> ## 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's new

> Dated changes to Helix, the mutagent CLI and the platform, newest first.

Run `helix --version` and `mutagent --version` to see which builds you have. Inside Helix, `/changelog`
prints the notes for the recent Helix releases.

<Update label="2026-09-29" description="Web app Configuration, new LLM providers, GitHub and Slack">
  **Web app**

  * A new **Configuration** page holds the workspace's **LLM Providers**, **Environments** and
    **Integrations**, plus the shared **Sandbox Providers** list. LLM providers moved here from
    Settings.
  * Signing up asks only for your organization's name; Mutagent creates a workspace named
    **Default workspace** in it. The next step, **Connect GitHub**, can be skipped.

  **LLM providers**

  * **OpenRouter** (`openrouter`) and **Z.AI (Coding Plan)** (`zai-coding-plan`) can be added to a
    workspace. The default Z.AI model is `glm-5.3`.

  **Cloud sessions, GitHub and Slack**

  * Cloud sessions, managed agents, and GitHub and Slack runs are in early access: not every account is let in yet.
  * A cloud session stopped after 15 minutes of inactivity wakes up when you send it a message. The
    web app shows **Waking up…**, then delivers your message, and the conversation continues in the
    same thread.
  * Connect GitHub and Slack from **Configuration › Integrations**. A Slack thread keeps one session
    for up to 1 hour; mention the app in a new message to start another.

  **Trace sources**

  * Langfuse and OpenObserve can be connected to a workspace with `mutagent integrations sources add`.
</Update>

<Update label="2026-09-23" description="Helix 0.0.34-m0, CLI workspaces">
  **Helix 0.0.34-m0**

  * `/cloud` checks whether cloud sandboxes are enabled for your account before it starts anything.
    If they are not, it says so in one line and leaves your local session as it was.
  * `/cloud status` shows whether cloud sandboxes are enabled for your account, or tells you to run
    `mutagent login` when your sign-in has expired.

  **Helix 0.0.33-m0**

  * `/cloud` runs your turns in a cloud sandbox while you keep the local session.
    `/cloud stop` removes the sandbox and reports `removing`, then `removed`.
  * A session is driven by a goal with done-when criteria. The goal cannot be completed until every
    criterion has evidence.
  * `helix -p "/diagnose …"`, and any other Helix command run headless, runs a real turn and prints
    its reply.
  * After the curl install, `helix` works in the same terminal when `~/.local/bin` or `~/bin` is on
    your `PATH`.
  * Web search settings with Exa and Firecrawl; Anthropic and xAI models on Google Vertex AI from
    `/login`; plan mode ends with Approve, Keep or Discard.

  **mutagent CLI: organizations and workspaces**

  * `mutagent login` stores an organization key that works in every workspace you belong to in that
    organization, for 30 days.
  * `mutagent workspaces use <name>` selects the workspace every later command works in.
    `--workspace <name|id>` overrides it for one command, then `MUTAGENT_WORKSPACE_ID`.
  * `--org <id|slug|name>` checks the key's organization; a mismatch exits 1 and sends nothing.
    `mutagent login --org <slug>` signs in to another organization.
  * See [Accounts, organizations and workspaces](/get-started/accounts).
</Update>

<Update label="2026-09-18" description="Session modes">
  * Cloud sessions have two modes, named the same in the CLI, the SDK and the API: **headless** (one
    task, the reply printed) and **interactive** (a session you keep sending to).
</Update>

<Update label="2026-09-17" description="Helix 0.0.32-m0, install, managed agents">
  **Helix 0.0.32-m0**

  * A sub-agent can be messaged for as long as it exists, including after it finishes; a message to a
    finished sub-agent resumes it.
  * Sub-agents can be named when spawned, and `SendMessage`, `StopAgent` and `ListAgents` also reach
    other Helix sessions on the same machine.

  **Install**

  * `mutagent install helix` installs the standalone `helix` binary, the same one the curl installer
    puts in `~/.mutagent/bin`. The earlier plug-in install into Claude Code and Codex is retired; see
    [Standalone binary](/helix/install/standalone).

  **Managed agents**

  * `mutagent agent deploy <agent.md>` checks, uploads and activates an `agent.md` folder, and
    `mutagent helix agent @<slug> -p "<task>"` runs it in a cloud sandbox. `agent check` and
    `agent pack` work locally, without a cloud sandbox.
</Update>

<Update label="2026-09-12" description="Environments, provider mirror">
  * **Environments**: `mutagent env set` stores the variables and secrets an agent's tools need, per
    workspace. Secrets are write-only: they are never printed back.
  * `mutagent providers mirror` copies the LLM provider keys you signed in with in Helix into the
    current workspace, when you ask it to.
</Update>

<Update label="2026-09-02" description="Evaluator and Diagnostics">
  * The Evaluate and Diagnose stages ship inside Helix only. The separate npm installs for them are
    retired; install [Helix](/helix/install/standalone) instead.
</Update>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.