Show HN: Llmbridge, a C++ LLM gateway with sub-millisecond overhead
llmbridge A sub-millisecond, drop-in OpenAI-compatible LLM gateway in C++. Microsecond translation overhead, dependency-free default build (TLS uses OpenSSL), p99 < 1 ms at 1,000 RPS. What it does llmbridge is a sub-millisecond LLM gateway.
- ▪llmbridge A sub-millisecond, drop-in OpenAI-compatible LLM gateway in C++.
- ▪Microsecond translation overhead, dependency-free default build (TLS uses OpenSSL), p99 < 1 ms at 1,000 RPS.
- ▪What it does llmbridge is a sub-millisecond LLM gateway.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,981 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/kottos-ai/llmbridge |
| Publication time | Tue, 15 Sep 2026 13:23:59 +0000 |
| Retrieval time | 2026-09-15T13:36:52.494Z |
| Last seen | 2026-09-15T13:36:52.494Z |
| 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 | XH_6bLOXol0p · 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
llmbridge A sub-millisecond, drop-in OpenAI-compatible LLM gateway in C++. Microsecond translation overhead, dependency-free default build (TLS uses OpenSSL), p99 < 1 ms at 1,000 RPS. What it does llmbridge is a sub-millisecond LLM gateway. It sits between your app and a model provider: clients speak the OpenAI API to it, and it translates each request to the upstream provider's dialect (Anthropic, Gemini, Cohere, ...) and the response back, adding microseconds, not milliseconds. Run it as a standalone binary, or embed the translation calls directly in your own C++. It's the work gateways like LiteLLM, Bifrost, and Helicone do internally, rebuilt to High Frequency Trading (HFT) latency standards. Three properties that matter: Drop-in OpenAI-compatible.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.