Skip to content

docs: full alignment of README.md and README.zh-CN.md #170

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Wool-xing merged 1 commit into from
Jun 1, 2026
Merged

docs: full alignment of README.md and README.zh-CN.md #170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
127 changes: 42 additions & 85 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,21 @@

---

Test-Agent turns any software, EXE, APK, Docker image, or API into a **fully tested project** — autonomous from requirement parsing to PoC-validated bug reports, powered by 16 AI agents.

- **All-platform** — Web · API · Android · iOS · WeChat Mini Program · Windows · macOS · Linux · Automotive · IoT · AI/LLM · Blockchain
- **All-protocol** — HTTP(S) · gRPC · WebSocket · TCP/UDP · GraphQL · MQTT · CAN-bus · Kafka · Modbus · …
- **Multi-LLM no lock-in** — 6 built-in (Claude / OpenAI / Gemini / Qwen / DeepSeek / Ollama) + OpenAI-compatible fallback for any provider, 3 env vars, zero code
- **Learn while using** — `--mode learn` outputs theory references at every step (22 KB cards across 13 domains)
- **Safe-by-default** — sandboxed exec · PII scrub · prompt-injection scan · decisions audit trail

---

## 🚀 Quick Start

> Prerequisite: Python 3.x. Git & Node.js auto-installed if missing (winget / brew / apt / apk).
>
> ⚠️ This project includes offensive security tools (pentest skill / SSRF probes / AI adversarial templates). Read [SECURITY.md](SECURITY.md) authorization requirements before running pentest or AI-adversarial workflows.
> ⚠️ This project includes offensive security tools (pentest skill / SSRF probes / AI adversarial templates). Read [SECURITY.md](SECURITY.md) before running pentest or AI-adversarial workflows.

```bash
# Download install script
Expand All @@ -34,123 +44,70 @@ python install.py ~/test-agent-project # macOS / Linux example, any folder
> python install.py D:\Test-Agent # example, any drive or folder works
> ```

**Expected duration**: ~10–15 min (includes pip install + Playwright chromium download). CN networks auto-detect and use Tsinghua PyPI mirror.
**Expected duration**: ~10–15 min (includes pip deps + Playwright browser). CN networks auto-use Tsinghua PyPI mirror.

After deployment, outputs under `workspace/`: test cases (Excel + xmind + markmap + opml) + Word report + decision logs.

**Next**: edit `.env` → `claude /login` → `cd project-dir && claude` → inside Claude: `/smoke-test`

---

## What is Test-Agent?

Test-Agent turns any software, EXE, APK, Docker image, or API into a **fully tested project** — autonomous from requirement parsing to PoC-validated bug reports. Built for QA teams, security researchers, automotive testers, and anyone who wants to **use AI testing while learning the theory behind it**.
**Next**: edit `.env` → `claude /login` → `cd project-dir && claude` → `/smoke-test`

- **16 expert agents** (11 production + 5 script — V1.x rollout 收尾,见 [ROADMAP.md](ROADMAP.md)) — functional · security · mobile · desktop · AI model · automotive · pentest …
- **30 active skills** (23 production + 7 script) **+ 2 vision-only** (reference, not executable) **+ 3 meta-skills** — TDD · E2E · regression · pentest · car-CAN-bus · eval-harness · …
- **78 production utils** — pytest · Playwright · JMeter · Appium · Burp · Allure · OpenCV · …
- **Multi-LLM (any provider, plug-and-play)** — 6 built-in (Claude / OpenAI / Gemini / Qwen / DeepSeek / Ollama) + **OpenAI-compatible fallback channel** for any other provider (Zhipu / Doubao / Kimi / Baichuan / Xunfei / …) via 3 env vars, zero code change. Cookbook: [`config/llm-providers.md`](config/llm-providers.md)
