Feature Overview

Capabilities at a Glance

Feature	What It Enables
Secure Isolation	Each agent runs in its own isolated environment for security and resource containment
Automatic Scaling	RunAgent scales agents automatically under load with fast cold starts
Real-Time Streaming	Clients receive tokens as they are generated — ideal for chat UIs and interactive applications
Cross-Language Access	Call the same agent from JavaScript, Go, Python, Rust without extra infrastructure
State & Memory (coming soon)	Agents can optionally hold memory across calls for richer, contextual behavior
Security & Auth (in progress)	Agent-scoped API keys, role-based access, sandbox limits
Telemetry & Observability (future)	Logs, metrics, traces to monitor latency, errors, and usage patterns
Agent-to-Agent (A2A) (vision)	Agents can call and coordinate with other agents for complex workflows
Versioning, Rollbacks, Rate Limits (roadmap)	Control agent versions, limit usage, and revert deployments if needed

How It Works (High Level)

Write an agent - Create a Python function with entrypoint configuration

Deploy serverlessly - RunAgent handles isolation, sandboxing, and automatic scaling

Call via SDK / REST / WebSocket - Use streaming, synchronous calls, across multiple languages

Monitor & scale - Track logs, metrics, retries, and rate limits

Iterate & evolve - Deploy new versions, add memory, enable agent communication

Production-Ready Features

Instant Deployment

Deploy agents to production in seconds with runagent deploy . - no infrastructure configuration needed.

Works seamlessly with LangGraph, CrewAI, AutoGen, AG2, Letta, and custom frameworks.

Python, JavaScript/TypeScript, Go, and Rust SDKs with idiomatic APIs. C++ and C# coming soon.

WebSocket-based streaming works natively across all SDKs with minimal code changes.

Next Steps

This page is a landing overview. For detailed instructions, go to the linked pages above.