The LL(k) Interpreted Parser (llip) is an automated tool to easily create an LL(k) parser and the related scanner without the need of generating anything. Everything is done on the fly through a simple DSL. == A Little comparrison against other tools Tools like JavaCC, ANTLR, Coco/R and others ...

LLM Chain is a powerful Ruby framework that provides tools for building sophisticated LLM-powered applications. It includes support for prompt management, conversation chains, memory systems, vector storage integration, and seamless LLM provider connections. Key features: • Chain-based convers...

Interact with PostgreSQL, MySQL, and Oracle databases using natural language. Powered by RubyLLM with a locally-running Ollama model.

Use this 'compiler' to build software using LLMs in a controlled way. In classical terms, the LLM is the compiler, the context description is the programming language, and the generated output is the binary.

Memory infrastructure for agents: short-term checkpointing, long-term file-based and graph-based memory, retrieval with time decay, and maintenance jobs.

The shared foundation for a family of gems (llm_mock_anthropic, and more) that build fake LLM SDK response objects for tests that stub the client directly. This gem defines the common provider contract those gems implement so tools like deja can drive any provider uniformly. You usually depend on...

Fabricate Anthropic Ruby SDK response objects — messages, content blocks, tool_use blocks, and streams — for tests that stub the client directly and return canned responses, without hitting the network or wrestling the real SDK's typed models. Also serializes those objects to/from plain hashes, w...

A simple and flexible framework for managing prompts and LLM interactions with OpenAI and Anthropic Claude

Build composable LLM workflows using Unix pipe philosophy. Each pipe is a YAML-configured LLM call that communicates via stdin/stdout.

A unified interface for multiple LLM providers (OpenAI, Anthropic, Google, OpenRouter). Supports streaming, tool calling, and configurable logging.

A client to interact with LLM APIs in a consistent way.

Ruby library for interacting with various LLM providers including Anthropic, Google Gemini, xAI, and other OpenAI-compatible API providers (including local models). Supports streaming, event-handling, conversation management, tool-use, image input, and cost-tracking.

Pipeline: URL → ContentFetcher (Markdown) → LlmClient (JSON). Supports Jina/Firecrawl fetchers and OpenAI-compatible/Anthropic LLM providers.

llm-spell is a command-line utility that can correct spelling mistakes with the help of a Large Language Model (LLM). Compared to traditional spell checkers like `aspell` and `hunspell`, llm-spell often produces fewer false positives and more accurate suggestions.

LLMs::Tool provides a simple DSL for defining tools that can be serialized to the correct JSON schema to be used with LLM systems

A Ruby gem for translating Markdown files using AI while preserving formatting

A library for accessing data from Lloyds Bank's online banking

Helping rubyist integration with lianlian pay(lianlianpay llpay) easier.

LLT meta gem

LLT Constants Package.