Skip to main content
Reliant is a cloud service. Its servers run your agents and call the AI model, and a daemon on a machine you choose does the hands-on work with your code. Everything else in Reliant is built from the handful of concepts below.

​
How the pieces fit

You use Reliant from the web app or the desktop app. When you send a message, Reliant’s servers run the agent loop: they call the model, and whenever the model wants to read a file or run a command, they send that request to your machine’s daemon and pass the result back to the model. Your repository stays on that machine. See Privacy & Security for exactly what is stored where.

​
Machine and daemon

A machine is where your agents’ tools run, and the daemon is the small program on it that carries those tools out. A machine is either your own computer (or another computer you own, such as a workstation or server) or a Reliant cloud machine that Reliant hosts for you. Cloud machines suspend after a period of inactivity, don’t bill for compute while suspended (the disk is still billed), and wake automatically when you next send a message. Manage them in Settings → Machines. Related: Machines

​
Chat

A chat is one conversation with an agent or a workflow, tied to a project. You can run many chats at once, each on its own branch or worktree, and step away while they work.

​
Project

A project is a code repository, or several, that your agents work in. A cloud machine gets its copy by cloning from GitHub, which you connect in Settings → GitHub.

​
The essentials

These three concepts are all you need to start building workflows.

​
Workflow

A workflow is a YAML file that defines a multi-step process. It specifies what steps to run, in what order, and under what conditions. The simplest workflow is the default agent loop: send your message to the LLM, execute tool calls, repeat until done — the same thing every ADE does. More interesting workflows chain multiple agents, run steps in parallel, loop until tests pass, or branch based on results. That’s what makes Reliant different. Workflows live in .reliant/workflows/ and are version-controlled with your code. Related: Workflow Overview

​
Node

A node is a single step in a workflow. Each node does one thing: There are more node kinds for routing, joining parallel branches and invoking tools directly. The Nodes reference lists every one. Nodes connect via edges that define execution flow — including conditional routing (e.g., “if tests pass, go to deploy; if they fail, go to fix”). Related: Creating Custom Workflows

​
Thread

A thread is the conversation history — the messages exchanged between you, the AI, and between agents. Threads matter most in multi-agent workflows where you control whether agents share context: Related: Threads

​
Building blocks

These concepts come into play as your workflows get more sophisticated.

​
Preset

A preset bundles parameter values into a reusable configuration: model selection, system prompt, temperature, tool access. Think of presets as agent personalities — the same workflow can behave differently with different presets. The “researcher” preset might use lower temperature with read-only tools. The “code reviewer” preset might use a specific system prompt. You can create custom presets in .reliant/presets/. Related: Presets

​
Execution mode

Controls how much autonomy the agent has: Auto (full autonomy), Manual (approve each action), or Plan (read-only exploration). You can switch modes mid-conversation. Related: Execution Modes

​
Worktree (Workspace)

A worktree is an isolated Git working directory on your machine. Reliant uses worktrees to let parallel agents work on separate branches without interfering, or to let you work on multiple branches simultaneously. In the UI, these appear as “Workspaces.” Related: Worktrees

​
Advanced

These are used in advanced workflow definitions. You don’t need them right away.

​
CEL (Common Expression Language)

The expression language used in workflow conditions and dynamic values:
Related: CEL Expressions

​
MCP (Model Context Protocol)

A standard for connecting AI assistants to external tools and data sources. Reliant includes built-in MCP servers and supports adding your own for database queries, API integrations, and custom tools. Related: MCP Servers

​
Tool

A capability the AI can use — reading files, searching code, running commands, making edits. Tools can be built-in, MCP-provided, or workflow-defined (response tools for structured output).