Personal memory for agents - fast memory retrieval, self-evolving skills, and lower cost.

Hands-on tutorials for building AI agents from scratch. Learn LLM APIs, prompt engineering, tool calling, and the agent loop through practical examples.

Loop engineering for long-running AI agents.

A configurable runtime for creating governed agentic loops to reliably enable autonomous execution of complex multi-step workflows.

论文解析 Agent 系统（Agent Harness + Loop Engineering），实现结构化抽取与闭环验证优化。

Contract-based multi-agent skill framework for Claude Code & Codex — compile YAML runbooks into SKILL.md with loop, parallel, and checkpoint support.

LoopCraft runtime harness plugin for Hermes with evidence-first execution, verification-first workflows, and self-correcting AI agent behavior. Installs as proofrail for compatibility.

Build Your One-Person Company with SoloEngine. Create your own OpenClaw, Cursor, Claude Code, or other Agentic AI that are exclusively yours—by simply dragging and dropping

Loop Engineering: a curated field guide to designing recurring AI agent and coding-agent loops — patterns, loop contracts, runnable examples, and resources above prompt, context, and harness engineering.

AI Software Runtime（ASR）是一套面向 AI 编程任务的自治式软件工程运行时。 其核心目标不是让 AI 更会写代码，而是让 AI 生成的软件能够稳定收敛。

A small, runnable reference implementation that accompanies Loop Engineering: A Practitioner's Guide. Each module maps to a chapter so you can read the book and the source side by side.

The sharpest loop engineering out there in the flagship pack. Plus a catalogue system with additional packs of subagents, skills, and hooks. Install per repo or per user. It's npm for your coding agent. The force multiplier behind the 100x engineer. Works with Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.

Design, validate, dry-run and audit safe Hermes Agent loop contracts before automation

Project-local agent harness skill for traceable AI workflows

Open-source loop engineering for auditable business briefings: claims, evidence, gates, findings, repairs, and human review.

Local-first, loop-native AI agent runtime: build a team of LLM agents that run your work, verify themselves, and compound into skills that are yours — while you stay the one who decides. Multi-agent orchestration, human-in-the-loop (H2A), MCP, sandboxed execution.

Quality-gated autonomous mission completion loop for Claude Code and Codex (plan, execute, review, score, iterate).

A git-native civilization loop — laws are Issues, votes are reactions, AI agents propose & narrate, the world ticks every 1h. Loop Engineering in action.

The harness your agents grow in.

Make your AI 10^79× stronger with AI workflow gates, evidence-backed TaskRuns, SOPs, and known-bug rules.