Sunglasses: An open-source input scanner for AI agents
Protection layer + neighborhood watch for AI agents. πΆ Try it in your browser β no install: sunglasses.dev/scan β scan text, GitHub repos, or images. Image OCR runs locally in your browser; the image never leaves your device. Most AI agent attacks don't look like attacks.
- βͺProtection layer + neighborhood watch for AI agents. πΆ Try it in your browser β no install: sunglasses.dev/scan β scan text, GitHub repos, or images.
- βͺImage OCR runs locally in your browser; the image never leaves your device.
- βͺMost AI agent attacks don't look like attacks.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,270 of its stories.
Story provenance
Source Β· retrieval Β· rights Β· ranking β open for full record
inspect β
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/sunglasses-dev/sunglasses |
| Publication time | Thu, 23 Jul 2026 14:48:45 +0000 |
| Retrieval time | 2026-07-23T14:56:52.246Z |
| Last seen | 2026-07-23T14:56:52.246Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch Β· cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 3DsA7eHfoYj8 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes β open original |
| Substitutes article? | No β link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
SUNGLASSES Sunglasses for AI agents. Protection layer + neighborhood watch for AI agents. πΆ Try it in your browser β no install: sunglasses.dev/scan β scan text, GitHub repos, or images. Image OCR runs locally in your browser; the image never leaves your device. What is SUNGLASSES? Most AI agent attacks don't look like attacks. They hide inside normal-looking content β emails, web pages, images, audio, PDFs, QR codes β and try to hijack your agent's behavior. SUNGLASSES is a free, open-source input defense layer. It filters everything before your agent sees it. Hidden instructions get stripped. Legitimate content passes through clean.
β¦
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.