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

# Release notes

> Recent Poolside inference deployment and model releases.

<Update label="July 2026" description="Deployment" tags={["Inference"]}>
  ## July 2026

  Poolside July 2026 deployment stack.
</Update>

<Update label="April 2026" description="Laguna M.1" tags={["Models"]}>
  ## Laguna M.1

  Laguna M.1 is available for agentic coding workflows that require multiple steps, tool use, and validation. It supports a 128K context window and improves Poolside's reference benchmark results compared with Malibu 2.2.

  See [Laguna M.1 release notes](/release-notes/laguna-m1).
</Update>

<Update label="April 2026" description="Laguna XS.2" tags={["Models"]}>
  ## Laguna XS.2

  Laguna XS.2 is available for faster agentic coding workflows, especially when you need strong coding performance on hardware with GPU constraints. It supports a 128K context window.

  See [Laguna XS.2 release notes](/release-notes/laguna-xs2).
</Update>

<Update label="2025" description="Malibu 2.2" tags={["Models"]}>
  ## Malibu 2.2

  Malibu 2.2 supports agentic coding workflows that require tool use across multiple turns. Use it for direct coding tasks where the model can gather context, edit files, and run validation commands.

  See [Malibu 2.2 release notes](/release-notes/malibu-2-2).
</Update>

<Update label="2025" description="Malibu 2.1" tags={["Models"]}>
  ## Malibu 2.1

  Malibu 2.1 improves code editing, instruction following, `.poolside` instruction support, long-context performance, and agent tool calling compared with Malibu 2.0.

  See [Malibu 2.1 release notes](/release-notes/malibu-2-1).
</Update>