- **BugTracker** — 1 active adapter (Zentao); 5 planned (Jira · GitHub · GitLab · Linear · Webhook, see roadmap)
- **6 notify channels** — WeChat Work · Lark/Feishu · DingTalk · Slack · Email · MS Teams
- **MCP integration** — 6 server modules implemented (test-orchestrator active by default; 5 others ready to enable in `.mcp.json`)
- **Self-test scaffolding** — L1 lint + L2 mock CI active in CI; L3 real-LLM + L4 weekly cron require `ANTHROPIC_API_KEY` secret (not configured in this repo by default)

## 🖥 Desktop App (Windows + macOS)
## 🖥 Desktop App

[![Download](https://img.shields.io/badge/Download-Latest%20Release-blue)](https://github.com/Wool-xing/Test-Agent/releases)

No Python/Node/Docker required. Download the installer for your platform and start testing immediately.

## 🎯 5 Key Capabilities

1. **All-platform** — Web / API / Android / iOS / WeChat-miniprogram / Windows EXE / macOS / Linux / Electron / game / IoT / audio-video / AI/LLM / blockchain / 车载
2. **All-protocol** — HTTP(S) / gRPC / WebSocket / TCP / UDP / GraphQL / SOAP / MQTT / SSH / serial / Kafka / RabbitMQ / Modbus / CAN-bus / SOME-IP / DoIP / UDS
3. **Multi-LLM no lock-in (any provider)** — 6 built-in providers via `tagent config use <name>` (Claude / OpenAI / Gemini / Qwen / DeepSeek / Ollama) plus **OpenAI-compatible fallback** via `tagent config use-compat` for any other (Zhipu / Doubao / Kimi / Baichuan / Xunfei / …) — 3 env vars, zero code change. See [`config/llm-providers.md`](config/llm-providers.md)
4. **Learn while using** — `--mode learn` outputs every step with theory references (22 KB cards across 13 domains: tools / coding / foundation / strategy / methods / protocols / platforms / gates / security / AI testing / compliance / process / build-your-own)
5. **Safe-by-default** — sandboxed exec / PII scrub / runtime prompt-injection scan / 4-gate marketplace verify / decisions audit trail
No Python / Node / Docker required. Download and run.

## 📸 Screenshots

| Upload | Dashboard | Catalog | History |
|--------|-----------|---------|---------|
| ![Upload](docs/assets/screenshots/upload.png) | ![Dashboard](docs/assets/screenshots/dashboard.png) | ![Catalog](docs/assets/screenshots/catalog.png) | ![History](docs/assets/screenshots/history.png) |

## 📊 Coverage

- **Product types**: Web · API · Mobile · Desktop · IoT · AI · Blockchain · Vehicle · Embedded · Serverless
- **Test types**: functional / performance / security / compatibility / weak-network / stability / reliability / accessibility / contract / visual / i18n / observability / chaos / mutation / AI-specific (hallucination / prompt-injection / drift / fairness) / compliance
- **Test design methods**: equivalence-partitioning · boundary-value · decision-table · state-transition · pairwise · orthogonal · exploratory SBTM · risk-based · TDD · BDD · ATDD
- **Quality gates**: smoke → regression → performance_ci_quick → performance_full → release (5-layer)

Coverage across the listed categories is broad but not exhaustive. Domain-specific gates (DO-178C avionics / HIPAA medical / IEC 61508 industrial) ship as skeleton compliance YAML profiles — production use in regulated industries requires domain expert review.

## 📖 Design Documents

For project design rationale, architecture decisions, and methodology rationale, see [FULL_GUIDE.md](FULL_GUIDE.md). Inspirations from upstream OSS (hermes / gbrain / karpathy / etc.) are credited in [NOTICE.md](NOTICE.md).

## 📂 Project Structure

