# Everstack

> Everstack unifies an AI gateway, agent runtime, isolated sandboxes, evaluations, memory, MCP, and OpenTelemetry observability in one self-hosted platform.

Use one OpenAI-compatible control plane to route every model, run stateful agents, execute code in isolated sandboxes, evaluate behavior, and trace the entire system.

## Core products

- [AI Gateway](https://everstack.ai/gateway): Route AI traffic across providers with one OpenAI-compatible API, configurable fallback, semantic caching, rate limits, tenant isolation, and OpenTelemetry traces.
- [Agent Runtime](https://everstack.ai/agents): Define durable AI agents as code and run them on self-hosted Everstack infrastructure with sandboxes, memory, tools, approvals, and observability.
- [Sandboxes](https://everstack.ai/sandboxes): Run code, agents, preview services, and jobs in isolated Everstack sandboxes with shell, files, lifecycle controls, signed previews, resource limits, and network po…
- [Workflows](https://everstack.ai/workflows): Combine durable tool-using AI agents with versioned visual workflows, parallel branches, triggers, retries, memory, and human approval gates.
- [Observability](https://everstack.ai/observability): Trace gateway requests, agent sessions, tools, sandboxes, evaluations, latency, token usage, and cost through OpenTelemetry-native observability.
- [Evaluations](https://everstack.ai/evaluations): Evaluate AI outputs with built-in metrics, LLM-as-judge scoring, sandboxed code scorers, datasets, baselines, scheduling, CI gates, and human review.
- [Guardrails](https://everstack.ai/guardrails): Protect AI inputs and outputs with runtime checks for prompt injection, sensitive data, unsafe content, jailbreak markers, dangerous code, and traceable policy viol…
- [EVS Sites](https://everstack.ai/sites): Publish browser-ready agent output as private, versioned EVS Sites with immutable releases, controlled access, activation, and rollback.

## Documentation

- [Documentation](https://docs.everstack.ai/getting-started): Install, configure, and run Everstack -- the unified AI infrastructure platform.
- [Installation](https://docs.everstack.ai/getting-started/installation): Sign up for Everstack Cloud and install the CLI.
- [Quickstart](https://docs.everstack.ai/getting-started/quickstart): Configure providers and send your first request.
- [Architecture](https://docs.everstack.ai/getting-started/architecture): How Everstack is designed, components, data flow, and the decisions behind them.
- [AI Gateway guide](https://docs.everstack.ai/getting-started/gateway/overview): The AI Gateway -- a unified, OpenAI-compatible proxy for 200+ LLM models.
- [Agent Runtime guide](https://docs.everstack.ai/getting-started/agents/overview): Autonomous AI agents with tool use, memory, and human-in-the-loop approval.
- [Sandbox guide](https://docs.everstack.ai/getting-started/sandboxes/overview): Isolated runtimes for code, jobs, apps, agents, and automations.
- [Vector memory guide](https://docs.everstack.ai/getting-started/memory/overview): Vector memory for RAG, semantic search, and long-term agent memory.
- [MCP guide](https://docs.everstack.ai/getting-started/mcp/overview): Model Context Protocol server registration and federated tool calling.
- [API reference](https://docs.everstack.ai/api-reference): Everstack REST API reference, OpenAI-compatible gateway and platform APIs.

