Intelligent context management for Claude Code development
[](https://www.npmjs.com/package/@google/genai) [](https://www.npmjs.com/package/@google/genai)
Global AI context manager — store your personal context and inject it into any AI tool.
Base context manager used to implement context managers for loglayer.
The **Model Context Protocol (MCP) client** for the [AI SDK](https://ai-sdk.dev/docs) lets you connect to MCP servers and use their tools with AI SDK functions like `generateText` and `streamText`.
OpenTelemetry AsyncLocalStorage-based Context Manager
OpenTelemetry Base Context Manager
OpenTelemetry Tracing
Complete AI context management solution — event tracking, snapshot generation, and seamless context handoff between AI tools. Works as both CLI and library.
AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.
TypeScript scope analyser for ESLint
The tRPC server library
Vertex Generative AI client for Node.js
Unified LLM API with automatic model discovery and provider configuration
Zep: Fast, scalable building blocks for production LLM apps
A collection of essential TypeScript types
Session management for TMCP (TypeScript Model Context Protocol) transport implementations. This package provides the base classes and in-memory implementations for both streaming session coordination and session metadata persistence.
Simple AI Context for Better Code Generation - Persistent context system for AI coding assistants
🎯 Stop wrestling with AI. Start building with purpose. The artisan's toolkit for agent workflows, Codex skills, and original Takomi capabilities like 21st.dev integration.
<h1 align="center">Backlog.md</h1> <p align="center">Markdown‑native Task Manager & Kanban visualizer for any Git repository</p>
CLI tools for AI agents
Package manager detector
A tiny (118 bytes), secure URL-friendly unique string ID generator
OpenTelemetry Context Zone with peer dependency for zone.js
KairosChain is a Model Context Protocol (MCP) server for self-managed, evolvable AI skill definitions. It combines Pure Skills design (Ruby DSL/AST) with a private blockchain, enabling AI agents to define, evolve, and audit their own capabilities through self-referential skill management. Supports stdio and Streamable HTTP transport.
AppyDave Tools is a consolidated productivity toolkit for YouTube content creation workflow. Includes single-purpose utilities for AI context gathering, subtitle processing, YouTube management, and more. All tools in one codebase for easier maintenance, each operates independently.
`agent99` is a Ruby gem designed to facilitate the creation and management of smart agents, providing a straightforward interface for tasks such as natural language processing, context handling, and conversing with various AI models. It allows developers to smoothly integrate and utilize AI capabilities within Ruby applications while ensuring flexibility and ease of customization.
SolidAgent extends ActiveAgent with database-backed prompt context management, declarative tool schemas, and real-time streaming updates. Provides has_context, has_tools, and streams_tool_updates concerns for building robust AI agents.
FerrumMCP is a browser automation server that implements the Model Context Protocol (MCP), enabling AI assistants to interact with web pages through a standardized interface. Features include navigation, form interaction, content extraction, screenshot capture, JavaScript execution, cookie management, and advanced capabilities like smart cookie banner detection and AI-powered CAPTCHA solving.
An MCP (Model Context Protocol) server that provides browser automation tools for AI agents using Ferrum and headless Chrome. Features 25 tools covering navigation, screenshots, form interaction, JavaScript evaluation, cookies, file downloads, and multi-session management.
A comprehensive Ruby gem for text translation, summarization, and multilingual content management using Mistral AI API. Features include context-aware translation, glossaries, batch processing, Rails integration with Mobility/Globalize support, monitoring, and advanced helpers for complex translation workflows.
RCrewAI is a powerful Ruby framework for creating autonomous AI agent crews that collaborate to solve complex tasks. Build intelligent workflows with reasoning agents, tool usage, memory systems, and human oversight. Key Features: • Multi-Agent Orchestration: Create crews of specialized AI agents that work together • Multi-LLM Support: OpenAI GPT-4, Anthropic Claude, Google Gemini, Azure OpenAI, Ollama • Rich Tool Ecosystem: Web search, file operations, SQL databases, email, code execution, PDF processing • Agent Memory: Short-term and long-term memory for learning from past executions • Human-in-the-Loop: Interactive approval workflows and collaborative decision making • Advanced Task Management: Dependencies, retries, async execution, and context sharing • Hierarchical Teams: Manager agents that coordinate and delegate to specialist agents • Production Ready: Security controls, error handling, comprehensive logging, and monitoring • Ruby-First Design: Built specifically for Ruby developers with idiomatic patterns • CLI Tools: Command-line interface for creating and managing AI crews
Rubagent is a lightweight Ruby framework for building modular, composable AI agents that can interact with LLMs (like OpenAI), tools, and external APIs. It provides a flexible architecture for defining agents, managing prompts, and orchestrating multi-step workflows using functional patterns. Features: - Streamed LLM responses (OpenAI, etc.) - Plug-and-play agent design - Shared context and memory flow - Support for custom tools and HTTP integrations - Built-in dry-rb and Zeitwerk compatibility
A powerful command-line tool that generates Anki flashcard decks (.apkg) from YAML files, direct prompts, or file attachments. Features AI-powered content generation using OpenRouter API with support for multiple models (GPT, Claude, Llama), file and directory attachment processing for context-aware generation, prompt file support, intelligent content filtering, and flexible deck management with sync capabilities.