Natural-language workflow setup
Describe the outcome you want in plain language, then use the notebook as the place where the agent plans and runs the work.
Clusy
Clusy is an agent-native notebook platform for ML and data science teams. It helps users describe a goal in plain language, then plan, run, inspect, and branch notebook workflows in the cloud.
Agent-native notebooks for ML and data science
Clusy is an agent-native notebook platform for machine learning and data science. It is designed for researchers and data teams that want to describe a goal in plain language and have the notebook agent plan, write, and run the workflow in the cloud.
The platform keeps execution visible in a real notebook, so users can inspect code, edit it, re-run steps, and branch experiments when they want to compare results. The source materials also show Clusy positioning its pricing around usage-based access to models and managed cloud sandboxes, starting with a free CPU tier and scaling up to GPU-heavy plans.
Core capabilities
Agent-led execution
Clusy can source data, inspect it, choose architecture and compute, and execute the workflow end-to-end inside a notebook.
Code-level review and control
Every step stays visible in a real notebook, so you can inspect, edit, and re-run the code rather than treating the output as a black box.
Notebook branching
Branch notebooks to fork experiments and compare alternative runs side by side.
Managed cloud compute
Run notebooks on managed cloud sandboxes with CPU or GPU options that scale from entry-level to top-end hardware.
Model tier access
Choose from the Auto model on Free, open models on Plus, and frontier models such as Claude and GPT on higher tiers.
Where Clusy fits
Model fine-tuning experiments
Use Clusy to set up a fine-tuning workflow from a simple prompt, then let the notebook agent source data, choose compute, and run the job without starting from a blank notebook.
Iterative research work
Queue a follow-up while a notebook is still running, then review the executed cells and results in the same notebook once the run completes.
Experiment comparison
Branch a notebook to fork two approaches and compare outputs side by side when you want to test alternative modeling choices or parameters.
Data-connected analysis
Connect to a warehouse or upload files when you need to work on live or local data inside the notebook rather than copying data into a separate tool.
Pros and Cons
Pros
- Supports a plain-language workflow that the agent turns into notebook execution.
- Keeps work visible in a real notebook, which preserves code-level control.
- Includes branching for comparing experiments side by side.
- Offers managed cloud sandboxes with both CPU and GPU options.
- Provides a free entry point, with paid tiers that expand model and compute access.
Cons
- The public pages do not provide a complete integration list beyond examples such as Hugging Face, Databricks, and Snowflake.
- The source materials do not spell out all limits, collaboration features, or export options in detail.
FAQ
What is Clusy?
Clusy is an agent-native notebook platform for machine learning and data science. You describe the outcome you want in plain language, and Clusy plans the work, writes and runs notebook cells on cloud CPUs or GPUs, and returns results you can inspect, edit, and re-run.
How is Clusy different from Jupyter or Google Colab?
Traditional notebooks start with a blank editor. Clusy adds an agent that can source and inspect data, select architecture and compute, execute the workflow end-to-end, and support branching so you can compare experiments side by side.
Which AI models can I use in Clusy?
The Free plan includes the Auto model for fast, low-cost everyday work. Plus adds open models such as DeepSeek and Kimi, while Pro and Max unlock every model, including Anthropic Claude and OpenAI GPT.
Can Clusy connect to my own data?
Yes. You can upload files, pull public datasets from sources like Hugging Face, or connect to Databricks or Snowflake and work against live tables from the notebook.
Is there a free plan?
Yes. Clusy offers a free plan with the Auto model on a CPU sandbox and no credit card required. Paid plans start at $30/month, with higher tiers adding more models, GPUs, and usage allowances.
Quick Facts
- Category
- Agent-native notebook platform
- Primary users
- Researchers and data teams
- Platform
- Cloud notebook environment
- Core workflow
- Describe a goal, let the agent plan and run the notebook, then inspect and edit the results
- Data sources mentioned
- Uploads, public datasets such as Hugging Face, Databricks, Snowflake
- Pricing
- Free plan available; paid plans start at $30/month
Clusy Alternativen
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
SonOf
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.
Ghost
Ghost ist ein terminalbasierter KI-Assistent für Chats, Code-Generierung und Aufgaben direkt in der Kommandozeile. Mit kostenlosen Modellen, Linux, macOS und Windows. Open Source.