Alternatives to SpeziLLM

SwiftOpenAI: an MIT-licensed Swift package for calling the OpenAI API with native async/await and Combine on Apple platforms.

PrivateGPT is the open-source on-premise RAG framework for local document Q&A — 57k GitHub stars, zero cloud calls.

RubyLLM is the Ruby-native AI framework for chat, agents, tools, and RAG across 19 providers with one API.

xsAI is an extra-small OpenAI-compatible AI SDK for JavaScript and TypeScript — 13.1 KB gzipped with every package included.

TypeLLM returns typed, schema-conformant values from text and images in one API call — no JSON repair loops.

Open-source Python library that constrains LLM output with regex, context-free grammars, and inline control flow.

Outlines is a Python library for structured generation that constrains LLM decoding so JSON, regex, and grammar outputs are valid every

Open-source TypeScript SDK for streaming AI apps and agents across 100+ models, with built-in provider fallbacks

Attention Sinks keeps Llama, Mistral, MPT, Falcon and Pythia chat models fluent with constant VRAM via a one-line import swap.

Hugging Face Tokenizers: train BPE, WordPiece and Unigram vocabularies and tokenize a GB of text in under 20 seconds.

Unified C# .NET library for calling 15+ LLM providers through a single strongly-typed API.

Free OpenAI API examples and Python notebooks for building chat, embeddings, and RAG apps

Open-source Ruby gem that calls 11 LLM providers through one consistent interface for embeddings, completions, and chat.

LMQL is a programming language for LLMs that uses types, templates and constraints to make prompts modular and outputs reliable.

DiscuroAI chains GPT-3 prompt templates and DALL-E 2 image calls into multi-step workflows you run with one API request that returns JSON.

Mellea turns type-annotated Python functions into validated, testable LLM calls with token-level constrained decoding.

Go SDK for AI apps: one type-safe API for text generation, streaming, tools and MCP across 25+ LLM providers.

Drop-in AI autocomplete for any text input — two lines of code, OpenAI's GPT models underneath.

Open-source Ruby gem giving one unified API across Anthropic, DeepSeek, Google, Mistral, Llama, and OpenAI

AnyAPI A/B tests your GPT-3 prompts and serves the winning variant as a live REST API endpoint.

A Scala library that calls OpenAI's HTTP APIs from the JVM with typed, effect-friendly code

Open-source Java library that tokenizes text with OpenAI's BPE encodings so you can count, encode and decode locally

Open-source framework for adding agent chat, generative UI, and human approvals to React apps on any agent backend.

Bitsandbytes is the free, MIT-licensed PyTorch library for 8-bit optimizers, LLM.int8() inference, and QLoRA 4-bit training.

Open-source Python framework that adds retrieval-augmented document Q&A to your app in five lines of code

Open-source Java library that puts a unified LLM and vector store API inside your JVM app

Eino is an open-source Go LLM framework from ByteDance for building agents, graphs, and RAG pipelines in your existing Go backend.

Open-source, self-hosted RAG API from talkd.ai that runs any LLM over your own documents via Docker Compose.

Open-source Python RAG framework that turns your PDFs, Notion pages, and websites into a queryable AI app in a few lines of code.

Rig is an open-source Rust LLM framework for shipping type-safe AI agents across 20+ providers.