Terminal AI coding CLI. Speaks any OpenAI-compatible API (OpenRouter, OpenAI, NVIDIA, Ollama, LM Studio, DeepSeek). Modes, slash commands, multi-agent swarming, key-rotation pool, optional voice + screen-reader, sandbox + permission gates, persistent inpu
CLI for Jira Cloud issue management with setup, profiles, and compact agent output
better fetch for Node.js. Works on any JavaScript runtime!
Compact version of Jimp
The best of both `JSON.stringify(obj)` and `JSON.stringify(obj, null, indent)`.
An ACP-compatible coding agent powered by Codex
mdast utility to make a tree compact
A convertor between XML text and Javascript object / JSON text.
[](https://www.npmjs.com/package/@aws-sdk/middleware-user-agent) [](https://www.npmjs.c
ESLint’s official `compact` formatter, unofficially published as a standalone module
Fork of node-fetch-native with support for custom agents
Turn a function into an `http.Agent` instance
HTTP proxy tunneling agent. Formerly part of mikeal/request, now a standalone module.
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-browser) [](https://www.n
Agent-native CLI for AI mobile testing and app automation across iOS, Android, tvOS, Android TV, macOS, and Linux.
Maps proxy protocols to `http.Agent` implementations
An HTTP(s) proxy `http.Agent` implementation for HTTPS
Exposes node v8 garbage collection stats
Crazy fast http radix based router
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/
Get a user agent string across all JavaScript Runtime Environments
the http/https agent used by the npm cli
Global HTTP/HTTPS proxy configurable using environment variables.
HTTP Agent that keeps socket connections alive between keep-alive requests. Formerly part of mikeal/request, now a standalone module.
ConciseErrors replaces ActionDispatch::DebugExceptions with a compact error page that highlights the exception and a truncated backtrace, making Rails crashes easier for humans and AI helpers alike.
Ruby-native LLM agent framework with provider adapters (Anthropic, OpenAI, Google), tool calling, streaming, and session persistence.
Agentlog adds a second Rails logger that emits terse, token-efficient request summaries for coding agents while leaving development.log untouched.
Production-grade coding agent with tool execution, middleware pipeline, context compaction, session persistence, and multi-provider LLM support.
mini_readline: A compact, little gem for console command entry with line edit and history, inspired by the standard readline gem. Also included are four sample auto-complete agents and the irbm utility, which is irb + mini_readline and not an Intermediate Range Ballistic Missile.
Claw is an Agent framework built on ruby-mana. Adds interactive chat, persistent memory with compaction, knowledge base, and runtime state persistence.
ace-compressor provides exact, compact, and agent context compression with benchmark comparison, producing structured ContextPack/3 output for efficient LLM context loading.
Behavioral spec-based task management with compact IDs, subtask trees, AI-powered implementation plans, and automated health checks. Same CLI for developers and coding agents.
RubyPi is a minimal, composable AI agent harness for Ruby. Build production-ready LLM agents and AI agents with a unified provider interface across OpenAI, Anthropic Claude, and Google Gemini, plus first-class support for tool calling (function calling), streaming responses, automatic retries, provider fallback, context compaction, and a think-act-observe agent loop. Anti-framework design — small, idiomatic, and explicit. Ideal for building autonomous AI agents, ReAct agents, tool-using LLM agents, and chatbots in Ruby.
RSpec formatter optimized for AI agents and CI systems. Outputs compact NDJSON with file references instead of verbose text. Supports log splitting, error deduplication, and context-efficient reporting.
Pocketrb is a Ruby AI agent framework featuring async message bus architecture, multi-LLM support (Claude, OpenRouter, RubyLLM), multi-channel messaging (CLI, Telegram, WhatsApp), planning system, context compaction, and simple JSON-based memory with keyword matching.
No description provided.
No description provided.
No description provided.