A Ruby gem providing a consistent interface for various AI/ML tokenizers including OpenAI GPT, Anthropic Claude, Google Gemini, Meta Llama, Mistral, Qwen, and embedding models like BERT, BGE, and multilingual-E5. Features caching, truncation, token counting, and error handling across different to...

Create a Slack bot that is smart and so easy to expand, create new bots on demand, run ruby code on chat, create shortcuts, chatGPT, DALL-E, Whisper... The main scope of this gem is to be used internally in the company so teams can create team channels with their own bot to help them on their d...

commit with ai

Output test code using LLM agents.

HTM (Hierarchical Temporal Memory) provides intelligent memory/context management for LLM-based applications. It implements a two-tier memory system with durable long-term storage (PostgreSQL) and token-limited working memory, enabling applications to recall context from past conversations using ...

Add this plugin to your Jekyll site and all posts will be automatically translated to the languages of your choice through ChatGPT

Kward is a Ruby CLI coding agent with local workspace tools, configurable prompts, web search, sessions, and an experimental JSON-RPC backend.

LLM Conductor provides a clean, unified interface for working with multiple Language Model providers including OpenAI GPT, Anthropic Claude, Google Gemini, Groq, OpenRouter, and Ollama. Features include prompt templating, token counting, and extensible client architecture.

Train and run GPT models in Ruby using torch.rb. A minimal, educational implementation of GPT-2 style models.

OpenAI Ruby Wrapper

Tiktoken tokenizer for Roseflow.

This gem provides static analysis for common prompt engineering anti-patterns, helping developers write better prompts for LLM interactions.

Pure-Ruby facade over Hugging Face `tokenizers`, OpenAI `tiktoken_ruby`, and SentencePiece bindings that maps ruby_llm model identifiers (gpt-4o, llama-3, mistral, ...) to the correct tokenizer and exposes a small API for counting, analyzing, and truncating text against a model's context window. ...