--- title: "Models and Tools · AssistantGeneral" description: "Run the model you choose, locally or in a cloud you pick, use tools that act on files and the web, and connect the systems and accounts you already have." url: "https://royalsoftworks.com/products/assistant-general/features/models-and-tools/" source: "https://royalsoftworks.com" format: "markdown" note: "Markdown rendering of the HTML page at `url`. Same content, same canonical URL." --- Features · 2 of 6 # Your models, a real toolbox, your stack. Run the model you choose, use tools that act on files, and connect the systems you already have. Models, your way ## Run any model — on your machine, or any cloud you choose. The default engine is local: llama.cpp running any GGUF model — Llama, Mistral, Qwen, Phi, Gemma, DeepSeek and hundreds more — entirely offline. When a task calls for a frontier model, connect a cloud provider in one click and route just that request to it. You are never locked to a single vendor, and nothing is sent anywhere unless you say so. - Local inference via llama.cpp — fully offline, no API keys - The built-in model writes faster with a small helper that drafts ahead; the main model checks every word, so the answer is unchanged - Optional providers: Anthropic, OpenAI, Google Gemini, xAI, Groq, Mistral, DeepSeek, Together, OpenRouter, or any OpenAI-compatible endpoint - Pool several machines or GPUs into one routed model cluster - Pick the model per task, per persona, or per team policy A real toolbox ## It uses tools to get work done, not just to talk about it. AssistantGeneral acts. It reads and edits files, runs shell commands behind a confirmation gate, researches across the open web, and authors real Office documents through a sandboxed Python runtime. For regulated work it can consult authoritative sources directly, so answers are sourced rather than guessed. - File read / write / surgical edit with diffs — never blind overwrites - Web and domain research tools with citations - Authoritative research: PubMed, Europe PMC, ClinicalTrials.gov, US case law, retraction screening - Office authoring: real .xlsx, .docx and .pptx via sandboxed Python Connected to your stack ## Bring in your data — and let it act in your apps. Twenty built-in connectors sync from the places your knowledge already lives: cloud storage, databases, Google Workspace, Microsoft 365, email, Dropbox and a built-in web crawler. Through the Model Context Protocol it goes further — nine connected accounts both read and take action in the tools your team runs every day, and you can add any other MCP server. - Connectors: S3, Azure Blob, Google Cloud Storage, SharePoint, OneDrive, Outlook, OneNote, Google Drive, Gmail, IMAP email, Dropbox, Postgres, MySQL, BigQuery, Snowflake, web crawler and more - Connected accounts read and act in Slack, Teams, Discord, Notion, Jira & Confluence, GitHub, GitLab, Linear, HubSpot - Runs as an MCP server itself, and connects to your custom MCP servers - Scheduled syncs keep the knowledge base current [Previous Finished files, answers with sources.](https://royalsoftworks.com/products/assistant-general/features/finished-work/) [Next Jobs that run without you.](https://royalsoftworks.com/products/assistant-general/features/automation/) [All of AssistantGeneral features](https://royalsoftworks.com/products/assistant-general/features/)