基于规范的AI编码代理开发流程:架构优先规划、任务分解、GitHub问题/公关跟踪、深度讨论,以及针对Claude Code、Codex、Cursor及其他支持Markdown的代理的自适应控制。
task-decomposition 开源项目推荐(50 个)
task-decomposition 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 50 个仓库Multi-agent engineering framework: evidence packs, runtime validation, task decomposition, cross-window worker execution, and CI artifact verification for Codex.
Loom is an AI harness, that can be used with local or cloud LLMs, for complex tasks. It decomposes work, drives execution through a verification harness, and keeps models on track with structured state instead of history. It can route between thinking and acting models, verifies outputs, and exposes an APP/TUI/API/CLI/MCP for both humans & agents.
An automated coding agent for small, cheap LLMs: split big goals into contract-driven task trees, execute each leaf in an isolated context, and verify with real builds and tests.
The issue tracker that lives in your repo. Built for AI agents. Works for humans.
基于 DeepSeek 大语言模型的 AI 编程助手 Agent —— 自然语言驱动的终端编码助手。支持自动读写文件、代码搜索、命令执行、Git 管理,复杂任务智能拆解与多 Agent 并行执行。
Use repository evidence to turn requirements into a small set of independently verifiable tasks, then register them in Linear.
Agentic AI refers to AI systems capable of autonomous decision-making, planning, and executing tasks based on goals—acting like intelligent agents. These systems combine LLMs with tools, memory, and feedback loops to complete complex workflows with minimal human input.
Multi-Agent AI legal assistant for solo lawyers practicing Chinese law. Model-agnostic, plug-and-play. 为执业中国法律的独立律师打造的多 Agent AI 助手 — 模型无关、即插即用。
AI Research Agent that plans research, calls tools, decomposes complex questions into subtasks, evaluates source reliability, and generates structured evidence-based reports. Week 5 of a 90-day AI Engineering roadmap.
Instantly decompose Azure DevOps work items into hierarchical trees and streamline agile planning in a single action! 🚀
Make any LLM 10x smarter. Recursive DAG decomposition + temporal knowledge graph = free models that match expensive ones. 30/30 tasks passing at $0.0006 total cost.
Krako 2.0 – Energy-efficient, triadic multi-tier inference infrastructure enabling adaptive routing across heterogeneous edge–cloud nodes.
Cursor skills and harness-oriented workflows for project intake, problem framing, and AI-ready task decomposition.
Description: A structured engineering workflow skill for complex AI-assisted coding, coursework, data analysis, and research projects.
AI-Driven Project Decomposition and Implementation
WBS 任务拆解工具:支持上传 PDF、DOCX、TXT 需求文档,自动生成工作分解结构和任务清单,并提供 Windows/macOS 桌面安装包。
Intelligent travel planning with multi-agent AI orchestration using n8n
Autonomous coding agent harness built on Claude Code SDK — implements Anthropic's long-running agent pattern: scan → plan → code → validate → git-commit in a loop. Turn requirements into working code with one command.
Skill-based Reasoning Intelligence — AI orchestration beyond the complexity ceiling
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/task-decomposition。
- 该话题在 GitHub 上共有 50 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1314 Star,覆盖 10 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。