Loop engineering framework for building durable, long-running agentic loops — browser, AI, or both

Simple agentic loops: run a markdown checklist one item at a time with a fresh agent session for each

Control subagents, agentic loops, and execution graphs from one local command center.

Install and run agentic loops — recurring AI agents defined in a single LOOP.md file. One file defines it; any harness can run it.

Infrastructure for autonomous agent economies — identity, reputation, payments, governance, discovery, coordination, and audit on Celo and Stellar. Also works fully off-chain with persistent memory, agentic loops, and tool-use.

A lightweight library for running agentic loops with LLMs and tool calling

Search 41,000+ agent skills, MCP servers, Claude Code plugins, and agentic loops from your terminal. The CLI for getagentictools.com.

A linter and governance layer for AI agent loops. Catches runaway, unverified, or unsupervised agentic loops before they cost you.

Qwen as a function — call Qwen CLI programmatically with types, composition, and agentic loops

Small, performant & immutable iteration utilities for Arrays and Objects

A runtime for self-improving agentic loops: dispatches coding agents against tracked tickets, verifies with CI, and merges through review.

Cloud and zero-trust agentic workflow marketplace for skills, agents, rules, MCP references, and compliance-aware architecture.

Playwright Tools for MCP

This is the official JavaScript SDK for [Loops](https://loops.so), with full TypeScript support.

Infrastructure for autonomous agent economies — identity, reputation, payments, governance, discovery, coordination, and audit on Celo and Stellar. Also works fully off-chain with persistent memory, agentic loops, and tool-use.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Pure business logic, types, schemas, and store interfaces for the Polpo AI agent orchestration platform

Kimi as a function — call Kimi CLI programmatically with types, composition, and agentic loops

Server & Client SDK for Agent2Agent protocol

Reusable project context and specialist workflows for the AI tools you already use. AIWG places agents, skills, commands, and rules in provider-readable locations, with optional utilities for artifact memory, workflow orchestration, recovery, and discover