# Laguna by Poolside

According to OpenAITools.app telemetry verified on 2026-11-11, Laguna by Poolside (poolside.ai) is an AI platform indexed under Large Language Models (LLMs) generating 73.1K monthly visits with a month-over-month traffic delta of -50.29K (-40.8%). Its primary geographic market is United States (30.5% traffic share), and it operates on a Contact for Pricing pricing model. Top competing alternatives by monthly volume include DeepSeek (372.76M visits/mo), Morph (306.96K visits/mo), Qwen 4 (Alibaba Qwen4) (35.1M visits/mo).

Open-weight agentic coding models from the Poolside foundation model lab

## Key Telemetry & Specifications

| Metric | Value |
| :--- | :--- |
| Tool Name | Laguna by Poolside |
| Handle | laguna-by-poolside |
| Status | active |
| Origin | open_source |
| Maintenance | active |
| Official Domain | poolside.ai |
| Website URL | https://poolside.ai |
| Categories | Large Language Models (LLMs), AI Agent, AI Developer Tools |
| Pricing Model | Contact for Pricing |
| Monthly Visits | 73,096 |
| MoM Traffic Change | -50,287 |
| MoM Growth Rate | -40.8% |
| Primary Market | United States |
| Market Share | 30.5% |
| Direct Visits | 37,883 |
| Organic Search Visits | — |
| Social Visits | — |
| Referral Visits | 8,126 |
| Email Visits | 539 |
| Review Score | 4.4 |
| Saved Count | 0 |
| Supported Platforms | Website |
| Billing Platforms |  |
| Attributes | Pricing: Contact for Pricing; Features: Website |
| Tags | AI software agents, Foundation models, Artificial General Intelligence, Enterprise AI, On-premise AI, Secure AI deployment, AI coding assistant |

## Overview

Laguna by Poolside is the open-weight foundation model family from Poolside, a company whose stated goal is to build software agents on the path to artificial general intelligence. The Laguna line currently spans two models: Laguna s 2.1, a 118B-parameter model with 8B active parameters and a 1M token context window that Poolside positions as frontier-class reasoning at mid-size cost, and Laguna xs 2.1, a 33B-parameter model with 3B active parameters and a 256K context window designed to be small enough to run on-device. Both are tuned for agentic coding rather than generic chat.,What makes the family notable is that the weights are published openly — you can download them on Hugging Face — while Poolside continues to develop the runtime it uses to train and operate agents through its own product experiences, currently in research preview. Poolside also works directly with government and enterprise partners, offering an on-premise and secure deployment posture for organisations that need to run frontier AI inside their own environments rather than through a third-party API.,Poolside pairs its model releases with unusually detailed public research. Its Model Factory blog series documents how the company trains, evaluates and iterates on foundation models, covering topics from GPU-to-GPU weight transfers and automated architecture ablations to reinforcement learning from code execution at scale. Other posts examine benchmark hacking and reward hacks, and hardware optimisations such as C2C activation offloading on Grace Blackwell superchips. For developer teams evaluating agentic coding models, Laguna is interesting primarily as an open, inspectable alternative with a serious research organisation behind it.

## Pricing & Plans

Poolside does not publish a public price list for Laguna. Model weights are available openly on Hugging Face at no cost, while commercial, enterprise and government engagements are arranged by contacting the company.

## Key Features & Capabilities

- **Laguna s 2.1 flagship model:** Laguna s 2.1 delivers frontier-class reasoning at mid-size cost with 118B parameters, 8B active and a 1M token context window for large codebases.
- **Laguna xs 2.1 on-device model:** Laguna xs 2.1 packs 33B parameters with 3B active and a 256K context window, small enough to run on-device while remaining useful for agentic coding.
- **Open weights on Hugging Face:** The Laguna models are published as open weights on Hugging Face, so teams can inspect, self-host and fine-tune them.
- **Agent runtime and tooling:** Poolside ships the runtime it uses to train and operate agents, exposed through product experiences currently in research preview.
- **Open research and engineering write-ups:** The company publishes a Model Factory blog series on training, evaluating and iterating on foundation models, plus research on benchmark hacking and hardware optimisation.

## Primary Use Cases

- **On-device coding assistance (Enterprise developer):** Run Laguna xs 2.1 locally so code and prompts never leave the machine, useful for regulated or air-gapped development environments.
- **Large-scale repository work (Engineering team lead):** Use the 1M token context of Laguna s 2.1 to reason over large repositories and long multi-step migration or refactoring tasks.
- **Self-host and fine-tune (ML engineer):** Download the open weights, fine-tune them on your own codebase and serve them on your own infrastructure for full control.
- **Build on published research (AI researcher):** Apply the published research on RL from code execution and benchmark evaluation when designing your own agent training pipelines.

## Strengths

- Weights for both Laguna models are published openly on Hugging Face
- A 1M token context window on Laguna s 2.1 suits large codebases and long agent trajectories
- Laguna xs 2.1 is small enough to run on-device, which helps with latency and data control
- Backed by unusually detailed public research on training, evaluation and hardware optimisation

## Limitations

- Weights are open but the full agent runtime and product experiences are still in research preview
- The larger Laguna s 2.1 model needs substantial infrastructure to serve at scale
- Documentation and enterprise/government engagement are still maturing compared with established coding assistants

## Frequently Asked Questions

### What is the Laguna model family?
Laguna is the model family from Poolside: Laguna s 2.1 (118B parameters, 8B active, 1M context) for frontier-class reasoning at mid-size cost, and Laguna xs 2.1 (33B parameters, 3B active, 256K context), designed to be small enough to run on-device.

