BrainSoup
BrainSoup is a Desktop AI platform launched by Nurgo Software. The core concept is "creating an exclusive AI agent team". Users can create multiple specialized AI Agents using natural language and let them collaborate to complete complex tasks. Supports native LLM (Ollama), multimodality (image/audio), RAG knowledge base, custom tools and low-code extensions. Starting at $5/month.
BrainSoup
Core parameters and statistics
| Parameters | Official verifiable information |
|---|---|
| Product Positioning | Personal AI Platform for desktop |
| Platform | Desktop (native desktop application) |
| Core concepts | Create multiple dedicated AI Agents to collaborate to complete complex tasks |
| LLM support | ChatGPT, Mistral AI, native LLM (Ollama) |
| Knowledge base | RAG (document import + dialogue knowledge accumulation) |
| Tool system | Built-in tools (calculation/browsing/sending emails/API calls/scripts) + custom tools |
| Multimodal | Image and audio understanding (via model collaboration architecture) |
| Price | Starting at $5/month |
| Developer | Nurgo Software |
A brief review: BrainSoup is not another chatbot, but an Agent orchestration platform that allows you to "form an AI team" on the Desktop.
User and market recognition
Gradually build user awareness in the field, and product capabilities are used by content creators and teams to improve work efficiency. Some industry users have incorporated it into their daily workflow. It is recommended to refer to the latest official disclosures for specific user scale and industry adoption rate data.
Cost advantage
C client/individual: Starting price is $5/month, no long-term contract. Compared to Claude Pro ($20/month) or ChatGPT Plus ($20/month), BrainSoup is cheaper and supports multi-agent orchestration and local LLM.
API/Developer: API is not provided separately. Low-code extensions are implemented through script files and require no SDK or API Key management.
Enterprise/Private: Supports local LLM (Ollama), can run completely offline, and data does not leave the device. However, there is currently no enterprise version management function.
Main functions
- Multi-Agent Creation and Orchestration: Create multiple dedicated AI Agents using natural language to collaborate in chat rooms to complete complex tasks. Each Agent has independent roles, tools, and data permissions.
- RAG Knowledge Base: Supports importing documents as the agent's knowledge boundary, and the dialogue process can also organically expand the knowledge base. Built-in Doc-E expert Agent guides use.
- Local LLM support: Integrate local models through Ollama, and the data does not leave the device at all.
- Built-in tool system: calculation, web browsing, email sending API call, image/video generation, script execution, etc. Supports ChatGPT plug-ins and custom tools.
- Multi-modal understanding: Image and audio file understanding, the architecture achieves low-cost multi-modality through multi-model collaboration.
- Low-Code Extensions: Interact with software contextually via text files and scripts in any language, no SDK required.
- Sandbox File System: Agents and users share files in a secure sandbox environment.
Model and version evolution
Continuous iterative updates, the latest version introduces performance optimization and new features. Historical version information can be viewed on the official release page. There is no complete public version evolution timeline yet. It is recommended to pay attention to the official announcement to understand the rhythm of feature updates.
Technical advantages
Main Type Judgment: Agent/MCP/Automation Tool - Desktop AI Agent orchestration platform.
Architecture Link: User → Natural Language Instructions → BrainSoup Agent Chat Room → Multi-Agent Collaboration → Built-in/Custom Tools → File System/API/External Services
The core design concept of BrainSoup is "dedicated Agent collaboration is better than general-purpose Agent" - by allowing multiple Agents with their own strengths to coordinate their work in the chat room, complex tasks can be disassembled and processed in parallel. Semantic Kernel technology gives the Agent time awareness and self-awareness, allowing it to remember the user and conversation context.
Guide to engineering pitfalls:
- Agent task allocation: When multi-Agent collaborates, the task allocation logic relies on natural language description, and overlapping or omissions of responsibilities may occur in complex scenarios. It is recommended to clarify the role boundaries and triggering conditions when creating an Agent.
- Local LLM performance: When using Ollama local models, inference speed and model capabilities depend on local hardware (GPU/memory), and large-scale document RAG retrieval may have high memory requirements.
- Extended debugging: Low-code extensions are implemented through script files. Debugging relies on log output and lacks IDE-level breakpoint debugging support.
How to use
| Entrance | Description |
|---|---|
| Desktop desktop application | Download BrainSoup.msi from the official website and install |
| Free trial | Low-entry subscription starting at $5/month |
| Doc-E built-in guidance | After installation, the built-in AI expert Doc-E will guide you to complete the initial configuration |
Product Pricing
The pricing model is subject to the official real-time page. Usually a freemium or subscription system is used, and basic functions can be used for free. Advanced functions or high-frequency use require paid subscriptions, and users are advised to evaluate the optimal solution based on actual usage.
Application scenarios
- Personal Knowledge Management: Import local documents into BrainSoup and create a dedicated knowledge base Agent for Q&A and analysis.
- Automated Workflow: Create multiple Agents to collaborate on repetitive tasks such as data processing, report generation, and email sending.
- Research and Writing: Let research agents collect information, analyze agent processing data, and writing agents generate reports, multi-agent pipeline operations.
Applicable people
- Individual Users: Content creators and knowledge workers who need AI assistance to improve their daily work efficiency.
- Developers: Technical teams who need to integrate AI capabilities into their own products or services through APIs.
- Enterprise: Organizations seeking to deploy AI at scale in their field.
Summary and Outlook
BrainSoup proposed an interesting idea for a desktop AI product - instead of using one all-powerful AI, it would instead form multiple dedicated AI teams. The starting price of $5/month is a low threshold among AI products. The product is still in its early stages, and the roadmap includes important features such as macOS, Headless server version, and cloud synchronization.
Not suitable for the boundary: Only supports the Desktop platform; the product is in its early stage and features are still being rapidly iterated; Agent orchestration requires certain configuration and understanding costs; cloud team collaboration is not supported.
Purchase Risk: As a small team, Nurgo Software needs to observe its long-term product maintenance capabilities and update rhythm. It is recommended to start a trial at $5/month and make sure that the Agent orchestration mode matches your personal workflow before committing to a long-term subscription.
Related tools: crewai, langchain
Version Info
- BrainSoup current ：Currently supports multi-Agent collaborative RAG knowledge base, local LLM (Ollama), multi-modality, custom tools, and low-code extensions.
- BrainSoup launch ：BrainSoup was first released as a desktop AI platform, supporting basic agent creation and conversation functions.
User Reviews