Documentation Index on Relurpify

Getting Started

Mon, 19 Oct 2026 18:58:18 +0000

# Getting Started

Audience: new users and developers who want a working relurpish workspace. Purpose: from zero to a first completed agent turn. Prerequisites: none; this is the starting doc.

# Prerequisites

Requirement	Version / notes
Go	1.25+
Container runtime	Docker; plus gVisor `runsc` for the default `gvisor` sandbox backend (the `docker` backend needs Docker alone)
Model backend	Ollama (default, endpoint `http://localhost:11434`), LM Studio (`http://localhost:1234`), any OpenAI-compatible endpoint, or the built-in `offline` scripted model
OS	Linux or macOS (amd64 / arm64)
git	Recommended in the workspace; the diff and verify tooling works best on a clean repository

# 1. Build

From the repository root:

The Relurpish Guide

Mon, 19 Oct 2026 18:58:18 +0000

# The Relurpish Guide

Audience: anyone driving the Euclo coding agent from the terminal. Purpose: daily use of the relurpish TUI — the screen, the commands, approvals, and recipes. Prerequisites: a working workspace; see Getting started .

# Starting and stopping

relurpish chat --workspace .

Flag	Meaning
`--workspace <dir>`	Workspace root (default: current directory)
`--hitl-mode governed\|permissive`	Who answers approval requests (default: `governed`)
`--sandbox-backend gvisor\|docker`	Sandbox execution backend (default: `gvisor`)
`--offline`	Shorthand for `--inference-provider offline`
`--inference-provider <name>`	`ollama`, `lmstudio`, `offline`
`--inference-model <name>`	Backend default model; the workspace config governs agent turns
`--inference-endpoint <url>`	Provider endpoint (Ollama default: `http://localhost:11434`)

Quit with ctrl+c.

The Recipe DSL (thoughtrecipes)

Mon, 19 Oct 2026 18:58:18 +0000

# The Recipe DSL (thoughtrecipes)

Audience: authors of agent workflows. Purpose: the complete syntax and semantics of .erpe recipe files. Prerequisites: a workspace with relurpify_cfg/euclo/ (Getting started ); tool-name resolution is described in Configuration .

# What a recipe is

A recipe is a single declarative file describing one agentic workflow: how it is triggered, what tool vocabulary its steps may use, which paradigms execute, which capabilities are invoked, and how state flows between steps via capture.

The Prompt DSL

Mon, 19 Oct 2026 18:58:18 +0000

# The Prompt DSL

Audience: prompt authors and recipe authors who bind prompts. Purpose: the .prompt file format, the registry, and how the runtime resolves prompts. Prerequisites: Configuration for where prompts live; RECIPE_DSL for import prompt.

# What a prompt file is

A .prompt file is a unit of model-facing text owned by the prompt layer, not by agent code: front matter (identity, tags, variable declarations) plus a markdown body. System and user prompts live in prompt files; Go code must not embed them.

Configuration

Mon, 19 Oct 2026 18:58:18 +0000

# Configuration

Audience: users and framework developers who configure a workspace. Purpose: the complete relurpify_cfg/ reference: every file, its keys, and the validation rules. Prerequisites: Getting started ; environment variables live there, not here.

# Where configuration lives

All workspace configuration lives in relurpify_cfg/ at the workspace root. The tree is generated from an embedded template bundle; doctor materializes it once on an empty workspace and never overwrites your edits (--fix is the explicit overwrite). Treat the tree like source code: it is what the runtime loads and relurplint validates.

Architecture

Tue, 13 Oct 2026 04:19:16 +0000

# Architecture

Audience: framework developers and contributors who need to reason about the whole system. Purpose: the system shape, the rules that hold it together, and what happens during boot and a turn. Prerequisites: the glossary ; Getting started for a running workspace.

# System overview

Relurpify is a modular monolith: one Go module that compiles to a small set of local binaries. There are no microservices and no network broker; nothing listens on a socket in the default flow. The app process and a background runner process cooperate through an atomic file spool.

Testing

Tue, 13 Oct 2026 04:34:10 +0000

# Testing

Audience: contributors writing or running tests. Purpose: the three test layers, how to run each, and the supporting fixture systems (tapes, goldens, conformance). Prerequisites: Contributing↗ for gates and the coverage floor; a model backend for live layers.

# The three layers

Layer	What it exercises	Needs a model?	Entry point
Unit	One package, colocated `*_test.go`	no	`make test-unit`
Framework integration	Cross-seam behavior over real runtime state	no	`make test-integ`, `make test-scenario`
Agent end-to-end (agenttest)	The real agent against a real or replayed model	live: yes; replay: no	`dev-agent agenttest run`

make test-unit also runs the config lint and is offline-friendly with a 60-second budget. Integration tests live in testsuite/ and cover the authorization, capability, knowledge, manifest, network-boundary, and telemetry seams plus a security/redteam directory; shared builders construct workspaces, documents, policies, and envelopes.

Code of Conduct

Tue, 13 Oct 2026 04:34:50 +0000

# Code of Conduct

Audience: everyone who interacts with the project. Purpose: the standards for participation and how enforcement works. Prerequisites: none.

# Our standard

Members of the project community are expected to behave professionally and respectfully.

Examples of behavior that contributes to a positive environment:

Using welcoming and inclusive language.
Being respectful of differing viewpoints and experiences.
Gracefully accepting constructive criticism.
Focusing on what is best for the community.
Showing empathy toward other community members.

Examples of unacceptable behavior:

Search

Mon, 01 Jan 0001 00:00:00 +0000

Type to search the full documentation index. Results are ranked by title and content matches.