# crmne/ruby_llm

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/crmne-ruby-llm).**

3,566 stars · 376 forks · Ruby · mit

## Links

- GitHub: https://github.com/crmne/ruby_llm
- Homepage: https://rubyllm.com/
- awesome-repositories: https://awesome-repositories.com/repository/crmne-ruby-llm.md

## Topics

`ai` `anthropic` `chatgpt` `claude` `deepseek` `embeddings` `gemini` `gpustack` `image-generation` `llm` `mistral` `ollama` `openai` `openrouter` `perplexity` `rails` `ruby` `vertex-ai` `xai`

## Description

ruby_llm is an LLM integration framework and AI agent orchestrator designed to connect applications to multiple large language model providers through a unified interface. It serves as a toolkit for building autonomous assistants with custom personas, managing structured output via JSON schemas, and implementing vector embedding engines for semantic search.

The project distinguishes itself as an observability suite and multimodal toolkit. It provides specialized capabilities for tracking token usage, calculating model costs, and tracing workflows via OpenTelemetry, while supporting the processing of images, audio, video, and documents through a consistent API.

The framework covers a broad surface of AI infrastructure, including retrieval-augmented generation workflows, multi-step task orchestration, and the ability to expose local Ruby methods as tools for AI models to execute. It also provides utilities for content moderation, multimodal data extraction, and concurrent request management.

The system includes tools to bootstrap AI infrastructure using database migrations and configuration files.

