aims to provide a clean and distraction-free IRC experience directly within the terminal, allowing users to chat efficiently.
🔗 Links:
• View Project
================
🔓 Open Source
🚀 duckstation | C++
🎯 Primary Use Case:
Emulating PlayStation 1 games on various platforms (Windows, Linux, macOS).
✨ Key Features:
• CPU Recompiler/JIT (x86-64, armv7/AArch32, AArch64, RISC-V/RV64)
• Hardware renderer supporting D3D11, D3D12, OpenGL, Vulkan and Metal APIs
• Upscaling, texture filtering, and true colour (24-bit) in hardware renderers
• PGXP for geometry precision, texture correction, and depth buffer emulation
• Save state support, with runahead and rewind
📖 Summary:
DuckStation is a PlayStation 1 emulator focused on playability, speed, and long-term maintainability. It aims for accuracy while maintaining performance on low-end devices, supporting various hardware renderers and CPU architectures.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Emulating PlayStation 1 games on various platforms (Windows, Linux, macOS).
✨ Key Features:
• CPU Recompiler/JIT (x86-64, armv7/AArch32, AArch64, RISC-V/RV64)
• Hardware renderer supporting D3D11, D3D12, OpenGL, Vulkan and Metal APIs
• Upscaling, texture filtering, and true colour (24-bit) in hardware renderers
• PGXP for geometry precision, texture correction, and depth buffer emulation
• Save state support, with runahead and rewind
📖 Summary:
DuckStation is a PlayStation 1 emulator focused on playability, speed, and long-term maintainability. It aims for accuracy while maintaining performance on low-end devices, supporting various hardware renderers and CPU architectures.
🔗 Links:
• View Project
================
🔓 Open Source
🚀 nanochat | Python
🎯 Primary Use Case:
Training and deploying a customizable LLM on a single machine for experimentation and learning.
✨ Key Features:
• Full-stack LLM implementation
• Single-node operation (8XH100)
• Complete pipeline: tokenization, pretraining, finetuning, evaluation, inference, web serving
• Minimal and hackable codebase
• Training and inference scripts (e.g., speedrun.sh)
📖 Summary:
nanochat is a full-stack implementation of an LLM similar to ChatGPT, designed to be minimal, hackable, and run on a single 8XH100 node. It covers the entire pipeline from tokenization to web serving, allowing users to train and interact with their own LLM. The repository provides scripts for pretraining, finetuning, evaluation, and inference, with a focus on accessibility and customization.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Training and deploying a customizable LLM on a single machine for experimentation and learning.
✨ Key Features:
• Full-stack LLM implementation
• Single-node operation (8XH100)
• Complete pipeline: tokenization, pretraining, finetuning, evaluation, inference, web serving
• Minimal and hackable codebase
• Training and inference scripts (e.g., speedrun.sh)
📖 Summary:
nanochat is a full-stack implementation of an LLM similar to ChatGPT, designed to be minimal, hackable, and run on a single 8XH100 node. It covers the entire pipeline from tokenization to web serving, allowing users to train and interact with their own LLM. The repository provides scripts for pretraining, finetuning, evaluation, and inference, with a focus on accessibility and customization.
🔗 Links:
• View Project
================
🔓 Open Source
🔥 OpenStock | TypeScript
🎯 Primary Use Case:
Providing an open-source alternative to commercial stock market platforms for tracking and analysis.
✨ Key Features:
• Real-time price tracking
• Personalized alerts
• Detailed company insights
• Open-source and free
📖 Summary:
OpenStock is an open-source platform for tracking real-time stock prices, setting personalized alerts, and exploring company insights. It aims to provide a free alternative to expensive market platforms, built with technologies like Next.js, TypeScript, and MongoDB.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Providing an open-source alternative to commercial stock market platforms for tracking and analysis.
