---

Table of Contents

• Features
• Installation
• Quick Start
• CLI
• AI Chat Providers
• Search Engines
• Text-to-Image
• Text-to-Speech
• OpenAI-Compatible API Server
• Python Client
• Tool Calling
• Model Registry
• Developer Tools
• Documentation
• Contributing
• License

---

---

Features

Search & AI

• Multi-Engine Search -- DuckDuckGo, Bing, Brave, Yahoo, Yep, Yandex, Mojeek, Wikipedia. (Search Docs)
• 90+ AI Providers -- Native, OpenAI-compatible, and local LLM interfaces. (Architecture)
• AI-Powered Search -- Perplexity, IAsk, Monica, AyeSoul, WebPilotAI. (Provider Matrix)
• OpenAI-Compatible API Server -- Serve any Webscout provider via OpenAI endpoints. (Server Docs)
• Unified Python Client -- Auto-failover chat and image generation. (Client Docs)

Media & Content

• Text-to-Image -- PollinationsAI, Together, Miragic, MagicStudio. (TTI Docs)
• Text-to-Speech -- ElevenLabs, Deepgram, OpenAI FM, Parler, Qwen, MurfAI, and more. (Model Registry)
• Speech-to-Text -- ElevenLabs STT. (Provider Matrix)
• YouTube Toolkit -- Video downloads, transcription, API access. (Docs)
• Weather Tools -- Detailed weather info with ASCII display. (Weather Docs)

Developer Tools

• SwiftCLI -- Elegant CLI framework. (SwiftCLI Docs)
• Scout -- HTML parser and web crawler. (Scout Docs)
• LitPrinter -- Styled console output. (LitPrinter Docs)
• LitAgent -- User-agent rotation and IP toolkit. (LitAgent Docs)
• GitAPI -- GitHub data extraction without auth. (GitAPI Docs)
• GGUF Conversion -- Quantize HuggingFace models to GGUF. (GGUF Docs)
• ZeroArt -- Zero-dependency ASCII art generator. (ZeroArt Docs)
• Utility Decorators -- @timeIt and @retry helpers. (Decorator Docs)
• Stream Sanitization -- SSE/HTTP stream processing. (Sanitize Docs)

Privacy & Utilities

• Temp Mail -- Disposable email via Emailnator, MailTM, TempMailIO.
• Proxy Manager -- Automatic proxy rotation. (Architecture)
• Awesome Prompts -- Curated system prompts for AI personas. (Prompts Docs)

---

Installation

pip (Standard)

pip install -U webscout

# With API server support
pip install -U "webscout[api]"

# With development tools
pip install -U "webscout[dev]"

uv (Recommended)

uv add webscout

# Run without installing
uv run webscout --help

# Install as global tool
uv tool install webscout

Docker

docker pull OEvortex/webscout:latest
docker run -it OEvortex/webscout:latest

See docs/DOCKER.md for full Docker deployment options including compose profiles.

---

Quick Start

AI Chat (No API Key)

from webscout import Meta

ai = Meta()
response = ai.chat("Explain quantum computing in simple terms")
print(response)

Web Search

from webscout import DuckDuckGoSearch

search = DuckDuckGoSearch()
results = search.text("best practices for API design", max_results=5)
for result in results:
    print(f"{result['title']}: {result['href']}")

Image Generation

from webscout.Provider.TTI import PollinationsAI

gen = PollinationsAI()
path = gen.generate_image(prompt="A serene mountain landscape at sunset")
print(f"Saved to: {path}")

See docs/getting-started.md for the full quick-start guide.

---

Command Line Interface

Webscout provides a rich CLI powered by Rich with multi-engine support.

webscout --help                       # List all commands
webscout version                      # Show version
webscout text -k "python programming" # DuckDuckGo search (default)
webscout images -k "mountains"        # Image search
webscout news -k "AI breakthrough" -t w  # News from last week
webscout weather -l "New York"        # Weather info
webscout translate -k "Hola" --to en  # Translation

Supported Engines

Category	Engines
text	ddg, bing, brave, yahoo, yep, mojeek, dogpile, wikipedia, yandex
images	ddg, bing, brave, yahoo, yep
videos	ddg, brave, yahoo
news	ddg, bing, brave, yahoo
suggestions	ddg, bing, brave, yahoo, yep
weather	ddg, yahoo
answers	ddg
translate	ddg
maps	ddg

# Use a specific engine
webscout text -k "climate change" -e bing
webscout text -k "quantum physics" -e wikipedia

Full CLI reference: docs/cli.md

---

AI Chat Providers

Native Providers (No Auth Required)

from webscout import Meta, Toolbaz, LLMChat, SonusAI, Netwrck, PiAI

ai = Meta()
print(ai.chat("What is the capital of France?"))

Authenticated Providers

from webscout import OpenAI, GROQ, GEMINI, Cohere, DeepInfra

groq = GROQ(api_key="your-key")
response = groq.chat("Write a Python function to sort a list")

OpenAI-Compatible Providers

from webscout.Provider.OPENAI import ChatGPT, Groq, DeepInfra

chatgpt = ChatGPT()  # No auth required
response = chatgpt.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)

See Provider.md for the complete provider matrix with file locations.

