eve weekly downloads statistics

eve

eve is a filesystem-first framework for durable backend agents on Vercel.

You author an agent as a directory on disk. The directory is the contract — markdown for the parts a human should read like a spec, TypeScript for the parts that benefit from real types and runtime behavior.

The framework is called eve. The published npm package is eve. The CLI binary is eve.

Preview Terms and Safeguards

eve is currently a preview and subject to the Vercel beta terms; the framework, APIs, documentation, and behavior may change before general availability.

As the deployer, it is your responsibility to ensure your agent complies with applicable laws.

You are responsible for configuring approval policies, tool restrictions, connection scopes, route/session authorization, sandbox controls, telemetry exports, and other safeguards appropriate for your use case.

Before using eve with non-public, sensitive, regulated, or production data, review which default tools, custom tools, MCP tools, shell/file/web tools, connected services, subagents, schedules, and external actions are available to the agent.

Require human approval or other safeguards for sensitive, irreversible, regulated, financial, healthcare, employment, housing, legal, safety-impacting, user-impacting, or external side-effecting actions.

Unless you configure stricter controls, eve agents may operate with permissive settings, including tool execution without human approval where approval is omitted and sandbox network egress that is not deny-all. Do not rely on model behavior alone to prevent sensitive or irreversible actions.

What eve Prioritizes

• Markdown-first authoring for instructions and procedures • TypeScript where typed runtime behavior matters • Durable message runs and follow-up turns • Inspectable compiled artifacts under .eve/ • Per-agent sandbox with optional authored overrides • A stable HTTP protocol built around immutable session IDs • A runtime model that keeps channels, harnesses, and workflow execution separate

Authored Directory

Authoring Helpers

Every authored directory has a typed helper. Import each from the matching subpath:

| Helper | Subpath | Authored Location |

| defineAgent(...) | eve | agent.ts, subagents//agent.ts | | defineInstructions(...) | eve/instructions | instructions.ts (or instructions.md) | | defineTool(...), defineDynamic(...), disableTool(...) | eve/tools | tools/.ts | | bash, readFile, writeFile, and other provided definitions | eve/tools/ | tools/.ts | | defineSkill(...) | eve/skills | skills/.ts (or skills/.md) | | defineHook(...) | eve/hooks | hooks/.ts | | defineChannel(...), POST, GET | eve/channels | channels/.ts | | eveChannel(...), slackChannel(...), vercelOidc(...) | eve/channels/eve, /slack, /auth | reused from channels/.ts | | defineSandbox(...) | eve/sandbox | sandbox.ts (or sandbox/sandbox.ts) | | defineSchedule(...) | eve/schedules | schedules/.ts (or schedules/.md) | | defineEval(...), defineEvalConfig(...) | eve/evals | evals/.eval.ts, evals/evals.config.ts |

Runtime accessors live on the subpath that owns the concern:

• getSession() — current session, turn, auth, parent lineage (eve/context) • getSandbox() — live sandbox handle for the current agent (eve/sandbox) • getContext(key), requireContext(key), hasContext(key), setContext(key), ensureContext(key, factory) — unified context helpers (eve/context)

The complete API reference, including types and lower-level runtime primitives, is in the TypeScript API Reference.

Tiny Example

agent/instructions.md

agent/tools/get_weather.ts

agent/agent.ts

Quick Start

eve init writes a new agent with eve's default model. Pass `--model openai/gpt-5.5 to choose another AI Gateway model, --reasoning high` to set a reasoning effort, or --channel-web-nextjs to add the Web Chat application. It installs dependencies, initializes Git, and opens the terminal UI in an interactive human terminal. Coding-agent invocations return setup instructions instead. Targeting an existing project directory (eve init .) adds the agent files and missing dependencies instead. Initialization does not create a Vercel project, configure browser sign-in, or deploy the agent.

To add Web Chat with Sign in with Vercel, run these commands from the agent's directory:

Choose a hosting layout, then Sign in with Vercel. The terminal UI's /add channel picker offers the same setup. A team owner or a custom role with App and environment permissions can provision access for members of the project's team. Setup configures production and preview credentials; run npx eve deploy to publish. Local development works without browser sign-in. See the Web Chat setup guide for recovery steps.

CLI commands:

• eve (including npx eve) — initialize the current directory, or start development in an eve project • eve init — create a new agent • eve info — discovery results and compiled artifacts • eve build — compile .eve/ and build the host output • eve start — serve the built .output/ app • eve dev — start the local runtime and REPL • eve add channel/web — add Web Chat and configure browser authentication • eve set [--model ] [--reasoning ] — change root model settings • eve extension init — create a new extension package • eve extension build — build an extension package

Deploying

eve is built to be durable. The runtime is Nitro + Workflows. Read the deployment guide for the deployment path, environment variables, and configuration.

Read Next

These files ship inside the installed package at node_modules/eve/docs/:

• Full docs index — recommended entry point • Getting Started — install, scaffold, and run locally • Project Layout — every authored directory in depth • agent.ts — agent config reference • Automatic Model Selection — choose an agent model for each request • TypeScript API Reference — complete define* and runtime helper reference • Vercel Deployment — deploy to production…

Description from the npm listing.