pcliangx/AppGenesisForge — Production-ready AI Agent Team template for Claude Code — 14 specialists, Agile+Scrum+TDD enforced v…

Description and use

**Brief Summary (2‑3 sentences)**
AppGenesisForge is a production‑ready, open‑source template that lets you build and deploy AI‑agent teams for Claude Code, complete with 14 pre‑defined specialist agents, Agile/Scrum/TDD enforcement, and a six‑stage PRD‑to‑UAT pipeline. It supports multi‑LLM back‑ends (DeepSeek, Doubao, Qwen, MiniMax), offers a WeChat Mini Program front‑end, and provides trilingual documentation (Chinese, English, Japanese), enabling you to ship a new feature in a single night.

**Value**

• **From ad‑hoc prompts to repeatable workflows:** The framework turns isolated prompts and tools into structured, version‑controlled agent pipelines, reducing the engineering overhead of stitching together LLM calls.
• **Built‑in governance:** Skill/hook/Definition‑of‑Done layers, Agile/Scrum ceremonies, and TDD scaffolding enforce quality and traceability without additional process tooling.
• **Multi‑LLM flexibility:** Swappable back‑ends let you pick the most cost‑effective or capable model per task, while the 4‑layer hook defense safeguards against prompt injection and misuse.
• **Rapid delivery:** The “feature overnight” promise comes from pre‑wired CI/CD gates, ready‑made WeChat Mini Program UI, and a CLI/SDK that abstracts deployment details.

**Practical Adoption Path**

1. **Evaluation:** Clone the repo, run the provided Docker/CLI starter, and experiment with the sample “Hello‑World” agent to verify integration with your LLM provider.
2. **Customization:** Replace or extend the 14 specialist agents with domain‑specific skills, adjust the hook/DoD definitions, and configure the multi‑LLM routing table.
3. **Pipeline Integration:** Hook the generated API/SDK into your existing backend or CI system; the six‑stage gate (PRD → Design → Implementation → Review → UAT → Release) maps directly to typical Jira/GitHub Actions workflows.
4. **Deployment:** Use the built‑in WeChat Mini Program or expose the agent services via the provided FastAPI gateway; the framework handles state persistence and agent memory out‑of‑the‑box.
5. **Scale & Iterate:** Leverage the multi‑LLM support to balance cost vs. performance, and add new hooks or test suites as the product matures.

**Production Readiness**

• **Activity & Adoption:** 239 stars, recent commits (as of 2026‑06‑23), and a growing community indicate active maintenance.
• **Architecture:** Python core, clear API/SDK boundaries, and a layered hook defense make the codebase auditable and extensible.
• **Process Rigor:** Enforced Agile/Scrum, TDD, and a formal DoD reduce regression risk and align with enterprise QA standards.
• **Multi‑LLM & Security:** Supports several LLM vendors and includes defensive hooks, mitigating model‑specific vulnerabilities.
• **Remaining Checks:** Final due diligence on licensing (MIT/Apache?), security scanning, and maintainer responsiveness is recommended, but the project is mature enough for a serious pilot in production environments.

Problem

pcliangx/AppGenesisForge helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

Production-ready AI Agent Team template for Claude Code — 14 specialists, Agile+Scrum+TDD enforced via skill/hook/DoD 3-layer (not wiki), PRD→UAT 6 stage gates, 4-layer hook defense, multi-LLM (DeepSeek/Doubao/Qwen/MiniMax), WeChat Mini Program, trilingual README (中文/EN/日本語). Ship a feature overnight.

Source