✨ Key Features:
• Real-time price tracking
• Personalized alerts
• Detailed company insights
• Open-source and free
📖 Summary:
OpenStock is an open-source platform for tracking real-time stock prices, setting personalized alerts, and exploring company insights. It aims to provide a free alternative to expensive market platforms, built with technologies like Next.js, TypeScript, and MongoDB.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
✨ VisualStoryWriting | TypeScript
🎯 Primary Use Case:
Editing and refining stories through visual manipulation and AI-powered suggestions.
✨ Key Features:
• Visualizing story events on a timeline
• Editing story text by manipulating visual representations
• Suggesting text edits based on character interactions
• Suggesting text edits based on character positions
📖 Summary:
The Visual Story-Writing repository provides a system that automatically visualizes a story based on its chronological events, characters, actions, and movements. It allows users to edit the story by manipulating these visual representations, with GPT-4o suggesting edits to the text based on the visual changes.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Editing and refining stories through visual manipulation and AI-powered suggestions.
✨ Key Features:
• Visualizing story events on a timeline
• Editing story text by manipulating visual representations
• Suggesting text edits based on character interactions
• Suggesting text edits based on character positions
📖 Summary:
The Visual Story-Writing repository provides a system that automatically visualizes a story based on its chronological events, characters, actions, and movements. It allows users to edit the story by manipulating these visual representations, with GPT-4o suggesting edits to the text based on the visual changes.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
💡 humanify | TypeScript
🎯 Primary Use Case:
Deobfuscating and making human-readable obfuscated or minified JavaScript code.
✨ Key Features:
• Deobfuscation of JavaScript code
• Unminification of JavaScript code
• Transpilation of JavaScript code
• Decompilation of JavaScript code
• Unpacking of JavaScript code
📖 Summary:
HumanifyJS is a tool designed to deobfuscate, unminify, transpile, decompile, and unpack JavaScript code using large language models (LLMs) like ChatGPT and Llama, combined with AST-level transformations via Babel. It offers both cloud-based (OpenAI, Gemini) and local modes for deobfuscation, providing users with flexibility based on their needs and resources.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Deobfuscating and making human-readable obfuscated or minified JavaScript code.
✨ Key Features:
• Deobfuscation of JavaScript code
• Unminification of JavaScript code
• Transpilation of JavaScript code
• Decompilation of JavaScript code
• Unpacking of JavaScript code
📖 Summary:
HumanifyJS is a tool designed to deobfuscate, unminify, transpile, decompile, and unpack JavaScript code using large language models (LLMs) like ChatGPT and Llama, combined with AST-level transformations via Babel. It offers both cloud-based (OpenAI, Gemini) and local modes for deobfuscation, providing users with flexibility based on their needs and resources.
🔗 Links:
• View Project
================
🔓 Open Source
🌟 core-sdk | TypeScript
🎯 Primary Use Case:
Creating interactive 2D canvas-based applications with features like drag-and-drop, shape manipulation, and plugin-based extensibility.
✨ Key Features:
• Framework-agnostic
• Plugin system
• Complete toolset (grid, rulers, guides, area selection)
• Hotkeys
• Rich shapes
📖 Summary:
The Flowscape Core SDK is a framework-agnostic 2D canvas engine built on Konva.js. It provides a set of tools and plugins for creating interactive 2D applications, including features like grid, rulers, hotkeys, and rich shapes. It's designed to be extensible and easy to integrate with different JavaScript frameworks.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Creating interactive 2D canvas-based applications with features like drag-and-drop, shape manipulation, and plugin-based extensibility.
✨ Key Features:
• Framework-agnostic
• Plugin system
• Complete toolset (grid, rulers, guides, area selection)
• Hotkeys
• Rich shapes
📖 Summary:
The Flowscape Core SDK is a framework-agnostic 2D canvas engine built on Konva.js. It provides a set of tools and plugins for creating interactive 2D applications, including features like grid, rulers, hotkeys, and rich shapes. It's designed to be extensible and easy to integrate with different JavaScript frameworks.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 Scraperr | TypeScript
🎯 Primary Use Case:
Web scraping and data extraction from websites.
