Portkey

PortkeySince 2025-07

Portkey is an enterprise-grade AI Gateway and LLMOps control plane designed to make production AI applications fast, reliable, and cost-efficient. By acting as a unified proxy between your applications and 250+ LLMs, Portkey handles automated provider fallbacks, load balancing, rate-limiting, and semantic caching with zero code changes. Engineering teams use Portkey to eliminate single-provider downtime risks (e.g. automatic failover from OpenAI to Anthropic during outages) while cutting inference latency and API costs by up to 40% through intelligent semantic caching.

Portkey provides comprehensive real-time observability, tracing every request, token cost, and latency percentile in a unified dashboard. The gateway supports fine-grained budget limits, user-level rate-limiting, and content moderation guardrails to protect production systems from abuse. With ultra-fast 10ms gateway overhead and SOC 2 Type II compliance, Portkey is engineered for high-throughput enterprise workloads.

LiveKit AgentsSince 2026-08

LiveKit Agents is an open-source real-time communication framework engineered to build conversational voice, video, and multimodal AI agents with sub-500ms latency. Leveraging WebRTC, it connects speech-to-text (Deepgram, Whisper), LLMs (OpenAI, Anthropic), and text-to-speech (Cartesia, ElevenLabs) in a tightly synchronized bidirectional stream. From customer service avatars to interactive language tutors and hands-free coding copilots, LiveKit Agents provides the enterprise infrastructure for real-time human-AI interaction.

Building real-time voice agents requires solving audio interruption, packet jitter, and latency stacking. LiveKit Agents abstracts these challenges with native Voice Activity Detection (VAD), turn-taking management, and edge-routed audio pipelines. Available in Python and Node.js with client SDKs across React, iOS, Android, and Flutter, LiveKit enables developers to self-host their agent backend or deploy onto LiveKit Cloud.