Laguna XS.2

Laguna XS.2

Poolside
+
+

Related Products

  • LTX
    182 Ratings
    Visit Website
  • JetBrains Junie
    12 Ratings
    Visit Website
  • Gemini Enterprise Agent Platform
    1,161 Ratings
    Visit Website
  • Planview AdaptiveWork
    718 Ratings
    Visit Website
  • Creatio
    589 Ratings
    Visit Website
  • Interfacing Integrated Management System (IMS)
    66 Ratings
    Visit Website
  • Google AI Studio
    41 Ratings
    Visit Website
  • Retool
    598 Ratings
    Visit Website
  • Runpod
    230 Ratings
    Visit Website
  • Google Cloud BigQuery
    2,027 Ratings
    Visit Website

About

Laguna XS.2 is Poolside’s open-weight agentic coding model, built as the lightest and fastest model in the Laguna family. It is a 33B total-parameter Mixture of Experts model with 3B activated parameters, trained completely in-house on 30T tokens. As Poolside’s newest generation model open to the community, Laguna XS.2 is a second-generation architecture and the company’s first open-weight model, built on the lessons learned from training Laguna M.1 across synthetic data and reinforcement learning. The model is designed for agentic coding workflows, where it can code, act, iterate quickly, and perform best inside Poolside’s coding agent. Laguna XS.2 is positioned as a strong model for rapid agentic iteration, especially for developers and teams that need a compact, efficient coding model rather than a heavier frontier system. It is released under an Apache 2.0 license, allowing the community to evaluate, fine-tune, quantize, serve, and build on the weights.

About

Overmind is a model training and deployment platform for teams building AI agents. It ingests production traces through OpenTelemetry and creates datasets from trace data, file uploads, and connectors for Langfuse, LangSmith, Braintrust, and Galileo. Teams can inspect agent context and runtime behavior, prepare and score datasets, evaluate prompts and models against their own examples, and optimize agent behavior through scored changes. The platform supports LoRA and full fine-tuning of open-weight models, benchmarking with configured evaluators, and deployment through an OpenAI-compatible endpoint; trained weights can also be downloaded. Users can work in the hosted console or run the platform on their own infrastructure with Docker Compose. It is designed for AI engineering and product teams operating agents in production that want to test, improve, or specialize models using their own data.

Platforms Supported

Windows Supported
Mac Supported
Linux Supported
Cloud Not Supported
On-Premises Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

AI developers and engineering teams that need efficient AI models for agentic coding, long-horizon software development, and rapid coding iterations

Audience

AI product teams and ML engineers running LLM agents in production who want a cheaper specialised model they own

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Not Supported

API

Offers API Supported

API

Offers API Supported

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version Supported
Free Trial Not Supported

Pricing

Free
Free plan: $0/month, with fair-use OTLP ingest, up to 10 optimization runs, 5 evaluation runs, 2 training jobs, and 2 deployment jobs per month, plus 5 projects and a $40 one-time credit. Pro: $120/month with higher limits, unlimited projects, optimization runs, evaluation runs, training jobs, and deployment jobs. Enterprise pricing is custom.
Free Version Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Not Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Company Information

Poolside
Founded: 2023
United States
www.poolside.ai/models

Company Information

Overmind
Founded: 2025
United Kingdom
www.overmindlab.ai

Alternatives

GLM-5.2

GLM-5.2

Z.ai

Alternatives

No Alternatives
Kimi K2.7 Code

Kimi K2.7 Code

Moonshot AI
Laguna M.1

Laguna M.1

Poolside
Poolside

Poolside

Poolside.ai

Categories

AI Coding Models Supported
AI Models Supported

Categories

AI Fine-Tuning Supported

Integrations

Claude Code Supported
OpenAI Codex Supported
Agent Client Protocol (ACP) Supported
Braintrust Not Supported
Cursor Not Supported
Galileo Not Supported
Hermes Agent Supported
Hugging Face Supported
Kilo Code Supported
Langfuse Not Supported
Model Context Protocol (MCP) Not Supported
Nous Portal Supported
Ollama Supported
OpenClaw Supported
OpenCode Supported
OpenRouter Supported
Poolside Supported
Roo Code Supported
Visual Studio Supported
Zed Supported

Integrations

Claude Code Supported
OpenAI Codex Supported
Agent Client Protocol (ACP) Not Supported
Braintrust Supported
Cursor Supported
Galileo Supported
Hermes Agent Not Supported
Hugging Face Not Supported
Kilo Code Not Supported
Langfuse Supported
Model Context Protocol (MCP) Supported
Nous Portal Not Supported
Ollama Not Supported
OpenClaw Not Supported
OpenCode Not Supported
OpenRouter Not Supported
Poolside Not Supported
Roo Code Not Supported
Visual Studio Not Supported
Zed Not Supported
Claim Laguna XS.2 and update features and information
Claim Laguna XS.2 and update features and information
Claim Overmind and update features and information
Claim Overmind and update features and information