robodogcli 2.6.7

Robodog

Robodog AI

Overview

Robodog is a lightweight, zero-install, command-line style generative AI client that integrates multiple providers (OpenAI, OpenRouter, LlamaAI, DeepSeek, Anthropic, Sarvam AI, Google Search API, and more) into a unified interface. Key capabilities include:

• Access to cutting-edge models: o4-mini (200k context), gpt-4, gpt-4-turbo, dall-e-3, Llama3-70b, Claude Opus/Sonnet, Mistral, Sarvam-M, Gemma 3n, etc.
• Massive context windows (up to 200k tokens) across different models.
• Seamless chat history & knowledge management with stashes and snapshots.
• File import/export (text, Markdown, code, PDF, images via OCR).
• In-chat file inclusion from a local MCP server.
• Built-in web search integration.
• Image generation & OCR pipelines.
• Accessible, retro “console” UI with customizable themes and responsive design.

---

Try Robodog

• Web: https://adourish.github.io/robodog/robodog/dist/
• Android: https://play.google.com/store/apps/details?id=com.unclebulgaria.robodog
• npm packages:
  • npm install robodoglib
  • npm install robodogcli
  • npm install robodog
  • pip install robodogcli
  • pip show -f robodogcli
  • python -m robodogcli.cli --help

---

Configuration

Click the ⚙️ icon in the top-menu to open settings:

Edit your YAML to configure providers, models, specialists, and the MCP server:

configs:
  providers:
    - provider: openAI
      baseUrl: "https://api.openai.com"
      apiKey: "<YOUR_OPENAI_KEY>"
      httpReferer: "https://adourish.github.io"
    - provider: openRouter
      baseUrl: "https://openrouter.ai/api/v1"
      apiKey: "<YOUR_ROUTER_KEY>"
    - provider: searchAPI
      baseUrl: "https://google-search74.p.rapidapi.com"
      apiKey: "<YOUR_RAPIDAPI_KEY>"

  specialists:
    - specialist: nlp
      resume: natural language processing, content generation
    - specialist: gi
      resume: image generation from text
    - specialist: search
      resume: web search integration

  mcpServer:
    baseUrl: "http://localhost:2500"
    apiKey: "testtoken"

  models:
    - provider: openAI
      model: gpt-4
      stream: true
      specialist: nlp
      about: best for reasoning
    - provider: openAI
      model: o4-mini
      stream: true
      specialist: nlp
      about: 200k token context, advanced reasoning
    - provider: openAI
      model: dall-e-3
      stream: false
      specialist: gi
      about: image creation
    - provider: searchAPI
      model: search
      stream: false
      specialist: search
      about: web search results

---

Supported Models

OpenAI

• gpt-4, gpt-4-turbo, gpt-3.5-turbo, gpt-3.5-turbo-16k, o4-mini, o1
• dall-e-3

Others

• LlamaAI: llama3-70b
• Anthropic: Claude Opus 4, Claude Sonnet 4
• DeepSeek R1
• Mistral Medium 3, Devstral-Small
• Sarvam-M
• Google Gemma 3n E4B

---

Key Features

• Multi-Provider Support: Switch between any configured provider or model on the fly.
• Chat & Knowledge: Separate panes for Chat History (💭) and Knowledge (📝)—both resizable.
• Stash Management:
  • /stash <name> — save current chat+knowledge
  • /pop <name> — restore a stash
  • /list — list all stashes
  • CTRL+SHIFT+UP — cycle through stashes
• File Import/Export:
  • /import — pick files (.md, .txt, .js, .py, .json, .yaml, .csv, PDFs, images)
  • /export <filename> — download knowledge & chat snapshot
  • 📤 / 📥 buttons in toolbar
    
• MCP File Inclusion:
  • /include all
  • /include file=README.md
  • /include pattern=*.js|*.css recursive
  • /include dir=src pattern=*.py recursive
  • /curl tell me about example.com
  • /play tgo to example.com tell me the page title Hand off included files into prompts seamlessly.
• Web Search: Enter /search mode or click 🔎 to perform live web queries.
• Image Generation & OCR: Ask questions to dall-e-3 or drop an image to extract text via OCR.
• Interactive Console UI: Retro “pip-boy green” theme, responsive on desktop/mobile, accessible.
• Performance & Size Indicators: Emoji feedback for processing speed and token usage.
• Extensive Command Palette: /help lists all commands, indicators, and settings.