## Tags

### Artificial Intelligence & ML

- [Autonomous Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-orchestration.md) — Functions as an orchestrator for building and deploying autonomous agents with persistent memory and complex workflows.
- [Provider-Agnostic Model Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/provider-agnostic-model-interfaces.md) — Standardizes diverse LLM provider APIs into a consistent interface to eliminate provider-specific parsing logic.
- [AI Agent Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-definitions.md) — Allows the creation of specialized assistants by combining models, instructions, and toolsets into reusable personas. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [AI Agent Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-orchestration.md) — Provides a framework for coordinating specialized AI agents with custom personas, instructions, and toolsets.
- [AI Code Interpreters](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-code-interpreters.md) — Implements environments where AI models generate and execute code to perform calculations or system interactions. ([source](https://rubyllm.com/overview/))
- [AI Conversation Managers](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-conversation-managers.md) — Offers interfaces for managing multiple AI model sessions, including history and configuration parameters. ([source](https://rubyllm.com/overview/))
- [AI Observability Suites](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-observability-suites.md) — Provides a diagnostic suite for tracing, monitoring token usage, and calculating the costs of AI workflows.
- [Persona and Behavioral Instructions](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-prompt-engineering-templates/automated-prompt-generation/persona-and-behavioral-instructions.md) — Defines AI personas and behavioral constraints using persistent system prompts throughout conversations. ([source](https://rubyllm.com/chat/))
- [AI Provider Managers](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-provider-managers.md) — Includes utilities for managing API keys and authentication connections across multiple AI services. ([source](https://rubyllm.com/configuration/))
- [AI Workflow Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-workflow-orchestrators.md) — Coordinates complex task sequences using sequential, parallel, and routing execution patterns. ([source](https://rubyllm.com/agentic-workflows/))
- [Language Model Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations.md) — Provides adapters and interfaces to send prompts and manage interactions with various hosted or local language model providers. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Chat History APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/chat-history-apis.md) — Provides interfaces for persisting and querying conversational message logs and history in a database. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Chat State Management](https://awesome-repositories.com/f/artificial-intelligence-ml/chat-state-management.md) — Provides headless management of chat history and streaming responses integrated into database models. ([source](https://rubyllm.com/next/))
- [Code Execution Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/code-execution-tools.md) — Provides built-in tools for agents to perform real-world calculations and logic via code execution. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Runtime Context Injections](https://awesome-repositories.com/f/artificial-intelligence-ml/context-injection/runtime-context-injections.md) — Passes session-specific data and user inputs to tools without exposing them to the LLM schema. ([source](https://rubyllm.com/agents/))
- [Conversation History Management](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-history-management.md) — Provides tools for storing and retrieving logs of agent-user interactions to maintain context. ([source](https://rubyllm.com/chat/))
- [Database Model Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/database-model-integrations.md) — Connects chat capabilities directly to database models for easy persistence and retrieval. ([source](https://rubyllm.com/))
- [External Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-execution.md) — Triggers local methods to perform actions or fetch real-time data based on model requests. ([source](https://rubyllm.com/next/))
- [Function Calling Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/function-calling-interfaces.md) — Enables language models to execute external tools and API functions to extend their capabilities. ([source](https://rubyllm.com/available-models/))
- [Image Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation.md) — Creates images from text prompts using a unified interface that abstracts different provider requirements. ([source](https://rubyllm.com/image-generation/))
- [Image Generation Models](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation-models.md) — Generates original visual content from text descriptions using AI painting models. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Persistent Chat Histories](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/ai-memory-systems/persistent-chat-histories.md) — Maintains long-term conversational context by saving chat sessions and messages to a database. ([source](https://rubyllm.com/getting-started/))
- [Conversational Response Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-response-generators/response-generation-configurations/conversational-response-generation.md) — Produces conversational chat responses through a unified interface connecting to multiple LLM providers. ([source](https://rubyllm.com/))
- [LLM Application Infrastructure](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-application-infrastructure.md) — Provides infrastructure for managing model registries, API keys, and a provider-agnostic interface.
- [LLM Integration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-integration-frameworks.md) — Serves as a unified integration framework for connecting applications to various large language model providers.
- [LLM Response Streaming](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-response-streaming.md) — Delivers language model outputs incrementally as standardized chunks to reduce perceived latency. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Multi-Modal Input Processors](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/multimodal-processing-tools/multi-modal-input-processors.md) — Implements a unified interface to ingest and normalize images, audio, videos, and PDFs for model processing. ([source](https://rubyllm.com/chat/))
- [Tool Call Executions](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-tool-connectors/tool-call-executions.md) — Executes custom Ruby classes as tools and persists the resulting interactions as conversation messages. ([source](https://rubyllm.com/rails/))
- [Model Routing Registries](https://awesome-repositories.com/f/artificial-intelligence-ml/model-architecture-registries/model-registries/model-routing-registries.md) — Maps model identifiers to routing logic and pricing metadata via a structured database registry.
- [Model Provider Abstractions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-abstractions.md) — Provides a unified interface that normalizes API interactions across multiple AI service providers. ([source](https://rubyllm.com/overview/))
- [Multimodal AI Toolkits](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-ai-toolkits.md) — Provides a comprehensive toolkit for processing text, images, audio, and video using a consistent API.
- [Multimodal Document Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-document-processing.md) — Processes images, videos, audio, and documents to extract information and summaries through a unified interface. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Multimodal Integration Libraries](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-integration-libraries.md) — Integrates diverse media types including images, audio, video, and PDFs into AI pipelines via a unified API.
