LiveKit Agents vs Anthropic SDK (TypeScript)
Side-by-side trajectory, velocity, and editorial themes.
LiveKit Agents added Answering Machine Detection — voice agents are becoming a serious telephony runtime.
LiveKit Agents is releasing roughly twice a week along the 1.5.x line, accumulating telephony-grade primitives around its voice loop. The headline is Answering Machine Detection in 1.5.9 — an LLM-classified detector for what kind of endpoint an outbound call hit. Surrounding work is split between reliability (barge-in cooldown, interruption guards, preemptive-generation tuning, observability retries) and provider breadth (Perplexity Responses, Soniox, Speechmatics, Cerebras, xAI, Rime WebSocket TTS). The mcp_servers parameter was also deprecated on Agent and AgentSession.
The product is converging on a real contact-center runtime, not just a realtime meeting agent. AMD, warm transfer, DTMF handling, recording retries, and avatar join/playback metrics are the feature surface phone deployments demand. The provider plugin universe keeps widening; LiveKit positions itself as the neutral broker between voice models and the actual network. Internal cleanups (mcp_servers deprecation, instruction parts, AvatarSession base class) suggest a tidying pass before a 1.6 cut.
Expect more telephony primitives — supervisor barge-in, richer DTMF flows, call-recording controls — and a unified MCP configuration surface across Agent and Session as the mcp_servers deprecation lands fully.
Anthropic ships a dedicated AWS client for Claude Platform on AWS, alongside steady Managed Agents expansion.
The TypeScript SDK family is on a weekly bump cadence (0.94 → 0.97 in two weeks) with two structural moves underneath. First, a new [email protected] introduces an AWS client for Claude Platform on AWS — a distinct package from the existing bedrock-sdk. Second, Managed Agents (CMA) is broadening visibly: webhooks, multiagents and outcomes types, vault validation, self-hosted sandboxes with helpers, a BetaManagedAgentsSearchResultBlock, and cache diagnostics beta in successive releases.
Anthropic is splitting its AWS distribution into two channels — Bedrock for the model API, and a separate Claude Platform on AWS surface that the new aws-sdk implies will bundle Managed Agents and related platform features. Managed Agents itself is hardening from a single-agent harness into a multi-agent orchestration product with webhooks, outcomes, and self-hosted execution. The combination reads as Anthropic moving from model API to deployable agent platform.
Expect a public Claude Platform on AWS announcement (likely an AWS Marketplace listing or product page) once [email protected] stabilizes. Managed Agents will keep adding orchestration surface — likely persistent memory hooks, audit endpoints, or agent-to-agent messaging primitives.
See more alternatives to LiveKit Agents →
See more alternatives to Anthropic SDK (TypeScript) →