```text
Test-Agent/
├── 00-项目导航.md ← 5-dimension category guide
├── docs/getting-started/ ← user manual / deploy / config / deliverables
├── agents/ ← 16 expert agents (11 production + 5 script, V1.x rollout 收尾)
├── skills/ ← 32 business skills (23 production + 7 script + 0 rollout + 2 vision) + 3 meta-skills
├── config/ ← conftest / pytest.ini / .env / .mcp.json
├── utils/ ← 78 production utils
├── ci/ ← GitHub Actions + Jenkins
├── runtime/ ← V1.x runtime layer (router / orchestrator / MCP / web / scheduler / subagent / learning_loop / backends / gateway / tutor / essence_watcher / marketplace)
├── docs/charter/ ← Vision charter (7 split files: vision-dimensions / coverage-matrix / agentchat-protocol / skills-bugtracker / install-deploy / test-architecture / runtime-license)
├── docs/theory/ ← 22 teaching KB cards across 13 categories
├── profiles/compliance/ ← 10 industry compliance YAML profiles
├── marketplace/ ← Community skills / agents / mcp / hooks (4 lanes, 4-gate verify)
├── install.py ← one-command cross-platform deploy
├── README.md ← This file
├── FULL_GUIDE.md ← Full engineering guide
├── CHANGELOG.md ← Version log
└── LICENSE / SECURITY.md / CONTRIBUTING.md / CODE_OF_CONDUCT.md
```

> **Skill Lifecycle (meta-tools)**:
> - **Current (A · methodology reference)**: Each subdir's SKILL.md serves as skill-design reference material.
> - **Usable today (B · perspective extension)**: Use `nuwa-skill` to distill new mental-model perspectives (Naval / Munger / Feynman); use `darwin-skill` to optimize perspective skills.
> - **V2.x Roadmap (C · testing-domain adaptation)**: Re-target nuwa as a test skill/agent distiller; re-target darwin's 8-dim scoring to testing domain.

## 📚 Documentation

| Audience | Read |
|----------|------|
| **First-time user** | [Quick start](docs/getting-started/INDEX.md) → [Deploy](docs/getting-started/部署说明.md) |
| **QA engineer** | [User manual](docs/getting-started/使用手册.md) → [Skill catalog](skills/) |
| **Architect / SRE** | [Architecture deep-dive](docs/charter/06-test-architecture.md) → [Runtime](docs/charter/07-runtime-license.md) → [Runtime modules](runtime/INDEX.md) |
| **Architect / SRE** | [Architecture deep-dive](docs/charter/06-test-architecture.md) → [Runtime modules](runtime/INDEX.md) |
| **Security researcher** | [Pentest expert](agents/15-渗透测试.md) → [pentest-coordinator](skills/pentest-coordinator.md) |
| **Automotive tester** | [Automotive expert](agents/16-车载测试.md) → [ASIL workflow](skills/automotive-test.md) |
| **Contributor** | [CONTRIBUTING.md](CONTRIBUTING.md) → [Marketplace](marketplace/INDEX.md) |

## 🛠️ Tech Stack
## 📊 Coverage

pytest 8.3 · Playwright 1.59 · Appium 5.3 · pywinauto · JMeter 5.6 · Allure · Airtest · OpenCV · Faker · SQLAlchemy 2.0 · MCP 1.0 · LiteLLM · Prefect · FastAPI · React 18 · Tailwind · Postgres+pgvector · MinIO · OpenTelemetry · Loguru · Docker Compose · GitHub Actions / Jenkins
- **Product types**: Web · API · Mobile · Desktop · IoT · AI · Blockchain · Automotive · Embedded · Serverless
- **Test types**: functional / performance / security / compatibility / weak-network / stability / accessibility / visual / i18n / chaos / mutation / AI-specific / compliance
- **Quality gates**: smoke → regression → performance_ci_quick → performance_full → release (5-layer)

## 🤝 Contributing
## 📂 Project Structure

See [`CONTRIBUTING.md`](CONTRIBUTING.md) for the contribution workflow.
```text
Test-Agent/
├── agents/ ← 16 expert agents
├── skills/ ← 32 business skills + 3 meta-skills
├── utils/ ← 78 production utils (pytest · Playwright · JMeter · Appium · …)
├── config/ ← conftest / pytest.ini / .mcp.json
├── runtime/ ← V1.x runtime (router · orchestrator · MCP · …)
├── ci/ ← GitHub Actions + Jenkins
├── docs/ ← user manual / architecture / theory / compliance
├── marketplace/ ← community skills / agents / mcp / hooks
├── install.py ← one-command cross-platform deploy
└── README.md / README.zh-CN.md
```

Community marketplace contributions (`marketplace/`) pass through **4 verification gates** (current implementation): signature presence (planned) → injection-regex scan → AST syntax-parse (V1.x: replace with real Docker sandbox) → frontmatter-presence score (V1.x: swap for real darwin-skill evaluator).
See [FULL_GUIDE.md](FULL_GUIDE.md) and [CHANGELOG.md](CHANGELOG.md) for details.

## 📜 License
## 🛠️ Tech Stack

pytest 8.3 · Playwright 1.59 · Appium 5.3 · JMeter 5.6 · Allure · OpenCV · SQLAlchemy 2.0 · MCP 1.0 · LiteLLM · FastAPI · React 18 · Postgres+pgvector · Docker

MIT License — see [LICENSE](LICENSE).
## 🤝 Contributing

Upstream components retain their own licenses; see [NOTICE.md](NOTICE.md) for attributions.
See [CONTRIBUTING.md](CONTRIBUTING.md). Community marketplace passes 4-gate verification.

## 🙏 Inspirations (essence absorbed)
## 📜 License

- [hermes-agent](https://github.com/NousResearch/hermes-agent) — closed learning loop + 7 backends + multi-platform gateway
- [gbrain](https://github.com/garrytan/gbrain) — self-wiring KB graph + eval replay + safe-by-default
- [andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills) — 4 LLM-coding principles
- [everything-claude-code](https://github.com/affaan-m/everything-claude-code) — TDD / verification / harness-first
- [pentagi](https://github.com/vxcontrol/pentagi) + [shannon](https://github.com/KeygraphHQ/shannon) — pentest agent black-box + white-box
- [build-your-own-x](https://github.com/codecrafters-io/build-your-own-x) — deep-dive learning path
MIT License — see [LICENSE](LICENSE). Upstream components retain their own licenses; see [NOTICE.md](NOTICE.md).

---

Expand Down
Loading
Loading