- [Structured Output Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-code-generators/structured-generation-engines/structured-output-generators.md) — Forces language models to produce strictly typed, machine-readable JSON data formats for programmatic parsing. ([source](https://rubyllm.com/available-models/))
- [Tool Schema Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-implementations/lightweight-model-implementations/custom-model-logic-interfaces/tool-schema-definitions.md) — Creates executable functions with structured schemas that models use to interact with external systems. ([source](https://rubyllm.com/tools/))
- [RAG Context Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/rag-context-retrieval.md) — Implements retrieval-augmented generation to provide relevant grounded context from knowledge bases to the model. ([source](https://rubyllm.com/agentic-workflows/))
- [Structured Data Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/structured-data-extraction.md) — Enforces and extracts structured JSON formats from model outputs for predictable programmatic parsing. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Structured Output Enforcements](https://awesome-repositories.com/f/artificial-intelligence-ml/structured-output-enforcements.md) — Enforces JSON response formats using domain-specific language definitions to ensure predictable programmatic parsing.
- [Text Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-numeric-transformations/text-embeddings.md) — Transforms text strings into numerical vector representations to enable semantic search and similarity analysis. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Tool Calling Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-calling-implementations.md) — Connects local code functions to a model to perform real-world actions or retrieve data. ([source](https://rubyllm.com/))
- [Dynamic Tool Schema Injection](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-integrations/dynamic-tool-schema-injection.md) — Dynamically injects structured tool schemas into model prompts to enable real-time interaction with local Ruby methods.
- [Vector Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/vector-embeddings.md) — Transforms raw text into numerical vector representations for use in semantic search and retrieval. ([source](https://rubyllm.com/))
- [Visual Input Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/visual-input-processing.md) — Analyzes visual content from images and PDF documents using large language models to extract information. ([source](https://rubyllm.com/available-models/))
- [Agent File Attachments](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-file-attachments.md) — Provides mechanisms to attach files and documents to messages to enable multimodal context for AI agents. ([source](https://rubyllm.com/rails/))
- [Parallel Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/parallel-tool-execution.md) — Runs multiple tool calls in parallel using lightweight threads to reduce overall agent latency. ([source](https://rubyllm.com/tools/))
- [Model Registries](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations/model-registries.md) — Provides a database-backed catalogue of available models and their provider routing configurations. ([source](https://rubyllm.com/rails/))
- [Multi-Provider Chat Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-integration-interfaces/ai-model-interfaces/llm-chat-interfaces/multi-provider-chat-interfaces.md) — Provides controllers and views for building real-time chat interfaces that support multiple AI providers. ([source](https://rubyllm.com/rails/))
- [AI Performance Monitoring](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-performance-monitoring.md) — Tracks AI operation efficiency, throughput, and response times via a monitoring dashboard with automated alerts. ([source](https://rubyllm.com/ecosystem/))
- [Audio Transcriptions](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-transcriptions.md) — Implements capabilities to convert spoken audio recordings into written text for analysis. ([source](https://rubyllm.com/))
- [Automated Output Evaluation](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-output-evaluation.md) — Provides automated quality and safety checks for model responses using deterministic assertions and secondary model evaluations. ([source](https://rubyllm.com/ecosystem/))
- [Evaluator-Optimizer Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-agent-loops/research-quality-refinement-loops/evaluator-optimizer-loops.md) — Implements an iterative loop between an evaluator and an optimizer to refine the quality of AI outputs. ([source](https://rubyllm.com/agentic-workflows/))
- [Prompt Configuration Files](https://awesome-repositories.com/f/artificial-intelligence-ml/declarative-agent-schemas/prompt-configuration-files.md) — Supports loading system instructions from external template files to separate prompt engineering from application code. ([source](https://rubyllm.com/agents/))
- [Local Model Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/local-model-execution.md) — Executes quantized models within the local process to enable offline capabilities and ensure data privacy. ([source](https://rubyllm.com/ecosystem/))
- [Model Capability Registries](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-and-validation/model-capability-assessment/model-capability-queries/model-capability-registries.md) — Provides a registry to track available models and automatically detect their capabilities and pricing. ([source](https://rubyllm.com/))
- [Model Metadata Registrars](https://awesome-repositories.com/f/artificial-intelligence-ml/model-api-gateways/model-metadata-registrars.md) — Implements interfaces for defining and persisting configuration metadata for external AI models. ([source](https://rubyllm.com/configuration/))
- [Model Context Protocol Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/model-context-protocol-integrations.md) — Integrates the standardized Model Context Protocol to link AI models to external tools and resources. ([source](https://rubyllm.com/ecosystem/))
- [Model Identifier Mappings](https://awesome-repositories.com/f/artificial-intelligence-ml/model-identifier-mappings.md) — Resolves user-defined model aliases and unique identifiers to specific model instances and backends. ([source](https://rubyllm.com/models/))
- [Real-Time Audio Transcribers](https://awesome-repositories.com/f/artificial-intelligence-ml/real-time-audio-transcribers.md) — Provides a unified interface to convert spoken language from various audio file formats into text. ([source](https://rubyllm.com/audio-transcription/))
- [Reasoning Capture Utilities](https://awesome-repositories.com/f/artificial-intelligence-ml/reasoning-models/reasoning-capture-utilities.md) — Captures and extracts the internal thinking process of reasoning-capable models to provide visibility into their logic. ([source](https://rubyllm.com/thinking/))
- [Reasoning Process Controllers](https://awesome-repositories.com/f/artificial-intelligence-ml/reasoning-workflows/reasoning-process-controllers.md) — Manages the reasoning process by persisting internal thinking steps before delivering a final answer. ([source](https://rubyllm.com/))
- [Unified Audio Transcription](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-transcription/automated-video-transcribers/offline-media-transcribers/unified-audio-transcription.md) — Converts spoken language from audio files into written text. ([source](https://cdn.jsdelivr.net/gh/crmne/ruby_llm@main/README.md))
- [Multimodal Context Injection](https://awesome-repositories.com/f/artificial-intelligence-ml/visual-content-analysis/multimodal-context-injection.md) — Enables sending files or documents back to the model alongside text to facilitate visual analysis. ([source](https://rubyllm.com/tools/))