### What are Laguna models best at?
Poolside describes Laguna s 2.1 as offering frontier-class reasoning at mid-size cost, optimized for quality, speed and efficiency, while Laguna xs 2.1 targets speed and on-device operation for agentic coding.

### Are the models open-weight?
Yes. The Laguna weights are published as open weights, and you can get them on Hugging Face. Poolside also ships the runtime it uses to train and operate agents.

### Who is Poolside?
Poolside is a foundation model company working towards AGI, with a stated focus on bringing intelligence to everywhere work gets done. Alongside model releases it publishes research, engages with government partners and offers product experiences in research preview.

### What is Laguna by Poolside's monthly traffic and growth trend?
Laguna by Poolside currently receives 73.1K monthly visits, with a month-over-month traffic change of -50.29K (-40.8% growth rate). Its primary source market is United States (30.5% share), including 37.88K direct visits/mo and — organic search visits/mo.

### Is Laguna by Poolside free? What is its pricing model?
Laguna by Poolside operates on a Contact for Pricing pricing model. Poolside does not publish a public price list for Laguna. Model weights are available openly on Hugging Face at no cost, while commercial, enterprise and government engagements are arranged by contacting the company. Supported billing and checkout platforms include: not listed.

### What are the best Laguna by Poolside alternatives in 2026?
Based on OpenAITools.app category traffic and feature fit, the top five alternatives to Laguna by Poolside are: 1. DeepSeek (372.76M visits/mo); 2. Morph (306.96K visits/mo); 3. Qwen 4 (Alibaba Qwen4) (35.1M visits/mo); 4. Gemma Open Models by Google (4.9M visits/mo); 5. BLACKBOX.AI (622.98K visits/mo).

### Which platforms and core AI capabilities does Laguna by Poolside support?
Laguna by Poolside is classified under Large Language Models (LLMs), AI Agent, AI Developer Tools, supports the following platforms: Website, and its core capability tags include: AI software agents, Foundation models, Artificial General Intelligence, Enterprise AI, On-premise AI, Secure AI deployment.

## Alternatives

| Tool Name | Monthly Visits | Pricing Model | Compare |
| :--- | :--- | :--- | :--- |
| [DeepSeek](https://openaitools.app/tool/deepseek) | 372,761,591 | Freemium | [Compare](https://openaitools.app/compare/deepseek-vs-laguna-by-poolside) |
| [Morph](https://openaitools.app/tool/morph-apply-ai-edits-to-files-fast) | 306,961 | Free Trial, Contact for Pricing | [Compare](https://openaitools.app/compare/laguna-by-poolside-vs-morph-apply-ai-edits-to-files-fast) |
| [Qwen 4 (Alibaba Qwen4)](https://openaitools.app/tool/qwen-4) | 35,101,353 | Freemium | [Compare](https://openaitools.app/compare/laguna-by-poolside-vs-qwen-4) |
| [Gemma Open Models by Google](https://openaitools.app/tool/gemma-open-models-by-google) | 4,900,914 | Freemium, Paid | [Compare](https://openaitools.app/compare/gemma-open-models-by-google-vs-laguna-by-poolside) |
| [BLACKBOX.AI](https://openaitools.app/tool/blackbox-ai-1) | 622,975 | Free Trial, Paid | [Compare](https://openaitools.app/compare/blackbox-ai-1-vs-laguna-by-poolside) |
| [Ollama](https://openaitools.app/tool/ollama) | 9,421,973 | Free, Freemium, Paid | [Compare](https://openaitools.app/compare/laguna-by-poolside-vs-ollama) |
| [Composio](https://openaitools.app/tool/composio) | 2,782,603 | Freemium, Contact for Pricing | [Compare](https://openaitools.app/compare/composio-vs-laguna-by-poolside) |
| [Gemini 4 Carbon (Gemini Carbon 4)](https://openaitools.app/tool/gemini-4-carbon) | 4,339,429 | Freemium | [Compare](https://openaitools.app/compare/gemini-4-carbon-vs-laguna-by-poolside) |
| [Qoder](https://openaitools.app/tool/qoder) | 5,145,040 | Freemium, Free Trial, Free | [Compare](https://openaitools.app/compare/laguna-by-poolside-vs-qoder) |
| [Pi Coding Agent](https://openaitools.app/tool/pi-coding-agent) | 1,929,244 | Free | [Compare](https://openaitools.app/compare/laguna-by-poolside-vs-pi-coding-agent) |
| [Google Antigravity](https://openaitools.app/tool/google-antigravity) | 16,054,109 | Freemium | [Compare](https://openaitools.app/compare/google-antigravity-vs-laguna-by-poolside) |
| [Merge](https://openaitools.app/tool/merge-dev) | 313,201 | Freemium, Contact for Pricing | [Compare](https://openaitools.app/compare/laguna-by-poolside-vs-merge-dev) |

---
Source: https://openaitools.app/tool/laguna-by-poolside