GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
Loop EngineeringLoop Engineering is the practice of designing recurring systems for AI agents and coding agents. Instead of prompting an agent turn by turn, you build a loop that discovers work, delegates it to one or more agents, verifies the result against tests or other deterministic gates, persists state outside the model, decides what happens next, and runs again on a cadence, an event, or until a verifiable goal is reached. It sits above prompt, context, and harness engineering: those improve a single run, while loop engineering governs repeated agent work over time, including budgets, retries, escalation to humans, and stopping conditions. Here are 516 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
agent skills mcp personal-assistant task-management super-agent agent-collaboration agent-harness proactive-agent loop-engineering
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
agent skills mcp chatbot self-hosted webui ai-agents super-agent ai-agent llms llm-tools agentscope personal-ai-assistant agent-harness harness-engineering loop-engineering
Personal memory across agents
skills memory mcp sandbox harness agent-memory claude-skills openclaw openclaw-skills loop-engineering
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
automation mcp devtools grok codex ai-agents claude github-actions devops-automation llm prompt-engineering anthropic coding-agents agentic-ai ai-coding claude-code loop-engineering
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
cli skills skill mcp opencode developer-tools dsh codex ai-agent llm-evaluation deepseek llm-orchestration agentic-ai claude-code ai-coding-agent coding-agent agent-os loop-engineering dsh-plugin
Comet: agent skill harness for turning ideas into evaluated workflows
Surge-style whole-home gateway and control plane for macOS with IPv4/IPv6 support— mihomo TUN, dnsmasq-powered DHCP/DNS, per-device routing, and an agent-friendly validation workspace.
macos dns tun dhcp proxy gateway dnsmasq surge home-network transparent-proxy macos-app policy-routing mihomo harness-engineering bypass-router loop-engineering
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.
skill cursor codex claude-code qoder harness-engineering agent-plugin harness-design loop-engineering
Multi-agent graph orchestration engine for building your own software factory. Bring your own QA workflow, and the engine enforces it.
qa multi-agent developer-tools code-review code-quality codex software-factory ai-agents claude github-copilot ai-code-review coding-agents agentic-workflow agent-orchestration claude-code agent-harness harness-engineering meta-harness agent-loops loop-engineering
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
agent cli gui loop harness codex cua claude long-horizon claude-code codex-desktop claude-plugin codex-plugin long-horizon-agents loop-engineering deepseek-harness longhorizon-harness
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
opencode cursor codex autonomous-agents ai-agents agent-learning claude-code agent-experience openclaw agent-traces loop-engineering agent-apprenticeship
The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.
skills design-patterns nvidia cursor refactor grok codex ai-agents single-source-of-truth fact-check long-context evals recursive-self-improvement coding-agents agent-skills claude-code context-engineering anti-slop harness-engineering loop-engineering
Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
productivity cursor obsidian knowledge-management worker-agents ai-agents closed-loop second-brain agentic self-evolving agent-skills claude-code agent-plugins agent-loop garry-tan gstack gbrain people-crm loop-engineering verification-harness
天枢harness是一个的终端编程智能体，它要回答的核心问题是：模型何以稳定地交付——目标不漂移、完成有证据、验证有闭环，不说"应该修好了"。为此它在模型与真实世界之间建立一层认知执行环境（CVM），把目标、状态、证据、资源、权限与终止条件从对话历史中外部化，由运行时持续管理。同时对deepseek v4极度优化。
cli gui tui harness super-agent ai-agent deepseek context-management coding-agent personal-ai-assistant agent-harness harness-engineering loop-engineering tianshu-harness tianshu
Codebase harness + loop engineer
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
agent automation framework multi-agent evolutionary-algorithms self-improvement llm-agent agentic rsi-ai auto-optimization agent-evolution loop-engineering
🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.
agent spring-boot skills multi-agent multiagent telegrambot dingtalk-robot ai-agent feishu-bot plan-and-execute spring-ai spring-ai-openai tool-calling mcp-protocol agent-harness openclaw llm-wiki loop-engineering agentscope-java
别再问我什么是 Loop Engineering — 橙皮书系列。A plain-language guide to loop engineering (中文 + English PDF). Free.
OpenLoomi is an open-source AI coworker. It connects your work tools, understands what you’re working on, and tells you what needs your attention, why it matters, and what to do next. It’s your open-source Attention Agent.
slack agent security ai telegram graph skills memory mcp gmail message whatsapp claw llm llm-model context-engineering promt-engineering harness-engineering loop-engineering attention-agent
Private control plane for AI agents
workflow automation mobile-app self-hosted openai personal-assistant control-plane agents codex ai-agents friday local-first ai-assistant byok agent-orchestration approval-first loop-engineering
Related topicsagentic-ai ai-agents automation llm prompt-engineering |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |