Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants.
-
Updated
Nov 18, 2026 - Go
Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants.
dsh-agent-team: Agent Teams for DeepSeek Harness. Hand work to a team of agents that carries it end to end while you set the direction and hold the gates. You stay on the loop, and step back in whenever you want.
AI-native organization: can 5 humans cover what once required 50? Ingora’s bilingual capability experiment—not a measured productivity claim. AI 原生组织双语实验。
Stop babysitting your agents. A workflow builder like n8n, where a step can be an agent and a choice a decision model. Night Shift runs it on your own machines, for any kind of work, and asks you only what needs you.
AI cockpit is a human control interface to AI systems. It is supposed to cover requirements from EU's AI act.
SuperDomestique (formerly faff): governed software delivery for increasingly independent AI agents.
사람이 얼마나 개입해야 하는지 짚어주는 AI 자동화 컨설턴트 Skill · An AI-automation consultant Skill for Claude Code & OpenAI Codex that tells you how much a human should stay in the loop.
Compilation of my research data
A Multi-agent RAG chatbot built with LangChain, LangGraph, and NVIDIA NIM, featuring router-based orchestration, LLM-as-a-judge evaluation, and human oversight for safe and grounded responses.
HumanAbsent: your local AI coding agents work while you're away; delegate from Telegram, approve risky writes, and return to a Morning/Audit handoff.
Human-on-the-loop mission control for simulated drones: GNSS-degradation detection, per-vehicle navigation trust, and recommendations that wait for operator approval. Simulation only.
Human-on-the-loop (HOTL) charter for AI agents, packaged as an Agent Skill: scored decisions, a Level 5 chief of staff, a settings cascade for preferences, and an optional local recall layer. Provider-agnostic, AGENTS.md-first.
Sparse Agent Foundry: AI creates and reviews reusable capabilities; humans govern goals and risk.
Run a team of AI coding agents on GitHub with a human on the loop, not in it.
To associate your repository with the human-on-the-loop topic, visit your repo's landing page and select "manage topics."