### Part of an Awesome List

- [AI Agents and Assistants](https://awesome-repositories.com/f/awesome-lists/ai/ai-agents-and-assistants.md) — Provides a framework for building specialized AI assistants with custom personas and complex workflows. ([source](https://rubyllm.com/))
- [AI Agent Deployment Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/ai-agent-deployment-frameworks.md) — Launches reusable assistants capable of performing complex tasks autonomously within production environments. ([source](https://rubyllm.com/next/))
- [Agent Execution Traces](https://awesome-repositories.com/f/awesome-lists/devops/observability-and-tracing/agent-execution-traces.md) — Sends OpenTelemetry traces of agent decisions and tool calls to backends for execution flow analysis. ([source](https://rubyllm.com/ecosystem/))
- [Sensitive Data Redaction](https://awesome-repositories.com/f/awesome-lists/devtools/information-extraction/sensitive-data-identification/sensitive-data-redaction.md) — Removes confidential data from conversations to prevent sensitive information from reaching external AI providers. ([source](https://rubyllm.com/ecosystem/))

### Data & Databases

- [Agent State Persistence](https://awesome-repositories.com/f/data-databases/agent-state-persistence.md) — Provides mechanisms to persist agent sessions, chat history, and internal context directly within database models.
- [Conversation History Stores](https://awesome-repositories.com/f/data-databases/conversation-history-stores.md) — Stores chats, messages, and system instructions in a database to maintain state across user sessions. ([source](https://rubyllm.com/rails/))
- [AI](https://awesome-repositories.com/f/data-databases/data-persistence/ai.md) — Integrates chat and message capabilities into database models to handle persistence and associations. ([source](https://rubyllm.com/overview/))
- [Structured Data Schemas](https://awesome-repositories.com/f/data-databases/structured-data-schemas.md) — Creates JSON schemas using a domain-specific language to enforce structured data output from models. ([source](https://rubyllm.com/ecosystem/))
- [Reasoning](https://awesome-repositories.com/f/data-databases/data-persistence/reasoning.md) — Saves reasoning output and token counts to a database for auditing and cost tracking. ([source](https://rubyllm.com/thinking/))
- [Document and Unstructured Extraction](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/data-processing/document-unstructured-extraction.md) — Parses information from files like PDFs and CSVs to convert unstructured content into usable data. ([source](https://rubyllm.com/))

### Development Tools & Productivity

- [Tool Interaction Streams](https://awesome-repositories.com/f/development-tools-productivity/search-filtering-tools/tool-interaction-filters/tool-interaction-streams.md) — Yields partial text and tool requests while resuming output delivery after tool execution completes. ([source](https://rubyllm.com/streaming/))
- [Application Debug Logging](https://awesome-repositories.com/f/development-tools-productivity/application-debug-logging.md) — Logs detailed request and response data to troubleshoot communication between the application and AI providers. ([source](https://rubyllm.com/error-handling/))

