Question 1

What is Everstack?

Accepted Answer

Everstack is an open-source AI infrastructure platform for building and operating production AI applications. It combines an OpenAI-compatible AI gateway, agent runtime, isolated sandboxes, memory, MCP, workflows, evaluations, guardrails, and observability in one control plane.

Question 2

Is Everstack an AI gateway or an agent platform?

Accepted Answer

It is both, plus the infrastructure around them. The gateway handles multi-provider routing, fallbacks, caching, rate limits, and keys. The runtime adds stateful agents, tools, memory, workflows, isolated execution, evaluations, and end-to-end traces, so teams do not have to join separate platforms themselves.

Question 3

Can I self-host Everstack?

Accepted Answer

Yes. Everstack can run on infrastructure you control with Docker or Kubernetes. Self-hosting keeps provider credentials, prompts, responses, policies, and telemetry inside your environment while preserving the same APIs and operational model.

Question 4

Which AI providers are supported?

Accepted Answer

Everstack supports OpenAI, Anthropic, Google Gemini, Azure OpenAI, AWS Bedrock, Cohere, Mistral, DeepSeek, Hugging Face, Qwen, MiniMax, Moonshot, Ollama, OpenRouter, and other OpenAI-compatible endpoints.

Question 5

How does Everstack isolate agent code execution?

Accepted Answer

Agent tasks run inside managed sandbox boundaries with explicit filesystem, network, resource, and lifecycle controls. Everstack keeps the runtime behind that stable sandbox contract so applications do not depend on the underlying isolation technology.

Question 6

How do evaluations and observability work together?

Accepted Answer

Everstack records model calls, tool use, sandbox execution, latency, tokens, cost, and outcomes as connected traces. Those production traces can feed datasets, LLM-as-judge scorers, code scorers, human review queues, and regression checks, closing the loop between what shipped and what should improve next.

Question 7

Does Everstack lock me into a framework or model provider?

Accepted Answer

No. Everstack exposes OpenAI-compatible APIs, native TypeScript, Python, and Go SDKs, Connect RPC services, and OpenTelemetry data. It works with common agent frameworks and model providers, so applications can change models or orchestration code without replacing the infrastructure layer.

Build, run, and govern AI on infrastructure you own.

One control plane from model request to production outcome

Production AI infrastructure without the platform tax

Designed for AI engineers and platform teams