> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mutagent.io/llms.txt
> Use this file to discover all available pages before exploring further.

# What is Helix

> The Agentic Development Lifecycle, as its own coding agent or inside yours — spec, build, evaluate, diagnose, optimize.

<Note>
  **Research Preview.** Helix is early and moving fast — run `helix --version` for the build you
  have. The loop runs end to end today; expect the command surface to change.
</Note>

Helix is the **Agentic Development Lifecycle (ADLC)**, run by a coding agent. It takes an agent
through one loop — **spec → build → evaluate → diagnose → optimize** — and holds every change for
your approval, so nothing ships until it has been re-checked against your real traces.

```mermaid theme={null}
flowchart LR
  S["① Spec"] --> B["② Build"] --> E["③ Evaluate"] --> D["④ Diagnose"] --> O["⑤ Optimize"]
  O -. "you approve" .-> B
  classDef s fill:#140d22,stroke:#7E47D7,color:#ede7f8;
  class S,B,E,D,O s;
```

## Point it at an agent

Point Helix at an agent — one you're building, or one already running — and it drives the loop: it
writes a spec, builds, scores the result against your [real traces](/helix/traces), root-causes what
failed, and applies a fix. Every change waits for your approval; nothing lands until you say so. See
[how the loop works](/helix/how-the-loop-works) for the full mechanism.

<Info>
  **No traces yet?** Building something new is fine — start at **Spec** and **Build**. Evaluate and
  Diagnose start working once you ship and your agent begins logging runs.
</Info>

## Two ways to run it

Helix comes in two forms. Both run the same loop.

<Card title="Standalone binary" icon="terminal" href="/helix/install/standalone">
  **Proprietary.** A single binary with the whole system inside — no Node, no npm, no checkout. Helix
  *is* the coding agent, with the sub-agent crew, the trace viewer and the agent and Prime modes
  built in.
</Card>

```bash theme={null}
curl -fsSL https://install.mutagent.io/helix | bash
helix
```

<Card title="Plugin" icon="puzzle-piece" href="/helix/install/plugin">
  Installs Helix into **Claude Code** or **Codex** as a plugin, through the `mutagent` CLI — the
  editor you already use.
</Card>

```bash theme={null}
mutagent login
mutagent install helix
```

<Tip>
  Not sure which? Take the **binary** — it is the full product and needs nothing else installed.
  Take the **Plugin** if you want Helix inside a Claude Code or Codex session you already live in.
  Then run [your first loop](/helix/install/first-loop).
</Tip>

## Drive it in plain English

Helix is a natural-language orchestrator. Describe what you want — *"Evaluate the Refund Processing agent
against last quarter's disputes and show the pass rate per policy rule"* — and it routes to the stage
that owns the job. Nothing runs until you ask, and nothing lands until you approve.

The binary also runs without the orchestrator when you want less:

| You type                                     | You get                                                                                                |
| -------------------------------------------- | ------------------------------------------------------------------------------------------------------ |
| `helix`                                      | The orchestrator — dashboard, lifecycle stages, a crew of specialist agents.                           |
| `helix agent` · `helix agent --name <agent>` | A plain coding agent, or one specific agent definition, with no orchestrator.                          |
| `helix --prime`                              | Prime — the RLM-based agent loop: the model writes and runs code against your repository, recursively. |

See [Three ways to run Helix](/helix/modes) for what each gives you and what to type.