SEIF
Start here

For integrators

You are wiring SEIF into another system — an editor, an agent framework, or a provenance pipeline. Connect over MCP and the CLI, then verify.

You want SEIF inside another system: an IDE, an agent framework, or a pipeline that needs verifiable provenance. SEIF exposes the same protocol two ways — a CLI for scripts and a Model Context Protocol (MCP) server for AI tools.

1. Connect over MCP

The MCP server gives any compatible AI tool the SEIF toolset — grounding, memory, governance, provenance — as first-class tools. This is the fastest way to make an agent SEIF-aware.

→ MCP setup

2. Wire it into your AI tool

Connect SEIF to the editor or agent you already use, so sessions ground, remember, and sign without leaving the tool.

→ AI tool integration

3. Emit verifiable provenance

Every artifact your system produces can carry a signed, timestamped Evidence record, addressable by a public URL and verifiable by anyone.

→ Provenance & governance

4. Drive it from scripts

Anything the tools expose, the CLI exposes too. Build SEIF into CI, hooks, or any automation.

→ CLI workflow

The CLI, MCP, and API references are generated directly from the binary and are always current.

For operators

You run SEIF workspaces day to day. The path from initializing a workspace to building durable memory, governing work in cycles, and keeping machines in sync.

What is SEIF

The mental model behind SEIF — workspaces, modules, evidence, and operating conduct.

On this page

1. Connect over MCP2. Wire it into your AI tool3. Emit verifiable provenance4. Drive it from scripts