Skip to content

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.

docs(readme): describe supervision as human on the loop (#1094)

cocofhua6644534e448
diff --git a/.github/repository-metadata.json b/.github/repository-metadata.json
index c0e260c2..7e978339 100644
--- a/.github/repository-metadata.json
+++ b/.github/repository-metadata.json
@@ -7,7 +7,7 @@
"sop",
"workflow-automation",
"software-engineering",
- "human-in-the-loop",
+ "human-on-the-loop",
"self-hosted",
"codex",
"claude-code",
diff --git a/README.md b/README.md
index f7d058b4..fcdd9f9d 100644
--- a/README.md
+++ b/README.md
@@ -64,7 +64,7 @@ Ask a coding agent to "fix this bug" and the result depends on that run. It migh
- **Repeatable.** Same SOP, same stages, same checks for every requirement. Start from built-in backend, frontend, bug-fix and product SOPs.
- **Separated roles.** Planning, implementation, review and testing each get their own prompt, executor, model, rules, Skills and MCP tools. A role works as an SOP node or as a subagent in chat.
-- **Human in the loop.** Approval gates where they matter. Read the report, approve, or send the work back to a chosen step.
+- **Human on the loop.** Agents run on their own while you supervise. Pause, steer or take over anytime, and approval gates stop the run where a human must decide: approve, or send the work back to a chosen step.
- **Observable and resumable.** Node status, tool traces, logs and artifacts in one place. Pause, retry a failed step, or rerun from any node.
- **Your stack, your servers.** Ten coding-agent CLIs as executors, from CodeBuddy, Codex and Claude Code to OpenCode, Cursor CLI and more. GitHub, Skills and MCP as tools. Docker sandboxes or your own machine as the runtime.
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 528856dc..06c049f9 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -64,7 +64,7 @@ https://github.com/user-attachments/assets/10b8ae2e-d7e7-4b78-8876-c45818d4a08f
- **可重复。** 同一条 SOP、同样的阶段、同样的检查,每个需求都一样。内置后端、前端、缺陷修复、产品方案四类 SOP 可直接起步。
- **角色分离。** 方案、实现、评审、测试各有独立的角色提示词、执行器、模型、规则、Skills 和 MCP 工具;同一个角色既能做 SOP 节点,也能在对话中作为子 Agent 调用。
-- **人在回路。** 在关键节点设置人工审批:看完报告再放行,或打回到指定环节返工。
+- **人在回路之上。** Agent 自主运行,你负责监督:随时暂停、引导或接管;需要人拍板的地方由人工关口拦下,看完报告再放行,或打回到指定环节返工。
- **可观测、可续跑。** 节点状态、工具轨迹、日志和产物集中呈现;支持暂停、重试失败步骤、从任意节点重跑。
- **技术栈和服务器都是你的。** 执行器支持 10 种编程 Agent CLI,从 CodeBuddy、Codex、Claude Code 到 OpenCode、Cursor CLI 等;工具接入 GitHub、Skills、MCP;运行环境可选 Docker 沙箱或你自己的机器。