# eve

> eve is a filesystem-first, Apache-2.0 framework for building durable backend AI agents that run on Vercel or self-hosted infrastructure. eve is currently in beta.

Use this file to choose the smallest relevant documentation set. Use `/sitemap.md` for the exhaustive page map and `/llms-full.txt` only for offline indexing or a large context window. For an installed project, prefer `node_modules/eve/docs/`: those docs match the installed eve version, while eve.dev documents the latest release.

eve.dev publishes framework documentation. It is not a shared API, authorization server, MCP server, or A2A server. Every deployed eve app exposes its own `/eve/v1` routes and authentication policy. External API, OpenAPI, and MCP URLs in these docs describe third-party connections or examples unless stated otherwise.

Documentation links below point directly to Markdown. Remove the `.md` suffix for the canonical HTML page.

## Introduction

- [Getting Started](https://eve.dev/docs/getting-started.md): Create a project, configure a model, understand its layout, and run it locally.

## Core Concepts

- [Execution Model and Durability](https://eve.dev/docs/concepts/execution-model-and-durability.md): Understand sessions, checkpointed steps, and parked work.
- [Sessions, Runs, and Streaming](https://eve.dev/docs/concepts/sessions-runs-and-streaming.md): Understand session IDs, NDJSON events, controls, and reconnecting.
- [Default Harness](https://eve.dev/docs/concepts/default-harness.md): Understand model context and compaction in the built-in loop.
- [Built-in Tools](https://eve.dev/docs/concepts/built-in-tools.md): Review default tools and add opt-in tools such as Workflow, glob, grep, and sleep.
- [Context Control](https://eve.dev/docs/concepts/context-control.md): Choose what the model sees and when.
- [Security Model](https://eve.dev/docs/concepts/security-model.md): Review trust boundaries, secret handling, credentials, and fail-closed behavior.

## Build

- [Agents](https://eve.dev/docs/agent-config.md): Configure the model, reasoning effort, compaction, and runtime behavior.
- [Instructions](https://eve.dev/docs/instructions.md): Write the agent's always-on system prompt.
- [Tools](https://eve.dev/docs/tools.md): Define typed actions and gate sensitive calls on human approval.
- [Connections](https://eve.dev/docs/connections.md): Connect external MCP and OpenAPI servers without exposing credentials to the model.
- [Channels](https://eve.dev/docs/channels/overview.md): Expose the agent through HTTP, Slack, Discord, and other messaging surfaces.
- [Base eve Channel](https://eve.dev/docs/channels/eve.md): Understand the HTTP API exposed by each running eve app.
- [Skills](https://eve.dev/docs/skills.md): Add procedures that the model loads on demand.
- [Sandbox](https://eve.dev/docs/sandbox.md): Configure the isolated shell, filesystem, lifecycle, and network policy.
- [Subagents](https://eve.dev/docs/subagents.md): Delegate work to copies of the root agent or declared specialists.
- [Evals](https://eve.dev/docs/evals/overview.md): Define repeatable scored checks and run them with `eve eval`.
- [Durable State](https://eve.dev/docs/concepts/state.md): Persist per-session memory across step boundaries.
- [Session Context](https://eve.dev/docs/guides/session-context.md): Use session metadata and runtime accessors in authored code.
- [Schedules](https://eve.dev/docs/schedules.md): Run prompts or handlers on a cron cadence.
- [Hooks](https://eve.dev/docs/guides/hooks.md): Subscribe to runtime stream events.
- [Dynamic Capabilities](https://eve.dev/docs/guides/dynamic-capabilities.md): Resolve models, tools, skills, subagents, and instructions at runtime.

