Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.

New user experiences for interacting with agents

Evaluation and Tracking for LLM Experiments

Android launcher without app drawer based on Lawnchair

Neo-Launcher

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

A full-featured and easy-to-use web framework with the Rust programming language.

aria2 is a lightweight multi-protocol & multi-source, cross platform download utility operated in command-line. It supports HTTP/HTTPS, FTP, SFTP, BitTorrent and Metalink.

A platform for building proxies to bypass network restrictions.

// Source : ISO

SpotX patcher used for patching the desktop version of Spotify

🐢 Open-Source Evaluation & Testing for AI & LLM systems

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

A flexible distributed key-value datastore that is optimized for caching and other realtime workloads.

Command line interface for testing internet bandwidth using speedtest.net

Uncomplicated Observability for Python and beyond! 🪵🔥

A fancy self-hosted monitoring tool

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

Yet another WebUI for Nginx

Penpot: The open-source design tool for design and code collaboration

Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.

Build Better Websites. Create modern, resilient user experiences with web fundamentals.

FFmpeg for browser, powered by WebAssembly

Open-source keyboard firmware for Atmel AVR and Arm USB families

Embedded graphics library to create beautiful UIs for any MCU, MPU and display type.

(CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.