### Quick Start Installer Script (macOS/Linux)

Source: https://github.com/operative-sh/web-eval-agent/blob/main/README.md

This command downloads and executes the main operative.sh installation script. It handles installing necessary dependencies like Playwright and uv, and configures your code editor. This is the recommended quick start method.

```bash
curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh
```

--------------------------------

### Manual Install: Install uv (macOS/Linux)

Source: https://github.com/operative-sh/web-eval-agent/blob/main/README.md

This command downloads and executes the `uv` package manager installation script directly from astral.sh. `uv` is used by the web-eval-agent for dependency management. This is part of the manual installation process.

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh)
```

--------------------------------

### Manual Install: Install uv (Windows)

Source: https://github.com/operative-sh/web-eval-agent/blob/main/README.md

This command downloads and executes the `uv` package manager installation script directly from astral.sh. `uv` is used by the web-eval-agent for dependency management. This is part of the manual installation process on Windows.

```bash
(curl -LsSf https://astral.sh/uv/install.sh | sh)
```

--------------------------------

### Manual Install: Install Playwright Dependencies (Windows)

Source: https://github.com/operative-sh/web-eval-agent/blob/main/README.md

This command uses `uvx` to install Playwright dependencies directly from the web-eval-agent git repository. This ensures the correct version and configuration of Playwright are used within the uv environment for the manual Windows installation.

```bash
uvx --from git+https://github.com/Operative-Sh/web-eval-agent.git playwright install
```

--------------------------------

### Manual Install: Install Playwright (macOS/Linux)

Source: https://github.com/operative-sh/web-eval-agent/blob/main/README.md

This command first installs Playwright and its Chromium browser globally using npm. It then uses `uvx` to ensure Playwright's browser dependencies are installed correctly within the uv environment. This is a crucial step for the agent to control a browser.

```bash
npm install -g chromium playwright && uvx --with playwright playwright install --with-deps
```

--------------------------------

### Project Dependencies List - Python

Source: https://github.com/operative-sh/web-eval-agent/blob/main/requirements.txt

This snippet contains the complete list of Python packages and their exact versions required by the project. This list is used by tools like pip (e.g., `pip install -r requirements.txt`) to install all necessary libraries.

```Python
annotated-types==0.7.0
anthropic==0.49.0
anyio==4.9.0
backoff==2.2.1
beautifulsoup4==4.13.3
browser-use==0.1.40
cachetools==5.5.2
certifi==2025.1.31
charset-normalizer==3.4.1
click==8.1.8
defusedxml==0.7.1
distro==1.9.0
filetype==1.2.0
google-ai-generativelanguage==0.6.15
google-api-core==2.24.2
google-api-python-client==2.166.0
google-auth==2.38.0
google-auth-httplib2==0.2.0
google-genai==1.9.0
google-generativeai==0.8.4
googleapis-common-protos==1.69.2
greenlet==3.1.1
grpcio==1.71.0
grpcio-status==1.71.0
h11==0.14.0
httpcore==1.0.7
httplib2==0.22.0
httpx==0.28.1
httpx-sse==0.4.0
idna==3.10
jiter==0.9.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.3.22
langchain-anthropic==0.3.3
langchain-core==0.3.49
langchain-google-genai==2.0.10
langchain-ollama==0.2.2
langchain-openai==0.3.1
langchain-text-splitters==0.3.7
langsmith==0.3.22
markdownify==0.14.1
mcp==1.6.0
monotonic==1.6
ollama==0.4.7
openai==1.70.0
orjson==3.10.16
packaging==24.2
playwright==1.51.0
posthog==3.23.0
proto-plus==1.26.1
protobuf==5.29.4
pyasn1==0.6.1
pyasn1-modules==0.4.2
pydantic==2.11.1
pydantic-core==2.33.0
pydantic-settings==2.8.1
pyee==12.1.1
pyparsing==3.2.3
python-dateutil==2.9.0.post0
python-dotenv==1.1.0
pyyaml==6.0.2
regex==2024.11.6
requests==2.32.3
requests-toolbelt==1.0.0
rsa==4.9
setuptools==78.1.0
six==1.17.0
sniffio==1.3.1
soupsieve==2.6
sqlalchemy==2.0.40
sse-starlette==2.2.1
starlette==0.46.1
tenacity==9.0.0
tiktoken==0.9.0
tqdm==4.67.1
typing-extensions==4.13.0
typing-inspection==0.4.0
uritemplate==4.1.1
urllib3==2.3.0
uvicorn==0.34.0
websockets==15.0.1
zstandard==0.23.0
Flask==3.0.3
Flask-SocketIO==5.3.6
```

--------------------------------

### Sample Web Evaluation Report Output (Text)

Source: https://github.com/operative-sh/web-eval-agent/blob/main/README.md

This snippet shows a sample report generated by the web evaluation agent. It includes the task description, a list of agent steps performed, captured console logs, network requests, and a chronological timeline of events during the evaluation run.

```text
📊 Web Evaluation Report for http://localhost:5173 complete!
📝 Task: Test the API-key deletion flow by navigating to the API Keys section, deleting a key, and judging the UX.

🔍 Agent Steps
  📍 1. Navigate → http://localhost:5173
  📍 2. Click     "Login"        (button index 2)
  📍 3. Click     "API Keys"     (button index 4)
  📍 4. Click     "Create Key"   (button index 9)
  📍 5. Type      "Test API Key" (input index 2)
  📍 6. Click     "Done"         (button index 3)
  📍 7. Click     "Delete"       (button index 10)
  📍 8. Click     "Delete"       (confirm index 3)
🏁 Flow tested successfully – UX felt smooth and intuitive.

🖥️ Console Logs (10)
  1. [debug] [vite] connecting…
  2. [debug] [vite] connected.
  3. [info]  Download the React DevTools …
     …

🌐 Network Requests (10)
  1. GET /src/pages/SleepingMasks.tsx                   304
  2. GET /src/pages/MCPRegistryRegistry.tsx             304
     …

⏱️ Chronological Timeline
  01:16:23.293 🖥️ Console [debug] [vite] connecting…
  01:16:23.303 🖥️ Console [debug] [vite] connected.
  01:16:23.312 ➡️ GET /src/pages/SleepingMasks.tsx
  01:16:23.318 ⬅️ 304 /src/pages/SleepingMasks.tsx
     …
  01:17:45.038 🤖 🏁 Flow finished – deletion verified
  01:17:47.038 🤖 📋 Conclusion repeated above
👁️  See the "Operative Control Center" dashboard for live logs.
```

--------------------------------

### Editor Configuration for web-eval-agent Tool

Source: https://github.com/operative-sh/web-eval-agent/blob/main/README.md

This JSON object defines the configuration for the `web-eval-agent` tool within compatible code editors. It specifies the command (`uvx`) to execute, the arguments to refresh the package from the git repository, and sets the `OPERATIVE_API_KEY` environment variable. This allows the editor to invoke the agent.

```json
    "web-eval-agent": {
      "command": "uvx",
      "args": [
        "--refresh-package",
        "webEvalAgent",
        "--from",
        "git+https://github.com/Operative-Sh/web-eval-agent.git",
        "webEvalAgent"
      ],
      "env": {
        "OPERATIVE_API_KEY": "<YOUR_KEY>"
      }
    }
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.