autonomous-agent-harness

仓库创建 2026年4月15日最近提交 20 天前SkillHot 收录 20 天前

▸ 精选理由

为无人工审查的长期自治运行提供关键运行时和恢复机制。

▸ 风险提示

自治运行可能导致无限循环或非预期外部请求，需限制权限

这个 Skill 做什么

提供任务队列、调度和持久化记忆以运行自治多代理循环。

为自治多代理循环提供任务队列、调度器和持久化记忆，跟踪任务状态并在失败时重试、记录决策。适合在 Orchestrator 无需人工把关、基于 PRD 自动运行的并行路径使用，让多个代理能有序协作。特别之处是把调度、重试和长期决策保存下来，支持跨会话的持续执行与审计。

▸ 展开 SKILL.md 英文原文

Provide a task queue, scheduler, and persistent memory system for autonomous multi-agent loops. Track task state, monitor agent progress, retry on failure, and persist decisions across sessions. Use this in the Orchestrator parallel path when running an autonomous PRD-driven loop without human gates.

自动化集成任务队列调度持久化故障恢复通用

Stars

Forks

仓库内 Skill

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/Codebrew-company/CodebrewRouter/master/.claude/skills/autonomous-agent-harness/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/Codebrew-company/CodebrewRouter/master/.claude/skills/autonomous-agent-harness/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# Autonomous Agent Harness â€” task queue + scheduler + memory

A runtime framework for fully autonomous agent workflows (no human gates). Manages task queues, agent scheduling, persistent decision logs, and failure recovery.

## When to use

- **Parallel path:** Orchestrator is running autonomously against a PRD (no human `/agent squad` gate).
- You need **task queue management** (prioritize, retry, skip on failure).
- Agent decisions must **persist across sessions** (in case of restart/recovery).
- You want **monitoring dashboards** (task status, agent health, completion %).

## Components

### 1. Task queue

Initial state (from PRD):

```
Queue:
  [pending] Task 1: Implement Provider X (a

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有