Features
Reinforcement fine-tuning with GRPO and DAPO algorithms
Multi-turn tool training for AI agents
Hands-on deployment support for full post-training workflow
Continuous improvement via automated retraining loops
Integration with evaluation solutions for performance monitoring
Real-time data ingestion and model updates as fast as every hour
Support for LoRA adapters in RL training
Fused logprobs for reduced memory in long-context RL
Concurrent training of thousands of LoRA adapters
Megatron-LM and SGLang integration for large model training
Full model ownership: serve with Osmosis or export to self-host
Data extraction with schema precision
Code generation fine-tuning for domain-specific languages
Testing and validation tools for training data overlap optimization
Laguna XS.2 model (33B params, 3B active, on-device)
Laguna M.1 model (225B params, 23B active, via API)
256K context length for multi-step reasoning
Multi-agent orchestration with planning and tool use
Sandboxed agent execution environments
Developer surfaces: agents, TUI, IDE extensions, binaries
Custom foundation models deployed on-prem or in VPC
Data connectors to repos, databases, data warehouses
Role-based access control for humans and agents
Executive-grade governance and auditability
On-prem, VPC, and workstation deployment (defense only)
Forward Deployed Research Engineers embed with teams
Real-time observability with end-to-end traces
Air-gapped network support
Open-weight model weights available
