Thinking-loop guard for dsh: observes the llm/stream waterfall and breaks a model that degrades into a loop. Detects three per-call shapes (reasoning-only calls, restated-material calls, self-repeating low-entropy reasoning) and re-fires instead of latchi

A TypeScript CodeAgent harness reconstructed from Arena message and tool traces.

A shim for the setImmediate efficient script yielding API

an agent that goes straight to the goal

Dotted thought-orb loading indicators for AI & agent UIs — nine tuned states, two sizes, auto dark/light

MCP server for sequential thinking and problem solving

A CLI application implementing the fauxberry thinking loop for Anthropic's Claude family of models

Unified LLM API with automatic model discovery and provider configuration

Pi extension: detects and interrupts infinite thinking-block and tool-call loops in real time before they exhaust your context window.

High-priority task queue for Node.js and browsers

JavaScript Performance Monitor

The **[Alibaba provider](https://ai-sdk.dev/providers/ai-sdk-providers/alibaba)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model, embedding model, and video model support for [Alibaba Cloud Model Studio](https://modelstudio.console.alib

High-priority task queue for Node.js and browsers

A repetition-loop guard for the Pi coding agent: detects thinking-runaway / 万字复读 (the model repeating the same text in a loop) in streamed output via message_update, then aborts and re-steers the model with a corrective steer message

Tiny helper to prevent blocking Node.js event loop

The concrete agent loop plugin for the DeepSeek Harness

fast, tiny `queueMicrotask` shim for modern engines

Exposes stats about the libuv default loop

Run a list of functions in order in a given object context. The functions can be callback-taking or promise-returning.

C function to get the current libuv event loop for N-API