MoltNet agent runtime — coding-agent-agnostic Task execution loop

Portable AI agent execution loop — brain-agnostic, zero embedded databases

Slate agent runtime: execution loop, tool protocol, edit engine and Node host.

The agentic runtime: LLM provider abstraction, tool-calling, execution loop, permissions, memory, budgets, audit.

MCP (Model Context Protocol) tool-calling for Aimatey - translate MCP tools into the IR tool-execution loop via an injectable client

Tempo plugin that provides a high-performance continuous execution loop (Ticker) based on temporal mathematics.

The core agent loop for AgentLayer. Wraps Vercel AI SDK's `streamText` in a resumable, approval-aware tool-execution loop, and defines the interfaces that platform packages (`agentlayer-filesystem`, `agentlayer-justbash`) implement. Ships isomorphic tools

Unified AI Development Framework - BMAD phases with Ralph execution loop

Autonomous parallel execution loop for Claude Code — feed it a dependency-annotated roadmap and it builds every eligible phase concurrently, each in its own git worktree, merging green work and parking red.

Autonomous PLAN.md execution loop for Pi that continues until all checklist items are complete.

KineticLiquid SDK — Solana-native liquidity execution & loop engine client library

Unified execution loop, precision clock, and pipeline orchestrator for Flux Engine

Minimal client-side execution loop for Adaptive MCP.

Automated task execution loop using Claude Code or OpenCode with TUI dashboard

fast, tiny `queueMicrotask` shim for modern engines

Unattended iterative Claude Code execution loop

Lock on asynchronous code

LangGraph

High-priority task queue for Node.js and browsers

Useful TypeScript utilities.