See what RunAgent supports — from sandbox microVM deployment to streaming SDKs, security, observability, and agent workflows.
Start Small, Scale Big
Capabilities at a Glance
| Feature | What It Enables |
|---|---|
| Sandboxed MicroVMs | Each agent runs in isolation (Firecracker-based), for security and containment |
| Autoscaling & Concurrency | RunAgent scales agents automatically under load, handles cold starts |
| Streaming Token Responses | Clients receive tokens as they are generated — ideal for chat UIs |
| Cross-Language Access | Call the same agent from JS, Go, Python, Rust without extra infra |
| State & Memory (coming soon) | Agents can optionally hold memory across calls for richer behavior |
| Security & Auth (in progress) | Agent-scoped API keys, role scopes, sandbox limits |
| Telemetry & Observability (future) | Logs, metrics, traces to monitor latency, errors, usage |
| Agent-to-Agent (A2A) (vision) | Agents can call and coordinate with other agents |
| Versioning, Rollbacks, Rate Limits (roadmap) | Control agent versions, limit usage, revert if needed |
How It Works (High Level)
- Write an agent (one Python function with entrypoint configuration)
- Deploy to microVMs — RunAgent handles sandboxing + autoscaling
- Call via SDK / REST / WS — streaming, sync calls, multi-language
- Monitor & scale — logs, metrics, retries, rate limits
- Iterate & evolve — new versions, memory, agent communication
Next Steps
- 👉 Start with Deploy your first agent
- 🧭 Explore Frameworks & How-tos
- 📖 Dive into SDK / API Reference
- 🔒 Or read about Architecture & Concepts
This page is a landing overview. For detailed instructions, go to the linked pages above.
Still have a question?
- Join our Discord Community
- Email us: [email protected]
- Follow us on X
- New here? Sign up