## Integrate

- [Add Integrations](https://eve.dev/docs/install-integrations.md): Discover and add official or third-party integrations.
- [Extensions](https://eve.dev/docs/extensions.md): Package and mount reusable eve capabilities.
- [Remote Agents](https://eve.dev/docs/guides/remote-agents.md): Call another eve deployment as a subagent.
- [Agent Client Protocol (ACP)](https://eve.dev/docs/protocols/acp.md): Use local or deployed eve agents from ACP clients.
- [Universal Commerce Protocol (UCP)](https://eve.dev/docs/protocols/ucp.md): Serve a UCP profile from a custom eve channel.
- [Frontend Frameworks](https://eve.dev/docs/guides/frontend/overview.md): Build browser chat interfaces with `useEveAgent`.
- [Next.js](https://eve.dev/docs/guides/frontend/nextjs.md): Mount eve routes and use the React client in Next.js.
- [Nuxt](https://eve.dev/docs/guides/frontend/nuxt.md): Mount eve routes and use the Vue client in Nuxt.
- [SvelteKit](https://eve.dev/docs/guides/frontend/sveltekit.md): Mount eve routes and use the Svelte client in SvelteKit.
- [Client SDK](https://eve.dev/docs/guides/client/overview.md): Call an eve app from scripts, services, tests, or custom UIs.

## Operate

- [Deployment Overview](https://eve.dev/docs/guides/deployment/overview.md): Choose between Vercel and self-hosted infrastructure.
- [Deploy to Vercel](https://eve.dev/docs/guides/deployment/vercel.md): Build and deploy with Vercel Workflow and Vercel Sandbox.
- [Self-Hosting](https://eve.dev/docs/guides/deployment/self-hosting.md): Run eve as a Node service or container.
- [Authentication](https://eve.dev/docs/guides/auth-and-route-protection.md): Secure an agent's HTTP routes and establish caller identity.
- [Observability](https://eve.dev/docs/guides/instrumentation.md): Trace agents with OpenTelemetry and inspect workflow metadata.
- [Terminal UI](https://eve.dev/docs/guides/dev-tui.md): Work with a local or deployed agent from the interactive terminal UI.

## Tutorial

- [Tutorial](https://eve.dev/docs/tutorial/first-agent.md): Build an agent with tools, durable state, and an interface.

## Patterns

- [Multi-Tenant Memory](https://eve.dev/docs/patterns/multi-tenant-memory.md): Compose tenant-scoped long-term memory from dynamic instructions and tools.
- [Dynamic Scheduling](https://eve.dev/docs/patterns/dynamic-scheduling.md): Build application-managed schedules from an eve schedule and authored tools.
- [Multi-Tenant Outbound Auth](https://eve.dev/docs/patterns/multi-tenant-auth.md): Select tenant-scoped credentials for tools and connections.
- [Multi-Tenant Approvals](https://eve.dev/docs/patterns/multi-tenant-approvals.md): Apply tenant policy to authored and connection tools.

## API Reference and Discovery

- [TypeScript API Reference](https://eve.dev/docs/reference/typescript-api.md): Find public `define*` helpers, runtime context, and import paths.
- [CLI Reference](https://eve.dev/docs/reference/cli.md): Find every eve command and option.
- [Responsible Use](https://eve.dev/docs/responsible-use.md): Review deployer responsibilities and safeguards.
- [Documentation Map](https://eve.dev/sitemap.md): Browse every documentation, integration, and template page with type and summary metadata.
- [Agent Instructions](https://eve.dev/agents.md): Read operational guidance for coding agents working with eve.
- [Full Documentation Corpus](https://eve.dev/llms-full.txt): Load all docs and integration content for offline indexing or a large context window.

## Optional

- [Integrations](https://eve.dev/integrations): Browse official channels, connections, extensions, and instrumentation providers.
- [Templates](https://eve.dev/templates): Browse complete example projects and their source.
- [Official eve Skill](https://github.com/vercel/eve/blob/main/skills/eve/SKILL.md): Install or inspect the coding-agent skill; its guidance defers to version-matched bundled docs.
- [Source Repository](https://github.com/vercel/eve): Read source, releases, issues, and contribution guidance.