Usage Examples

Web‐Automation Testing with /play

Run AI-generated Playwright tests end-to-end. Robodog will:

1. Parse your natural-language instructions into discrete steps
2. Spin up a headless browser and execute each step, retrying once on failure
3. Log each attempt and, at the end, print a Success/Failure summary

Example:

  /play navigate to https://example.com, extract the page title, and verify it contains 'Example Domain'

Expected output:

Instructions: navigate to https://example.com, extract the page title, and verify it contains 'Example Domain'

----- Parsed steps -----

1. Navigate to https://example.com
2. Extract the page title
3. Verify the title contains 'Example Domain'

Starting step 1: Navigate to https://example.com --- Attempt 1 on page: (about:blank) --- Step 1 attempt 1 → Success: None

Starting step 2: Extract the page title --- Attempt 1 on page: Example Domain (https://example.com) --- Step 2 attempt 1 → Success: 'Example Domain'

Starting step 3: Verify the title contains 'Example Domain' --- Attempt 1 on page: Example Domain (https://example.com) --- Step 3 attempt 1 → Success: True

--- /play summary --- Step 1: Success Step 2: Success Step 3: Success

Switch Model

/model o4-mini

→ “Model is set to o4-mini”

Ask a Question

Simply type your query in the Chat💬 box and hit 🤖 or Enter.

Import Files

Click 📤 or type:

/import

Select one or more files—content is appended to Knowledge📝.

Export Snapshot

/export my_conversation.txt

Downloads a plain-text transcript of Chat History, Knowledge, and Content logs.

Include Code from Your Project

/include pattern=*robodog*.js recursive

Includes all *.js files matching pattern under all configured project roots.

Web Search

/search What is Robodog AI?

Returns top results with clickable links.

Generate an Image

/dall-e-3 Create a sci-fi console UI in 1024x1024

→ Displays generated image inline.

---

Robodog CLI

python robodog.py --folders c:\projects\robodog\robodogcli --port 2500 --token testtoken --config config.yaml --model o4-mini

## MCP File Service Syntax  

![Robodog MCP File Service](screenshot-mcp.png)  
```txt
/include all
/include file=*.md
/include pattern=*service*.js recursive
/include dir=src pattern=*.py recursive

Globs: *, ?, character classes. No full regex.

---

MCP Server Startup

python robodog.py --folders c:\projects\robodog\robodogcli --port 2500 --token testtoken --config config.yaml --model o4-mini

---

Supported File Formats

• Text & Markdown: .txt, .md, .markdown
• Code: .js, .ts, .py, .java, .c, .cpp, .go, .rs
• Config/Data: .yaml, .yml, .json, .xml, .csv
• PDF: .pdf
• Images: .png, .jpg, .jpeg, .gif, .bmp, .tiff, .pbm, .pgm, .ppm

---

Command Reference

Run /help in-app or see the list below:

/help                    — show help  
/model <name>            — switch model  
/import                  — import files  
/export <filename>       — export snapshot  
/clear                   — clear chat & knowledge  
/stash <name>            — stash chat+knowledge  
/pop   <name>            — retrieve stash  
/list                    — list stashes  
/temperature <n>         — set temperature (0–2)  
/max_tokens <n>          — set max tokens  
/top_p <n>               — set nucleus sampling  
/frequency_penalty <n>   — set frequency penalty  
/presence_penalty <n>    — set presence penalty  
/rest                    — use REST completions  
/stream                  — use streaming completions  
/include …               — include files via MCP  
/play <instructions>     — run AI-driven Playwright tests against a website: parses your instructions into code, executes each step, and summarizes success/failure

Also supports keyboard shortcuts:

• CTRL+SHIFT+UP to cycle stashes
• CTRL+S to save a snapshot

---

Indicators & Emojis

• [💭] Chat History
• [📝] Knowledge Content
• [💬] Chat Text
• [👾] User
• [🤖] Assistant
• [💾] System
• [🐋/🦕/🐘/🐁] Token usage levels
• [🐢/🦘/🐆/🦌/🐕] Performance (response time)

---

Accessibility & PWA

• Meets Section 508 and WCAG principles.
• Detects standalone ≥Installable as a PWA on supported devices.

---

Build & Run

# Clone or unzip robodog
cd robodog
python build.py
# Open in browser
open ./dist/robodog.html

Run the CLI

The cli an optional service that can run robodog commands and host the MCP file service for local context

pip install robodogcli
pip show -f robodogcli
python -m robodog.cli --help
python -m robodog.cli --folders c:\projects\robodog\robodogcli --port 2500 --token "<mcpServer.apiKey>" --config config.yaml --model o4-mini    

Use Robodog

Robodog is hosted on github, navigate. Robodog stores user data in the browser local storage.

open https://adourish.github.io/robodog/robodog/dist/

Experience the future of AI interaction—fast, contextual, and extensible. Enjoy Robodog AI!