Floneum: Build LLM workflows with drag and drop
Floneum is a graph editor for building workflows that use large language models through a drag and drop interface.
What is Floneum?
Floneum is a graph editor for language tasks. You assemble workflows by dragging and dropping nodes, and the graph can call large language models for steps such as generating text, generating structured text, creating embeddings, and searching an embedding database. Other built-in nodes cover file reads and writes, running Python, browser automation, RSS and article fetching, list and string handling, comparisons, and arithmetic. The editor ships with 41 built-in plugins and can be extended with your own. Extensions load as WebAssembly modules in a sandboxed environment, so a plugin only receives the resources it needs rather than full system access. Plugins can be written in any language that compiles to WebAssembly, including Rust, C, Java, and Go, with wrappers provided for Rust.
Who is Floneum for?
- People assembling LLM pipelines visually
- Developers writing WebAssembly plugins
- Teams automating text and data tasks
Is Floneum worth it?
A visual graph editor for LLM workflows that stands out for its sandboxed WebAssembly plugin model
Where Floneum is strong
- Drag and drop graph editor for LLM workflows
- 41 built-in plugins covering text, files, browser and math
- Sandboxed WebAssembly plugins with scoped resource access
Where it falls short
- No pricing information is published on the site
- Plugin authoring requires a language that compiles to WebAssembly
How do you get started with Floneum?
- 01Open Floneum and start a new workflow graph
- 02Drag nodes from the built-in plugin set onto the canvas and connect them
- 03Follow the guide to build your first plugin if you need custom nodes
Floneum: frequently asked questions
What does Floneum actually do?
It is a graph editor where you build workflows that use large language models by dragging and dropping nodes and connecting them.
How many plugins come with it?
The site lists 41 built-in plugins, covering embeddings, text generation, search, file access, Python execution, browser automation, lists, logic and arithmetic.
How are plugins kept safe?
Plugins load through WebAssembly in a sandboxed environment and are given access only to the resources they need, rather than full system access.
What languages can I write plugins in?
Any language that compiles to WebAssembly. The site names Rust, C, Java and Go, and notes that Rust has ergonomic wrappers.
Floneum alternatives
The closest tools in our directory, matched on category, focus areas and audience.
| Tool | Best for | Free plan | Starting price | Focus areas |
|---|---|---|---|---|
| Floneum | Visually building LLM workflows with sandboxed plugin extensions | Unknown | — | — |
| Inngest | The above tool is an AI-personalized documentation tool for Inngest's event-driven and scheduled serverless functions. | Unknown | — | — |
| Composio | Connecting AI assistants and agents to many apps | Yes | $29/mo | — |
| Verdent AI | Solo builders and small teams shipping full products | Yes | $5/mo | — |
| HumanLayer | Teams reviewing agent plans and diffs together | Yes | — | — |
| OpenHands Daytona | Teams executing untrusted AI-generated code at scale | Yes | — | — |
| Chainlit | An open-source Python library for quickly building and sharing user interfaces for your LLM applications. | Yes | Free | — |
| Mage | An open-source data pipeline tool for transforming and integrating data. | Yes | Free | — |
| Termdock | Terminal-centric AI dev environment unifying workspaces, terminals, and Git. | Yes | Free | — |
| Aide Dev | Developers tracking agentic coding research and benchmarks | Unknown | — | — |
| Blueprints | Developers starting open-source AI projects from a template | Unknown | — | — |

