Give Local LLMs Web Access with SearXNG, Firecrawl & Camofox
Make local LLMs more useful by adding web access: SearXNG for search, Firecrawl for scraping, and Camofox for JS-heavy sites. Search→Extract→Interact.
Useful tip:
Running an LLM locally? Give them web access.
Use this stack:
- SearXNG — search and source selection
- Firecrawl — scraping and crawling sites by known URLs
- Camofox — browser fallback when a site is tied to JavaScript or requires interaction
Workflow:
Search → Data extraction → Interaction
Ask your favorite agent to set up this stack and connect it to local models. After that, they become noticeably more useful.
You’re welcome.
Comments
Weekly digest
The best of vibe coding, AI agents and open source — once a week, no spam.
Related articles
All articlesCline Desktop Launches AI Agent Workspace for macOS & Windows
Cline Desktop offers an open‑source AI workspace with parallel agents, task scheduling, checkpoints, branching, and a plugin marketplace, now on macOS and Windows.
Tolaria: Free macOS Markdown Knowledge Base App Built with AI Agents
Tolaria is a free, open-source macOS desktop app for Markdown knowledge bases and collaboration—built in 3 months as a major AI-assisted coding experiment.
Google Opens Harness²: Open‑Source Framework for Recursive AI Agents
Google releases Harness², an open‑source harness enabling recursive management and learning for AI agents with system prompts, memory, tools, subagents, and plugins.