Libraries

An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

• Inference
• Libraries

A zero-dependency canvas charting engine for building TradingView-style trading charts in JavaScript, with 66 technical indicators, 24 drawing tools, 17 chart types, and real-time streaming.

• Libraries

A free, CC0-licensed library of copy-paste retro 3D and demoscene graphics effects, such as plasma, raytracing, and voxel terrain, runnable as WebGL 1 or plain 2D canvas.

• Libraries

A document editor library for React with full DOCX import and export, real pagination, tracked changes, comments, live collaboration, and tools for AI agents to edit documents.

• Libraries

A SQL-first data-access toolkit for TypeScript that keeps ordinary SQL visible in tagged template literals, binds interpolated values safely by default, supports readable conditional SQL directives, and lets a schema validate the returned rows.

• Libraries
• Databases

A Swift package that answers multiple-choice, graded and yes/no questions about a piece of text using an on-device language model on Apple Core AI, returning a probability for each possible answer, inspired by TypeSafe's Jev.

• Inference
• Libraries

An independent implementation of TypeSafe's Jev wire format that adds typed, probability-scored multiple-choice, graded and yes/no questions on top of any OpenAI-compatible client, reading logprobs where a provider exposes them.

• Inference
• Libraries

Converts HTML into clean Markdown, through a web interface or directly in PHP, and can add content negotiation to an existing page so the same URL serves HTML or Markdown.

• Libraries

A fully generated C# SDK for the Jina API, covering embeddings, reranking and search, with Microsoft.Extensions.AI integration and support for .NET Framework, .NET Standard and modern .NET features such as trimming and NativeAOT.

• RAG
• Libraries

An async Python client for the SLMP protocol that Mitsubishi MELSEC PLCs speak over Ethernet, built from the observed behavior of a real CPU rather than its manual.

• Libraries

A Swift package that decomposes an image with Apple's Vision, CoreML, ARKit and LiDAR frameworks, fans it out into several vision-language-model calls, and aggregates typed results.

• Libraries

A zero-shot keyword and keyphrase extraction library that reads keywords directly out of a pretrained language model's attention weights, no fine-tuning or labeling required.

• Libraries

A C# REPL library that can be embedded in any .NET application, with syntax highlighting, code completion and runtime type introspection.

• Languages
• Libraries

A .NET library for on-demand local AI inference that ships with no bundled models, downloading and caching embeddings, generation, vision, OCR, translation, transcription, speech-synthesis and image-generation models the first time they are used.

• Inference
• Libraries

A library that stops one AI agent from silently overwriting another's concurrent edits to shared state such as a plan file or memory store, using a MESI-style coherence protocol and optimistic-concurrency commits verified in TLA+, across LangGraph, CrewAI and AutoGen.

• Agent frameworks
• Libraries

An on-device AI backend library for building in-game assistance features - screenshot understanding, retrieval-augmented Q&A, memory and speech recognition - accelerated on Intel GPU and NPU hardware, exposed to a game client over a local HTTP API.

• RAG
• Libraries

A .NET library and CLI that runs, fine-tunes and serves large language models in-process, adding local chat, RAG, agents and voice to .NET applications without Python, a GPU or a separate model server.

• Inference
• Libraries

Generates an OpenAPI 3.1 specification for a Phoenix application automatically, by reading its Ecto schemas, JSON views and router instead of a separate spec file.

• Libraries
• APIs

A .NET binding for Google DeepMind's EmbeddingGemma-300m model that runs fully local, offline text embedding with no API key or cloud dependency, distributed as a single NuGet package for ASP.NET Core and Microsoft Semantic Kernel.

• RAG
• Libraries

A V language binding for llama.cpp, letting V programs run quantized large language models such as DeepSeek or Qwen locally on CPU hardware.

• Inference
• Libraries

A 128-bit universal hash function for fast file and data-stream integrity checks with cryptographic strength, formally proven in Lean to have a low collision rate and reaching up to 130 GB/s on modern desktop CPUs.

• Libraries

A fast, idiomatic Go client library for the Telegram MTProto API, covering bots and user accounts, with generated protocol types, a handler and middleware system, a plugin lifecycle, pluggable storage backends and MTProxy support.

• Libraries
• APIs

A C# library that implements neural network inference and training as GPU compute kernels for .NET, running the same code on WebGPU, CUDA, OpenCL, WebGL, WebAssembly, and CPU, including inside a browser via Blazor WebAssembly.

• Inference
• Libraries

A Rust proc-macro SDK, released as the typebridge CLI, that generates matching TypeScript, Python Pydantic, Go, Swift, Kotlin, GraphQL, JSON Schema, Ruby, PHP and Dart types from annotated Rust structs and enums.

• Languages
• Libraries