Urgent.News

What's breaking now, across thousands of outlets.

AI

aiFetchly — a local-first desktop AI agent for lead gen, research, and outreach

Most marketing AI tools live in a browser tab and forget your files the moment you close the chat. aiFetchly is an open-source, local-first desktop AI agent (Windows, macOS, Linux) built for business research, document-grounded drafting, lead organization, and scheduled outreach — with permission-gated tools you can review. What it does Tool-using AI chat with transcripts and permission controls…

aiFetchly is a new desktop AI agent designed for marketing and research tasks. Unlike many marketing AI tools that operate in a browser tab and discard files when the chat ends, aiFetchly runs locally on Windows, macOS, and Linux devices. It is built for business research, document-grounded drafting, lead organization, and scheduled outreach, all within a permission-gated environment where users can review tools.

The tool utilizes a Knowledge Library powered by Retrieval-Augmented Generation (RAG), enabling it to ground emails and reports in your own PDFs, Word documents, and HTML. This feature allows for more relevant and context-specific responses.

aiFetchly facilitates lead generation across multiple search engines, including a Local Business Finder that integrates with Google Maps and Yandex Maps. The results can be exported in CSV or JSON formats for further analysis.

For email writing and outreach campaigns, aiFetchly offers AI-generated drafts which can be sent through SMTP from your server. Users can customize filters and deduplicate contacts as needed. A task scheduler adds functionality such as cron jobs, dependencies, the ability to pause or resume tasks, and execution history tracking.

The platform's extensibility is enhanced by support for skills, plugins, MCP tools, and specialist subagents, making it highly customizable for various business needs.

Local-first design is a key aspect of aiFetchly. By keeping a business Knowledge Library and task history on the desktop, it ensures that recurring operational workflows are fully reviewable. Users can examine which tools have been executed, what content has been drafted, and identify any elements that still require human approval before sending out communications.

For more details on aiFetchly's features, visit https://www.aifetchly.com/features. The platform's documentation provides in-depth guidance on lead generation, available at https://docs.aifetchly.com/docs/category/lead-generation. Installation instructions are available at https://docs.aifetchly.com/docs/getting-started/installation.

The development team welcomes feedback from users and builders working on similar local agents for non-coding workflows.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

I recorded my Kubernetes AI agent failing, on purpose

Most demos of AI-for-infrastructure tools show a clean run. I think that is exactly backwards, and I want to explain why by walking through the thirty seconds of my own demo that a normal product…

  • AI agent demonstrates handling Kubernetes deployment failures
  • Agent identifies crash-looping issue and missing DATABASEURL
  • Guardrail mechanism controls AI actions, ensuring accuracy

More from Sunday 13 September →