Contact

Running EmbedCache in production or evaluating it against a managed embeddings API? Tell us about your setup — models, throughput, and cache size — and we'll get back to you. For bugs and feature requests, please open an issue on GitHub.

Name *

Email *

Company / team

What's this about? Self-hosting the REST service in production FastEmbed model selection / adding a model SQLite cache sizing, eviction, or invalidation Semantic chunking (Ollama / OpenAI) Migrating off OpenAI / Cohere / Voyage embeddings Something else

Message *

Attachment (optional, max 4 MB) — logs, a config, or a benchmark

Send Message

Prefer email? Reach us at contact@skelfresearch.com.