### System Administration & Monitoring

- [Event Monitoring Systems](https://awesome-repositories.com/f/system-administration-monitoring/event-monitoring-systems.md) — Broadcasts AI-related internal events and task lifecycle data for monitoring and observability. ([source](https://rubyllm.com/rails/))
- [AI Observability](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/ai-observability.md) — Offers specialized tracking for token usage, cost calculation, and workflow tracing via OpenTelemetry.
- [Token Usage Analytics](https://awesome-repositories.com/f/system-administration-monitoring/usage-monitoring/token-usage-analytics.md) — Calculates normalized input, output, and cached token counts for accurate usage tracking and billing. ([source](https://rubyllm.com/rails/))
- [Cost and Token Trackers](https://awesome-repositories.com/f/system-administration-monitoring/usage-monitoring/token-usage-analytics/cost-and-token-trackers.md) — Estimates financial costs of AI interactions by applying model-specific pricing registries to token usage. ([source](https://rubyllm.com/chat/))
- [Token Cost Calculators](https://awesome-repositories.com/f/system-administration-monitoring/usage-monitoring/token-usage-analytics/token-cost-calculators.md) — Computes financial usage expenses by applying model-specific pricing to normalized token counts. ([source](https://rubyllm.com/upgrading/))
- [Model Interaction Monitors](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/model-interaction-monitors.md) — Emits event metadata for model requests, completions, and images to monitor usage and provider performance. ([source](https://rubyllm.com/instrumentation/))

### User Interface & Experience

- [AI Response Adapters](https://awesome-repositories.com/f/user-interface-experience/browser-based-interfaces/backend-adapters/ai-response-adapters.md) — Uses adapters to standardize diverse AI model API responses into a consistent internal object format. ([source](https://rubyllm.com/overview/))

### Web Development

- [AI Workflow Pipelines](https://awesome-repositories.com/f/web-development/middleware-orchestration/ai-workflow-pipelines.md) — Coordinates multi-step AI task sequences using a pipeline of evaluators and optimizers to refine outputs.
- [AI Provider Routing](https://awesome-repositories.com/f/web-development/api-endpoint-configurations/service-endpoint-configurations/ai-provider-routing.md) — Implements dynamic routing of requests across different AI model providers and API keys on a per-chat basis. ([source](https://rubyllm.com/rails/))

### Graphics & Multimedia

- [AI Audio Analysis](https://awesome-repositories.com/f/graphics-multimedia/audio-music/audio-processing/ai-audio-analysis.md) — Provides capabilities to accept audio files or streams for transcription and voice interaction. ([source](https://rubyllm.com/available-models/))
- [Automated Media Analyzers](https://awesome-repositories.com/f/graphics-multimedia/media-processing-analysis/media-analysis/automated-media-analyzers.md) — Extracts insights and data from images and videos using integrated computer vision processing. ([source](https://rubyllm.com/))

### Networking & Communication

- [RPC Traffic Debugging](https://awesome-repositories.com/f/networking-communication/rpc-protocols/rpc-traffic-debugging.md) — Provides diagnostic logging of raw message exchanges to troubleshoot AI provider integrations. ([source](https://rubyllm.com/configuration/))

### Security & Cryptography

- [Content Moderation](https://awesome-repositories.com/f/security-cryptography/content-moderation.md) — Analyzes model inputs and outputs using moderation models to identify and block harmful content. ([source](https://rubyllm.com/moderation/))

### Software Engineering & Architecture

- [Fiber-Based Concurrent Execution](https://awesome-repositories.com/f/software-engineering-architecture/concurrent-task-execution/fiber-based-concurrent-execution.md) — Utilizes lightweight fibers to execute multiple tool calls and AI requests in parallel without blocking the main process.
- [Execution Telemetry Pipelines](https://awesome-repositories.com/f/software-engineering-architecture/event-driven-architectures/execution-telemetry-pipelines.md) — Implements telemetry pipelines that broadcast internal execution data and token usage for monitoring and OpenTelemetry tracing.
- [Concurrent AI Requesting](https://awesome-repositories.com/f/software-engineering-architecture/object-pooling/task-pools/concurrent-request-pools/concurrent-ai-requesting.md) — Dispatches multiple language model queries using non-blocking tasks to prevent application freezing. ([source](https://rubyllm.com/async/))