Libraries

A Rust image-dithering and halftoning library that works directly on typed pixel buffers, offering ordered, diffusion, stochastic and palette-based methods to avoid banding when reducing color depth.

• Libraries

An open-source Python package that produces typed, calibrated decisions from any open-weights language model in a single forward pass, reading the model's own next-token probabilities rather than generating text, as an open alternative to TypeSafe's Jev.

• Inference
• Libraries

A Python library that runs structured natural-language tasks, such as extracting bullet points, generating question-and-answer pairs and building knowledge graphs, locally through a fine-tuned 135-million-parameter language model instead of a large general-purpose one.

• Models
• Libraries

An unofficial PyTorch implementation of the Recurrent Looped Transformer proposed by Yifan Zhang of Princeton, an encoder-decoder architecture that can share weights between encoder and decoder and vary its recurrent block size across a sequence.

• Models
• Libraries

A Go dependency-injection library that generates plain Go code at compile time, combining a minimal Fx-style API with Wire-style code generation so there is no runtime reflection or extra runtime dependency.

• Libraries

A Python library that compiles neural-network graphs directly into programs for Apple's Neural Engine, bypassing Core ML so that training, not just inference, can run on the chip.

• Inference
• Libraries

A framework for running neural network models in the browser, React Native and Electron on the user's own GPU, compiling its kernels to WebGPU shaders at runtime instead of a WASM binary.

• Inference
• Libraries

A tool that reconstructs a path from custom C code to a runnable kernel on Intel Core Ultra NPUs, exposing the chip's programmable SHAVE cores that Intel's public software stack otherwise hides behind graph-level programming only.

• Libraries

A React Native library for on-device subject cutouts, image labeling and OCR, using Apple's Vision framework on iOS and Google's ML Kit on Android through Nitro Modules.

• Mobile
• Libraries

A software development kit for building an AI copilot into a product, with React components for the frontend and a multi-provider LLM SDK for the backend.

• Libraries
• UI kits

A Python implementation of the DroneCAN protocol stack, a lightweight CAN-bus communication protocol for aerospace and robotics, providing code generation, an interface and supporting utilities.

• Libraries

A Rust crate implementing the BM25 relevance-scoring algorithm as an embedder, scorer and in-memory search engine, for use directly or alongside vector databases such as Qdrant, Pinecone or Milvus.

• RAG
• Libraries

A Python automation layer for authoring and filling HWPX documents, Hancom Office's format, providing a Python API, a command-line tool and an optional MCP server for AI agents, without requiring Hancom Office or Windows.

• Libraries

A Dart code-generation and build system, used as an alternative to the standard Dart build tools, aimed at faster incremental builds and a simpler configuration model.

• CLI tools
• Libraries

A Java library that adds code completion, parsing and error-underlining for languages such as Java, JavaScript, C, CSS and HTML to the RSyntaxTextArea text-editing component.

• Editors
• Libraries

An open-source Python library that simulates quantum circuits locally, so quantum programs written for the Amazon Braket SDK can be tested on a laptop before being submitted to the Braket cloud service.

• Testing
• Libraries

A Godot 4.5 plugin that runs a local LLM inside a game through a bundled llama.cpp backend, giving an in-game agent node both a text reply and an action a creature or NPC can act on.

• Inference
• Libraries

A library that generates short, memorable word-based identifiers for AI agents to pass through prompts and logs, using fewer tokens than a UUID and configurable collision resistance.

• Agent memory
• Libraries

A JSON-based document format that renders like a PDF, diffs cleanly in git and edits in any text editor, aimed at documents that software agents read and write as often as people do.

• Libraries

A provider library that lets a developer run Qiskit quantum programs on quantum devices and simulators available through Amazon Braket.

• Libraries

An on-device speech infrastructure library in C++17 for Linux, Windows and Android, providing voice activity detection, streaming speech-to-text, speaker diarization, text-to-speech and a voice-agent pipeline.

• Speech
• Libraries

A Ruby framework, made for Rails but usable in plain Ruby, for building observable, cost-controlled LLM pipelines with automatic model fallback, retries and consensus-based decisions.

• Agent frameworks
• Libraries

Ruby bindings for llama.cpp that run open-source language models such as Gemma, Qwen, Llama and GPT-OSS locally, directly inside a Ruby application, plus a standalone interactive CLI chat.

• Inference
• Libraries

A fast, multithreaded CPU library of SIMD-optimized quantization and dequantization kernels for machine learning, more than twice as fast as PyTorch's built-in routines on tested hardware.

• Models
• Libraries