✨ Key Features:
• XPath-Based Extraction
• Queue Management
• Domain Spidering
• Custom Headers
• Media Downloads
📖 Summary:
Scraperr is a self-hosted web scraping solution that allows users to scrape websites without writing code. It offers features like XPath-based extraction, queue management, domain spidering, and data export in various formats, making it a versatile tool for web data extraction.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Web scraping and data extraction from websites.
✨ Key Features:
• XPath-Based Extraction
• Queue Management
• Domain Spidering
• Custom Headers
• Media Downloads
📖 Summary:
Scraperr is a self-hosted web scraping solution that allows users to scrape websites without writing code. It offers features like XPath-based extraction, queue management, domain spidering, and data export in various formats, making it a versatile tool for web data extraction.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 ssh-bot | Go
🎯 Primary Use Case:
Remotely executing commands on servers or devices within a home network via a Telegram bot interface.
✨ Key Features:
• Executing commands on local or remote hosts via SSH
• Support for parallel command execution
• SSH connection manager with host availability check
• Support for directory navigation
• Combined access to remote hosts by key and/or password
📖 Summary:
The ssh-bot is a Telegram bot written in Go that allows users to execute commands on remote hosts via SSH. It eliminates the need for VPNs or external IP addresses by providing asynchronous command execution and supports various authentication methods and configuration options.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Remotely executing commands on servers or devices within a home network via a Telegram bot interface.
✨ Key Features:
• Executing commands on local or remote hosts via SSH
• Support for parallel command execution
• SSH connection manager with host availability check
• Support for directory navigation
• Combined access to remote hosts by key and/or password
📖 Summary:
The ssh-bot is a Telegram bot written in Go that allows users to execute commands on remote hosts via SSH. It eliminates the need for VPNs or external IP addresses by providing asynchronous command execution and supports various authentication methods and configuration options.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
💡 inpaint-web | TypeScript
🎯 Primary Use Case:
In-browser image inpainting and upscaling
✨ Key Features:
• Image Inpainting (修复)
• Super-Resolution (图片高清化)
• Image Modification History
• Model Optimization
• Post-Processing Integrated into the Model
📖 Summary:
Inpaint-web is a free and open-source inpainting and image-upscaling tool that operates entirely within the browser using WebGPU and WASM technologies. It allows users to repair and enhance images directly in their browser without relying on server-side processing.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
In-browser image inpainting and upscaling
✨ Key Features:
• Image Inpainting (修复)
• Super-Resolution (图片高清化)
• Image Modification History
• Model Optimization
• Post-Processing Integrated into the Model
📖 Summary:
Inpaint-web is a free and open-source inpainting and image-upscaling tool that operates entirely within the browser using WebGPU and WASM technologies. It allows users to repair and enhance images directly in their browser without relying on server-side processing.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🚀 flint | TypeScript
🎯 Primary Use Case:
Managing KVM virtual machines with a focus on ease of use and minimal overhead.
✨ Key Features:
• Modern Web UI (Next.js + Tailwind)
• Single Binary (<11MB)
• CLI and API for automation
• Cloud-Init support
• Snapshot-based template system
📖 Summary:
Flint is a lightweight KVM management tool designed for developers, sysadmins, and home labs. It provides a modern web UI, CLI, and API for managing virtual machines, emphasizing simplicity and efficiency by avoiding XML and unnecessary bloat.
🔗 Links:
• View Project
================
🔓 Open Source
🎯 Primary Use Case:
Managing KVM virtual machines with a focus on ease of use and minimal overhead.
✨ Key Features:
• Modern Web UI (Next.js + Tailwind)
• Single Binary (<11MB)
• CLI and API for automation
• Cloud-Init support
• Snapshot-based template system
📖 Summary:
Flint is a lightweight KVM management tool designed for developers, sysadmins, and home labs. It provides a modern web UI, CLI, and API for managing virtual machines, emphasizing simplicity and efficiency by avoiding XML and unnecessary bloat.
