> ## Documentation Index > Fetch the complete documentation index at: https://docs.openrtc.tech/llms.txt > Use this file to discover all available pages before exploring further. # OpenRTC > livekit-agents on steroids. Host all your agents in one worker, with hot reload, live introspection, per-tenant isolation, and zero-downtime deploys. Your Agent code does not change. **OpenRTC is livekit-agents with the operational parts filled in.** Keep writing standard `livekit.agents.Agent` subclasses. Register them on one `AgentPool` instead of one worker per agent, and host them all in a single process: shared prewarm loads once, every call still gets its own `AgentSession`, and you never inherit an OpenRTC base class. The payoff is the stuff livekit-agents leaves to you: **50+ sessions per worker, hot reload, live introspection, per-tenant isolation, and zero-downtime deploys.** See the before/after: what you delete, what you keep, and what you gain. Start here if you already run livekit-agents. Install OpenRTC and run two agents through one worker in a few minutes. ## What changes (and what doesn't) | | livekit-agents | OpenRTC | | --------------------- | ----------------------------- | -------------------------------------- | | **Your `Agent` code** | standard subclasses | **unchanged** | | **Workers** | one process per agent | one worker hosts every agent | | **Prewarm** | reloads per process | loaded once, shared | | **Scaling** | \~3 GB per idle worker | 50+ concurrent sessions in one process | | **Shipping a change** | restart, drop in-flight calls | hot reload, no dropped calls | ## What you get on top Register any number of standard `Agent` subclasses on one pool. No base class, no rewrite: your tools and node hooks stay exactly as written. Sessions run as `asyncio` tasks in one loop, 50+ concurrent, sharing one Silero VAD and turn detector. Process isolation is one flag away. Every call resolves to one agent by job metadata, room metadata, or room-name prefix. Precedence is explicit and a typo never falls through silently. Edit an agent file and live calls swap to the new code on their next turn, with zero dropped audio. A bad save rolls back on its own. `openrtc top` gives an htop-style view of per-session memory, CPU, and event-loop blocks inside the shared worker. Give every client its own provider keys, session caps, and blast-radius circuit breaker, all in one pool. One noisy tenant never touches the others. Blue-green drain: the new version takes new calls while the old drains its in-flight calls to hangup, then exits. No live call is ever dropped. The universal entrypoint, coroutine density, and shared prewarm under the hood, when you want the details. OpenRTC owns the **runtime** lane: density, routing, hot reload, introspection, per-tenant isolation, and deploys. For cost, pipeline latency, and quality metrics, it emits `agent_name` and `metadata["tenant"]` on every session for voicegateway to consume, and does not duplicate that lane.