---

Search Engines

from webscout import DuckDuckGoSearch, BingSearch, YepSearch, YahooSearch, BraveSearch

# DuckDuckGo
ddg = DuckDuckGoSearch()
results = ddg.text("python frameworks", max_results=5)

# Bing
bing = BingSearch()
results = bing.text("climate change solutions")

# Brave
brave = BraveSearch()
results = bravesearch.text("machine learning tutorials")

Search docs: docs/search.md

---

Text-to-Image

from webscout.Provider.TTI import PollinationsAI, TogetherImage

# PollinationsAI
poll = PollinationsAI()
poll.generate_image(prompt="A cyberpunk city at night")

# Together AI
together = TogetherImage()
together.generate_image(prompt="A robot playing chess")

TTI docs: docs/getting-started.md#image-generation

---

Text-to-Speech

from webscout.Provider.TTS import ElevenlabsTTS, ParlerTTS

tts = ElevenlabsTTS()
tts.text_to_speech("Hello, world!", voice="alloy")

TTS model registry: docs/models.md

---

OpenAI-Compatible API Server

Run a local FastAPI server that serves any Webscout provider through standard OpenAI endpoints.

# Start the server
webscout-server

# Custom config
webscout-server --port 8080 --host 0.0.0.0 --debug

Use with the OpenAI Python Client

from openai import OpenAI

client = OpenAI(api_key="dummy", base_url="http://localhost:8000/v1")

response = client.chat.completions.create(
    model="ChatGPT/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Docker Deployment

docker-compose up webscout-api
docker-compose -f docker-compose.yml -f docker-compose.no-auth.yml up webscout-api

Full server docs: docs/openai-api-server.md | Docker: docs/DOCKER.md

---

Python Client

The unified Client class provides auto-failover across providers with smart model resolution.

from webscout.client import Client

client = Client(print_provider_info=True)

# Auto provider + model selection
resp = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Summarize Webscout."}]
)
print(resp.choices[0].message.content)

# Streaming
stream = client.chat.completions.create(
    model="ChatGPT/gpt-4o-mini",
    messages=[{"role": "user", "content": "Write a limerick about Python."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

# Image generation
img = client.images.generate(prompt="A neon owl", model="auto", size="1024x1024")
print(img.data[0].url)

Client docs: docs/client.md

---

Tool Calling

Webscout has a built-in tool calling system that works with any provider.

from webscout.Provider.Apriel import Apriel
from webscout.AIbase import Tool

def get_weather(city: str) -> str:
    return f"Weather in {city}: Sunny, 25C"

weather_tool = Tool(
    name="get_weather",
    description="Get current weather for a city.",
    parameters={"city": {"type": "string", "description": "City name."}},
    implementation=get_weather,
)

ai = Apriel(tools=[weather_tool])
print(ai.chat("What is the weather in London?"))

Tool calling docs: docs/tool-calling.md

---

Model Registry

Enumerate available models across all providers.

from webscout import model

# All LLM models
all_models = model.llm.list()
print(f"Total: {len(all_models)}")

# Models by provider
summary = model.llm.summary()
for provider, count in summary.items():
    print(f"  {provider}: {count}")

# TTS voices
voices = model.tts.list()
print(f"Total voices: {len(voices)}")

Model registry docs: docs/models.md

---

Developer Tools

Tool	Description	Docs
SwiftCLI	CLI framework with decorators	docs/swiftcli.md
Scout	HTML parser & web crawler	docs/scout.md
LitPrinter	Styled debug printing	docs/litprinter.md
LitAgent	User-agent rotation	docs/litagent.md
GitAPI	GitHub data extraction	docs/gitapi.md
GGUF	Model conversion & quantization	docs/gguf.md
ZeroArt	ASCII art generator	docs/zeroart.md
Weather	Weather toolkit	docs/weather.md
Decorators	@timeIt and @retry	docs/decorators.md
Sanitize	Stream sanitization	docs/sanitize.md
Prompts	System prompt manager	docs/awesome-prompts.md

---

Documentation

Resource	Description
Getting Started	Installation, first chat, web search, image generation
Architecture	System design, layers, and data flows
CLI Reference	All CLI commands and options
Python Client	Unified client with auto-failover
API Server	OpenAI-compatible FastAPI server
Model Registry	Enumerate LLM, TTS, TTI models
Tool Calling	Function calling with any provider
Search Docs	Multi-engine search API
Scout	HTML parser and crawler
Provider Development	Create custom providers
Deployment	Production deployment guide
Docker	Docker setup and compose profiles
Inferno	Local LLM server
Troubleshooting	Common issues and solutions
Contributing	How to contribute
Provider Matrix	Complete provider listing
Docs Hub	Full documentation index

---

Contributing

See docs/contributing.md for guidelines.

1. Fork the repository
2. Create a feature branch
3. Make changes with descriptive commits
4. Submit a pull request

---

License

Apache-2.0. See LICENSE.md.

---