🔗 Links:
• View Project
================
🔓 Open Source
🚀 Disciplined-AI-Software-Development | Python
🎯 Primary Use Case:
Collaborating with AI systems on software development projects to mitigate common issues like code bloat and architectural drift.
✨ Key Features:
• AI Behavioral Configuration using custom instructions and persona frameworks
📖 Summary:
The Disciplined AI Software Development methodology provides a structured approach for collaborating with AI systems on software development projects. It addresses common issues like code bloat, architectural drift, and context dilution through systematic constraints and validation checkpoints. The methodology uses four stages with systematic constraints, behavioral consistency enforcement, and validation checkpoints.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Collaborating with AI systems on software development projects to mitigate common issues like code bloat and architectural drift.
✨ Key Features:
• AI Behavioral Configuration using custom instructions and persona frameworks
📖 Summary:
The Disciplined AI Software Development methodology provides a structured approach for collaborating with AI systems on software development projects. It addresses common issues like code bloat, architectural drift, and context dilution through systematic constraints and validation checkpoints. The methodology uses four stages with systematic constraints, behavioral consistency enforcement, and validation checkpoints.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
💡 Daft | Rust
🎯 Primary Use Case:
Large-scale data processing and analysis, including multimodal data, in distributed computing environments.
✨ Key Features:
• Familiar interactive API (Lazy Python Dataframe, SQL)
• Powerful Query Optimizer
• Data Catalog integrations (AWS Glue, Unity Catalog, Apache Iceberg)
• Rich multimodal type-system (Images, URLs, Tensors)
• Seamless Interchange (Apache Arrow)
📖 Summary:
Daft is a distributed query engine, written in Rust, designed for large-scale data processing using Python or SQL. It focuses on providing a familiar interactive API, powerful query optimization, data catalog integrations, rich multimodal type-system, seamless interchange with Apache Arrow, and is built for cloud environments.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Large-scale data processing and analysis, including multimodal data, in distributed computing environments.
✨ Key Features:
• Familiar interactive API (Lazy Python Dataframe, SQL)
• Powerful Query Optimizer
• Data Catalog integrations (AWS Glue, Unity Catalog, Apache Iceberg)
• Rich multimodal type-system (Images, URLs, Tensors)
• Seamless Interchange (Apache Arrow)
📖 Summary:
Daft is a distributed query engine, written in Rust, designed for large-scale data processing using Python or SQL. It focuses on providing a familiar interactive API, powerful query optimization, data catalog integrations, rich multimodal type-system, seamless interchange with Apache Arrow, and is built for cloud environments.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
💡 pocket-server | TypeScript
🎯 Primary Use Case:
Running and managing AI agents locally and interacting with them remotely via a mobile application.
✨ Key Features:
• Agent runtime and tools
• Native mobile terminal
• File system + editor
• Repo search
• Background/cloud agents
📖 Summary:
Pocket Server is a local runtime environment for AI agents, designed to run on a user's machine and be controlled via a mobile app. It provides core OS capabilities like agent runtime, a mobile terminal, file system access, and remote access, enabling users to interact with their codebase and agents from their phone.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source
🎯 Primary Use Case:
Running and managing AI agents locally and interacting with them remotely via a mobile application.
✨ Key Features:
• Agent runtime and tools
• Native mobile terminal
• File system + editor
• Repo search
• Background/cloud agents
📖 Summary:
Pocket Server is a local runtime environment for AI agents, designed to run on a user's machine and be controlled via a mobile app. It provides core OS capabilities like agent runtime, a mobile terminal, file system access, and remote access, enabling users to interact with their codebase and agents from their phone.
🔗 Links:
• View Project
• Homepage
================
🔓 Open Source