RepoRadar
Leave a Tip
Item detail
github.com

Johell1NS/browser-search

RepoRadar surfaced Johell1NS/browser-search — a searxng + camofox + cloakbrowser — into the Research & Search section, where it sits at Silver tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 8.7 out of 10.

Open source →Back to radar
Score7.6
Popularity1.0
Risklow
TierSilver
Score breakdown
Usefulness8.0
Novelty8.0
Momentum6.0
Maturity5.6
Open-source/build8.4
Evidence7.2
Workflow potential8.7
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for any developer, researcher, or AI-curious user who wants their agent (Claude Code, OpenCode, Cursor, OpenClaw) to do real web research against anti-bot-protected sites without depending on a hosted search vendor or a paid anti-detect browser service. The three-tool orchestration shape is the durable differentiator: most 'web search for agents' skills ship one tool (SearXNG-only, or playw

Who should use it

Any developer, researcher, or AI-curious user who wants their agent (Claude Code, OpenCode, Cursor, OpenClaw) to do real web research against anti-bot-protected sites — SearXNG for the search, Camofox for the JS-heavy pages, CloakBrowser for the anti-bot-protected pages, automatic escalation between themAnyone who does not want to depend on a hosted search API or a paid anti-detect browser service — SearXNG handles search (no SaaS vendor, multi-source meta-search), Camofox handles JS-heavy browsing (Docker REST API, no headless-browser babysitting), CloakBrowser handles anti-bot (npm install, no residential-proxy subscription)Anyone who wants a research skill with an explicit 'do not browse social media that requires login (Instagram/Facebook/TikTok/LinkedIn/Twitter/X)' guardrail — the rule is encoded in the SKILL.md so the agent reads it at load time, not buried in a READMEAnyone who wants a research skill that is read-only by default — the agent can fetch URLs and take screenshots but cannot write to the filesystem, 'safe to run even in Plan mode'Multilingual teams — the documentation ships in 12 languages (EN, Simplified Chinese, Spanish, Japanese, Korean, Portuguese-Brazil, French, German, Russian, Arabic, Hindi, Italian), which is the right shape for a global research-community releaseAnyone who has hit the ceiling of hosted-search APIs on paywalls or rate limits — SearXNG is meta-search (it queries dozens of backends, so a single backend's rate limit does not cap the whole search)Anyone who needs their agent to escalate from a simple `curl` to a stealth browser transparently — the SKILL.md is the orchestration layerPrivacy-sensitive deployments — the whole stack runs in Docker on the user's machine, so the queries and the visited URLs never leave the box

Who should skip it

Skip Johell1NS/browser-search if the source link, documentation, or setup requirements do not align with your current workflow or stack.

About this signal

Johell1NS/browser-search is tracked by RepoRadar as a searxng + camofox + cloakbrowser in the Research & Search section. It was first seen on 2026-07-04 and last updated on 2026-07-04. The current verdict is 'try now' with a Silver tier and moderate setup difficulty. Across RepoRadar's eight signals, Johell1NS/browser-search is strongest on workflow potential (8.7) and open-source/build quality (8.4) and weakest on maturity (5.6) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned Johell1NS/browser-search a composite score of 7.6 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to read AI benchmarks without getting fooled for the checklist behind this score.

Risk explanation

Risk label is still being reviewed from the captured evidence. Treat the item as unknown-risk until you review the linked source, permissions, setup path, and data access.

Evidence links
Closest alternatives / related signals
web-searchbrowsingsearchanti-botcloudflareakamaidatadomesearxng