Show HN: VernLLM – The AI resilience layer for TypeScript
VernLLM is an open-source TypeScript library that adds resilience features to LLM chat completion calls. It offers retries, timeouts, circuit breaking, caching, structured output validation, and usage tracking across multiple providers. The library can wrap existing LLM clients without requiring code changes and supports custom cache backends.
- ▪VernLLM provides built‑in retry logic with exponential backoff, per‑attempt timeouts, and a circuit‑breaker that trips after repeated failures.
- ▪It validates responses against Zod schemas, ensuring typed and structured JSON output.
- ▪Caching is handled via a pluggable adapter, allowing developers to use Redis, databases, or in‑memory stores.
- ▪The library works with a wide range of LLM providers, including OpenAI, Anthropic, Gemini, and many others.
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,796 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 | VernLLM |
| Canonical URL | https://vernllm.vercel.app |
| Publication time | Wed, 29 Jul 2026 17:05:25 +0000 |
| Retrieval time | 2026-07-29T17:16:08.799Z |
| Last seen | 2026-07-29T17:16:08.799Z |
| 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 | Hd621bmZw1L_ · 1 stories |
| 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
VernLLMDocumentationSearch⌘K{"@context":"https://schema.org","@type":"SoftwareSourceCode","name":"VernLLM","description":"A lightweight resilience layer for LLM chat completion calls. Retries, timeouts, circuit breaking, caching, structured output, and usage tracking, with one interface across providers.","url":"https://vernllm.vercel.app","programmingLanguage":"TypeScript","codeRepository":"https://github.com/LakBud/vernLLM"}Reliable LLM calls,by default.A lightweight resilience layer for LLM chat completions.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at VernLLM.
Discussion
0 commentsMore from VernLLM
