Structured or plain-text LLM output through a configurable provider fallback chain: free tiers first, paid floor last, with pluggable cooldown storage and unified reasoning effort.

Framework-free registry of LLM reasoning-effort capabilities, per-vendor wire params, and context limits (Anthropic / OpenAI / Google + proxy routes).

n8n community node: xAI Grok Chat Model with the reasoning_effort parameter (none/low/medium/high). A faithful clone of n8n's built-in xAI Grok node, plus a Reasoning Effort control. Connect this as the Chat Model sub-node to your AI Agent.

Pi tool that delegates a self-contained sub-task to OpenAI's Codex CLI via `codex exec --json`. Streams structured events as partial output, returns the final agent message. Configurable default model + reasoning effort, with multi-turn session continuity

Claude Code status line showing model, reasoning effort, context usage bar, and session cost (with optional caveman badge).

This is an n8n community node that provides access to OpenAI's GPT-5 models and advanced features through the Responses API. It supports PDF processing, multiple file inputs, and all the latest GPT-5 capabilities including reasoning effort control, verbos

Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence

[](https://www.npmjs.com/package/@agentclientprotocol/codex-acp)

Parse incomplete json text in best-effort manner

Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company

Graphlit API Client for TypeScript

`@helloxiaohu/plugin-openai-compatible-gpt` bridges the [XpertAI](https://github.com/xpert-ai/xpert) agent platform with model providers that expose an OpenAI-compatible REST API and GPT-style reasoning effort control.

OpenCode plugin for AWS Kiro (CodeWhisperer) providing access to Claude models

Paperclip adapters for Hermes Agent local CLI and Hermes Gateway HTTP/SSE runs

Open-source replica of Work Louder's Codex Micro using a consumer gamepad as the physical AI-agent controller.

Pi extension for controlling thinking effort with model-adaptive min/max aliases

A coding agent in your terminal. Type what you want. It does the rest.

Grammar parsing support for cspell

SOTA NPM module for agentic processes using local or cloud LLMs.

n8n ChatModel node with extended reasoning/thinking support for OpenRouter, DeepSeek, and any OpenAI-compatible API