Free browser calculators and an error debugger for PyTorch tensor shapes, plus a $29 one-time local toolkit called Tensor Preflight.
Freemium
SelfMachines
No-code, modular workflow builder for designing, training and serving AI and data-processing pipelines.
What is SelfMachines?
SelfMachines is a no-code workflow builder for creating, training, managing and serving information retrieval and processing pipelines tailored to a business's logic. Its blog describes a ladder of seven abstraction levels: layers (about 50 types drawn from frameworks such as TensorFlow and PyTorch), blocks, stages, graphs, metagraphs called nodes, agents and systems. Each level is assembled from graphs of the one below, and users can define their own module types and reuse them in other pipelines. Systems are run on data through jobs, and a tutorial shows an image classifier agent built on the CIFAR dataset. The company is in a beta phase and invites early customers to apply for discounted access to early features while helping shape custom ones. No pricing is published.
Use cases
- Build neural network pipelines without code
- Train and serve custom AI agents
- Create information retrieval workflows
- Define reusable custom module types
- Compose multi-agent systems
- Train an image classifier agent
Who it's for
Why use SelfMachines
- Lets you assemble deep learning building blocks visually instead of writing framework code.
- Reusable custom module types mean your own components can sit alongside the built-in ones.
- The layered design lets you start with simple layers and work up to multi-agent systems.
- Early beta customers can get discounted access and influence future customized features.
SelfMachines features
- No-code visual workflow builder
- About 50 layer types, learnable and non-learnable
- Seven abstraction levels from layer to system
- User-defined module types saved to a personal library
- Built-in graphs such as transformer encoder and ResNet feature extractor
- Agents composed as graphs of metagraphs
- System graphs that combine agents, API callers and data sources
- Jobs to execute systems on data
How to get started with SelfMachines
- Apply to join the beta program to get access to the platform.
- Assemble layers into blocks, stages and graphs in the web interface, or create your own module types.
- Combine graphs into agents and agents into systems for more complex tasks.
- Run a system on your data using a job, then train and serve the result.
SelfMachines limitations
- Currently in a beta phase for early customers
- Pricing is not published
- Documentation is mainly blog posts and a tutorial
SelfMachines pricing
We couldn't confirm pricing on the official site. Check selfmachines.com for current prices.
Prices can change and may vary by country or exclude tax. Check the official pricing page.
SelfMachines alternatives
The main SelfMachines alternatives listed on Debuly are Langflow, Flowise, AutoGen, Haystack, IBM watsonx.ai and OpenHands Software Agent SDK. The table compares pricing and platforms; order is A–Z.
| Tool | Pricing | Starting price | Platforms |
|---|---|---|---|
| SelfMachines | Pricing unknown | — | Web |
| AutoGen | Open source | — | API, CLI |
| Flowise | Open source | — | Web, API, CLI, Self-hosted |
| Haystack | Open source | — | Python, Self-hosted |
| IBM watsonx.ai | Freemium | — | Web, API, SDK |
| Langflow | Open source | — | Web, Windows, macOS, Linux |
| OpenHands Software Agent SDK | Open source | — | Python, TypeScript, API, Docker |
AutoGen
Microsoft's MIT-licensed Python and .NET framework for multi-agent AI apps, now archived; new projects are pointed to Microsoft Agent Framework.
Open sourceVisit AutoGen (official site)
Flowise
Open-source visual builder for AI agents, chatbots and RAG workflows, self-hosted or on Flowise Cloud.
Open sourceVisit Flowise (official site)
Haystack
Open-source Python framework from deepset for building RAG pipelines, AI agents and multimodal apps from modular components.
Open sourceVisit Haystack (official site)
IBM watsonx.ai
IBM's AI development studio for building generative AI apps and agents with foundation models, prompt tools, and machine learning, billed by usage.
Langflow
Open-source low-code visual builder for AI agents, RAG apps and MCP servers, with Python customization and an API for every flow.
Open sourceVisit Langflow (official site)
OpenHands Software Agent SDK
Python, TypeScript and REST SDK for building coding agents that run locally or in Docker and Kubernetes workspaces
SelfMachines FAQ
How much does SelfMachines cost?
No prices are published. The company is accepting applications from early beta customers, who are offered discounts on early features.
Is there a free plan for SelfMachines?
No free plan is listed. Apply through the beta page to ask about early access terms.
What can I build with SelfMachines?
You can build models from layers, blocks, stages and graphs, create agents and systems, and run them on data with jobs. A tutorial demonstrates an image classifier agent.
Can I add my own components to SelfMachines?
Yes. You can create custom module types, add them to your personal library and use them as building components in higher-level abstractions or other pipelines.
Who is SelfMachines for?
It targets teams that want to design and operate machine learning pipelines and agents visually, such as ML engineers, data scientists and AI product teams.
What are alternatives to SelfMachines?
Visual workflow and ML builders you could compare include KNIME, Dataiku, Langflow and Flowise.
Sources & verification
Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.
| Source | Type | Accessed |
|---|---|---|
| selfmachines.com/ | official | |
| selfmachines.com/beta_phase/ | official | |
| selfmachines.com/blogs | official |
Image credits
- Logo: none collected yet, so a monogram is shown.
- Cover: none collected yet, so a generated tile is shown.
Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.
More in Developer platforms 4
All developer platforms toolsAI cloud with OpenAI-compatible serverless inference for open-source models and on-demand or reserved GPU instances.
PaidGateway and control layer for LLM, MCP and agent traffic, with usage metering, billing and cost limits built in.
Contact salesPython, TypeScript and REST SDK for building coding agents that run locally or in Docker and Kubernetes workspaces
Open source
