AI Agent
Clusy
Clusy is an agent-native notebook that lets you fine-tune LoRA models by simply describing what you want, automating data sourcing, architecture selection, and execution.
Clusy
What is Clusy?
Clusy is an AI-powered notebook that uses agents to automate the process of fine-tuning machine learning models, particularly LoRA adapters, from data sourcing to execution.
Clusy vs Similar AI Tools
| Pricing Model | Free, Freemium | Free | Free, Free Trial | Free, Paid |
| Free Credits | ||||
| Key Features |
|
|
|
|
| Pros |
|
|
|
|
| Cons |
|
|
|
|
| Best For |
|
|
|
|
How to use Clusy?
- 1Describe your desired outcome in plain language.
- 2Attach a dataset if you have one (optional).
- 3Clusy turns the request into a plan and dispatches sub-agents to scope it.
- 4Watch the notebook execute end-to-end.
- 5Review the fine-tuned model output.
Clusy Key Features
- Agent-native notebook for ML and data science
- Fine-tune LoRA models using plain language prompts
- End-to-end automation: data sourcing, inspection, architecture selection, compute, execution
- Concurrent follow-up tasks while a notebook runs
- Backed by Founders, Inc.
Clusy Use Cases
- Quickly fine-tune LLMs for domain-specific tasks
- Experiment with LoRA adapters without manual coding
- Automate repetitive model fine-tuning workflows
- Rapid prototyping of custom ML models
Clusy Pricing & Free Credits
Clusy currently operates on a Free, Freemium model.
Free Tier
Free Plan
$0
Basic access to try fine-tuning with limited compute.
Paid Plans
Pro Plan
Contact for Pricing
Full access with higher compute limits and priority support.
Clusy Pros & Cons
Pros
- Reduces fine-tuning complexity to a single prompt
- Automates data sourcing and pipeline decisions
- Agent-native architecture allows concurrent tasks
- Suitable for both beginners and experts
Cons
- Currently focused on LoRA fine-tuning only
- Requires some ML knowledge for optimal results
- Limited transparency into underlying agent decisions
What is Clusy best for?
- Data scientists looking to streamline fine-tuning
- ML engineers needing rapid model iteration
- Researchers exploring LoRA adapters
- Teams wanting to automate ML workflows