Laguna M.1
AI model · Code model · Text → Code by Poolside
An early foundation model in the Laguna family for agentic coding research.
Laguna M.1 is one of the initial foundation models in the Laguna family developed by Poolside for agentic coding. It was released in research preview to demonstrate the company's progress in training and operating coding agents. The model is built to function within Poolside's specialized runtime environment, which is used for both training and agent operations. It represents an earlier iteration in the Laguna series, preceding the 2.1 versions. Laguna M.1 is intended for researchers and developers exploring the frontier of automated software engineering.
Model specs
The full spec card (context, pricing per token, modalities and more) on AntSpace. Sign up free to see the full spec card.
Overview
Laguna M.1 is one of the initial foundation models in the Laguna family developed by Poolside for agentic coding. It was released in research preview to demonstrate the company's progress in training and operating coding agents. The model is built to function within Poolside's specialized runtime environment, which is used for both training and agent operations. It represents an earlier iteration in the Laguna series, preceding the 2.1 versions. Laguna M.1 is intended for researchers and developers exploring the frontier of automated software engineering.
Model Availability
- Laguna Family Foundation: The model was released alongside Laguna XS.2 as part of the first two models in the Laguna family.
- Research Preview Access: It is available through research preview product experiences for evaluation.
- Agent Runtime Compatibility: The model is designed to work with the runtime Poolside uses to train and operate agents.
Added by AntSpace from public sources (poolside.ai).