RT Avi Chawla (@_avichawla)I just built my own multi-agent deep researcher!It uses a 100% local LLM and MCP.Here's an overview of how it works:- User submits a query- Web agent searches with Bright Data MCP tool- Research agents generate insights using platform-specific tools- Response agent crafts a coherent answer with citationsTech stack:- Bright Data MCP for real-time web access- CrewAI for multi-agent orchestration- Ollama to locally serve GPT-OSSWhy Bright Data MCP?To build this workflow, we needed to ...

Technology Stack - The multi-agent deep researcher utilizes a 100% local LLM and MCP [1] - The system employs CrewAI for multi-agent orchestration and Ollama to locally serve GPT-OSS [2] Web Access Solution - Bright Data Web MCP is used to gather information from several sources, addressing issues like IP blocks and CAPTCHA blocks [1] - Bright Data MCP offers platform-specific tools compatible with major agent frameworks [2] - Bright Data MCP provides real-time web access [2] Workflow - The workflow involves a user submitting a query, followed by a web agent searching with the Bright Data MCP tool [2] - Research agents generate insights using platform-specific tools, and a response agent crafts a coherent answer with citations [2]