FriendliAI

LM-Kit.NET is a complete local AI runtime for .NET that lets engineering teams ship AI-powered features without cloud dependencies, per-token costs, or data leaving the network. Most .NET AI integrations stop at inference. LM-Kit.NET covers the full range of capabilities production applications actually need: agentic workflows with tool calling, planning, and memory; document intelligence with OCR and structured extraction; retrieval-augmented generation with built-in vector storage; multilingual speech-to-text; vision and multimodal understanding; text analysis with classification, NER, PII extraction, and sentiment; and text generation with translation, summarization, and constrained output. Ships in one NuGet package, runs in-process with no sidecar services, and works across all major hardware acceleration backends. Drop-in replacement for Semantic Kernel through its Microsoft.Extensions.AI compatibility layer.

Wafer delivers the fastest open source LLMs for enterprise through serverless and dedicated inference built for production AI workloads. Its serverless inference gives teams access to top open models with no infrastructure, no deployment overhead, and fast APIs, including GLM-5.2-Fast for low-latency inference with EAGLE speculative decoding and a per-stream throughput SLA, GLM-5.2 as a flagship model with stronger coding and reasoning capabilities, and more. Wafer’s technology uses agents that optimize inference across the stack, identifying and enhancing bottlenecks in orchestration, algorithms, serving engines, GPU kernels, and diverse hardware. It profiles the stack to see whether latency or throughput comes from scheduling, decoding, kernels, memory pressure, or hardware fit, then tries many paths and ships the measured winner. Instead of relying on a single switch or heuristic, Wafer searches model, engine, kernel, and hardware combinations.