Show HN: An LLM translator whose source is a single prompt
The LLM Translator project allows users to create a customizable translation app using a single prompt. It supports OpenAI-compatible APIs and offers various features for user configuration and template management. The app is designed in a neobrutalist style and includes a bilingual user interface.
- ▪Users can configure any OpenAI-compatible API with their own base URL, key, model, and temperature settings.
- ▪The app features customizable translation templates that allow users to define their own prompts and switch between them easily.
- ▪It includes a two-column workspace for input and output, along with a settings drawer for API configuration and template editing.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
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/hamsterbase/llm-translator |
| Publication time | Tue, 26 May 2026 18:23:11 +0000 |
| Retrieval time | 2026-05-26T18:37:53.470Z |
| Last seen | 2026-05-26T18:37:53.470Z |
| 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 · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | cgnKrI1BAkMr |
| 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 — open original |
| Substitutes article? | No — 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
LLM Translator 中文 This project is just one prompt. Copy the prompt below into Claude Code or any other LLM to generate the complete app. Online Demo: https://tasks.hamsterbase.com/llm-translator/ Features Bring your own model — configure any OpenAI-compatible API (base URL, key, model, temperature). Customizable translation templates — define your own prompts with {{text}} / {{source_lang}} / {{target_lang}} placeholders and switch between them via tabs. Prompt Build a single-file HTML app (Vue 3 + Tailwind via CDN, no build step) — an LLM-powered translator in neobrutalist style: cream paper background with a black grid, thick 4–6px black borders, hard offset shadows (no border-radius), accent colors acid-yellow / hot-orange / cobalt / pink, Archivo Black headings + JetBrains Mono body.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.