browser-search
Reduces hallucination risk by grounding AI responses in real-time web data.
A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.
- Ask Claude to search the web for current API documentation without hallucinating outdated information.
- Generate a competitive analysis by browsing multiple websites to gather current pricing and features.
- Find the latest security vulnerabilities or CVEs affecting your technology stack right now.
Reduces hallucination risk by grounding AI responses in real-time web data. Self-hosted architecture eliminates API costs and vendor lock-in while maintaining full control over search behavior and data.
Engineering teams deploying autonomous AI agents requiring factual accuracy and cost-effective external data retrieval.
https://github.com/Johell1NS/browser-search
By Johell1NS
How to Get It
claude plugins install Johell1NS/browser-search
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Search the web for current API documentation without hallucinating outdated information
Trust Signals Auto-scanned
Community Pulse New
- Windows popup to change competing browser search engine to Bing anticompetitive? — Hacker News · 76 pts
- Arc Search combines browser, search engine, and AI into something new — Hacker News · 9 pts
- Arc Search combines browser, search engine, AI into something new and different — Hacker News · 6 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 465 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 465 GitHub stars; contributors unknown; last commit 0d ago; license MIT.