Official implementation of "SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching" (COLM 2025). A novel KV cache compression method that organizes cache at sentence level using semantic similarity.

Ultra-low-latency LLM gateway with microsecond caching, dynamic routing, budgets, analytics, and forecasting.

This app leverages Semantic Caching to minimize inference latency and reduce API costs by reusing semantically similar prompt responses.

Semantic caching demo with real-time streaming and a cost & sizing calculator, powered by Azure Managed Redis and Azure OpenAI.

Evaluate how a semantic cache performs on your dataset by computing key KPIs over a threshold sweep and producing plots/CSVs:

Rust Local Token Compression Proxy for coding agents, built solo for GenAI Genesis 2026. 🏆 1st Google Sustainability Hack

High-performance LLM observability and evaluation platform with automated instrumentation, stateful chat orchestration, semantic vector memory caching, and scheduled Temporal workers for cost anomaly detection.

Python library for the Semcache API

Semantic caching for LLM responses using Redis Vector DB, LangChain, and HuggingFace embeddings, parses PDFs, generates FAQs with Groq, and serves similarity-based answers without redundant LLM calls.

An intelligent gateway for Claude APIs that dynamically routes requests to the most cost-efficient model, caches responses, and escalates based on confidence signals — reducing LLM spend without sacrificing quality.

Semantic caching system using Meta Llama 3.3, Groq, FAISS, and Sentence Transformers to reduce LLM latency and API costs through meaning-based query matching.

A retrieval-augmented generation pipeline in Python with a rigorous offline evaluation harness. Chunks and embeds documents, retrieves by vector similarity, and generates grounded answers — with pluggable LLM providers (including a deterministic local fake for tests) and metrics for retrieval quality and answer faithfulness. No API key required.

Semantic memory and caching for LLM agents with classifier-validated equivalence instead of naive cosine thresholds.

A systems research platform for semantic KV-cache orchestration, topology-aware memory placement, distributed prefix reuse, and rack-scale inference memory simulation.

Node SDK for the Semcache API

LLM cost monitoring and optimization toolkit

Production-grade Java 25 Virtual Thread inference gateway bridging NVIDIA Triton → Dynamo with Earliest Deadline First (EDF) priority queuing, adaptive batching, and async shadow validation.

Semantic LLM Gateway featuring intelligent prompt routing (basic MoE), L1/L2 semantic caching (Redis + pgvector), fault-tolerant model fallbacks, and real-time streaming telemetry. Built to reduce AI inference latency and optimize API compute costs.

Machine-readable companion to the IEEE OJ-CS survey 'Semantic Caching and Response Reuse for Large Language Model Services: A Survey' (Chukkapalli, Mishra, Naik, 2026): 21-work evidence matrix, systematic-search log, proposed benchmark trace schema, stdlib-only contract validator, and CPU pilot. Code MIT; data CC-BY-4.0.

LLMOps API Gateway in Go. Optimizes GenAI workloads with Qdrant semantic caching, Redis rate-limiting, and OpenTelemetry metrics.