## Explore

- [Model catalog](https://everstack.ai/models): Browse AI models across OpenAI, Anthropic, Google, AWS Bedrock, Azure, and more. Compare context windows, capabilities, modalities, and token pricing.
- [Compatibility](https://everstack.ai/compatibility): See how Everstack connects your SDKs, agent frameworks, AI model providers, tools, channels, webhooks, MCP servers, and OpenTelemetry pipelines.
- [Pricing](https://everstack.ai/pricing): Compare Everstack plans for AI gateway routing, observability, agents, hosted browser automation, static site publishing, and isolated sandbox workloads.
- [Everstack CLI](https://everstack.ai/cli): Install the Everstack CLI to manage LLM gateway routing, agents, isolated sandboxes, and observability from one automation-friendly command surface.
- [Comparisons](https://everstack.ai/comparison): Compare Everstack with AI gateway and infrastructure platforms across routing, agent runtimes, sandboxes, observability, deployment ownership, and governance.
- [Changelog](https://everstack.ai/changelog): Follow Everstack releases across AI gateway routing, agents, sandboxes, evaluations, observability, and platform operations.
- [Roadmap](https://everstack.ai/roadmap): See what Everstack has shipped, what is in progress, and what is coming next across agents, sandboxes, evaluations, and observability.
- [Blog](https://everstack.ai/blog): Read Everstack product updates, engineering deep dives, and practical guidance for operating production AI infrastructure.

## Plans and pricing

### Plan prices

| Plan | Monthly | Yearly | Seats included | Best for |
| --- | --- | --- | --- | --- |
| Starter | $0 | $0 | 1 seat | Try Everstack and ship your first workload |
| Build | $20 | $200 | 3 seats included | For building production AI applications |
| Scale | $100 | $1,000 | 10 seats included | For scaling production workloads |
| Enterprise | Custom | Custom | Unlimited seats | For large organizations |

Additional seats:

- Build: $15 per month or $150 per year per additional seat beyond 3 included.
- Scale: $39 per month or $390 per year per additional seat beyond 10 included.

Annual billing: 2 months free with annual billing.

### Sandbox compute prices

Sandboxes bill per second on fixed machine sizes. Each sandbox includes 20 GiB of disk.

| Sandbox size | vCPU | Memory | Price per hour |
| --- | --- | --- | --- |
| Nano | 0.5 | 0.5 GiB | $0.0333 |
| Small | 1 | 1 GiB | $0.0666 |
| Medium | 2 | 2 GiB | $0.1332 |
| Large | 4 | 4 GiB | $0.2664 |
| XL | 8 | 8 GiB | $0.5328 |

Every new organization receives a one-time $5 sandbox compute credit with no payment method required.

### Metered infrastructure prices

| Meter | Price | Note |
| --- | --- | --- |
| Hosted browser session | $0.01 per browser hour | Billed per second with a 1 minute minimum |
| Site edge requests | $2.00 per 1M requests | Charged after the included monthly allowance |
| Site data transfer | $0.10 per GB | Response bytes delivered to visitors |
| Site deployment storage | $0.03 per GB-month | All retained immutable versions |

Model-provider inference is billed separately from plan and metered infrastructure prices.

Full plan allowances, feature matrix, and pricing FAQ: https://everstack.ai/pricing

## Developer resources

- [Everstack OpenAPI index](https://everstack.ai/openapi.json): Machine-readable index of every published Everstack OpenAPI document.
- [Everstack API reference](https://docs.everstack.ai/api-reference): Human-readable reference for the same operations.
- [Everstack API keys and authentication](https://docs.everstack.ai/getting-started/quickstart): Create an API key and send it in the x-everstack-api-key header.
- [Everstack CLI](https://everstack.ai/cli): Install the evs command line tool to script Everstack from a terminal.
- [Everstack MCP server](https://docs.everstack.ai/getting-started/mcp/everstack-mcp-server): Connect an MCP client to Everstack tools.
- [Everstack API catalog](https://everstack.ai/.well-known/api-catalog): Well-known link set describing the API surface.
- [Everstack source code](https://github.com/everstacklabs/everstack): Apache 2.0 Community Edition.

## LLM resources

- [Complete public corpus](https://everstack.ai/llms-full.txt): Full published text from the Everstack landing site and documentation.
- [Website](https://everstack.ai): Canonical Everstack product site.
- [Documentation](https://docs.everstack.ai): Canonical setup and operator documentation.

This file is intentionally compact and contains no repository source code. Use the linked pages for current details and llms-full.txt only when complete public context is required.