Group: GitHub Nacode Studios

Sort by:Popular▼

✓Popular✓Newest

The opt-in gRPC engine for Kdrant, the coroutine-first Kotlin client for the Qdrant vector database. REST remains the default; reach for this when throughput or streaming is the bottleneck.

Semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Semantic cache for LLM calls on Kotlin Multiplatform, with guards against false cache hits. Targets JVM, iOS, macOS, Linux, Windows, JS and Wasm.

Semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

A Ktor server plugin for Kmemo — the semantic cache for LLM calls on Kotlin/JVM — making a SemanticCache available to route handlers, with guards against false cache hits.

A caching ChatModel wrapper for LangChain4j, backed by Kmemo — the semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Micrometer MeterBinder for Kmemo, the semantic cache for LLM calls on Kotlin/JVM — hit rate, per-reason and per-guard miss counters, and embed/search/verify latency, in the registry your app already runs.

SLF4J CacheListener for Kmemo, the semantic cache for LLM calls on Kotlin/JVM — a structured log line per hit, miss, write and eviction, with prompt redaction on by default.

A caching Advisor for Spring AI's ChatClient, backed by Kmemo — the semantic cache for LLM calls on Kotlin/JVM, with guards against false cache hits.

Spring Boot auto-configuration for Kmemo, the semantic cache for LLM calls on Kotlin/JVM — a SemanticCache bean from your Embedder, configured under the 'kmemo' properties prefix.

In-process approximate-nearest-neighbour CacheStore for Kmemo, the semantic cache for LLM calls on Kotlin/JVM — a pure-Kotlin HNSW index that scales the default store past an exact scan, with no extra dependency.

Postgres (pgvector) CacheStore for Kmemo, the semantic cache for LLM calls on Kotlin/JVM — a durable, one-dependency semantic cache over JDBC with pgvector nearest-neighbour search.

A JVM-only Redis (RediSearch) CacheStore for Kmemo, the Kotlin Multiplatform semantic cache for LLM calls. Cross-process vector search via FT.SEARCH KNN, on a Lettuce coroutine client.