Features
Structure before code.
Nodeon doesn't generate code. It produces the brief your agent builds from, MCP-native graph access, scoped prompts, spec files, dependency order.
The canvas
Four node types. That's the whole language.
Everything you plan is some arrangement of these. No syntax to learn, nothing to memorise.
Screen
A page or view. Layout, state, and navigation.
Feature
A capability. Auth, search, upload, checkout.
Logic
Rules and flow. What happens, when, and why.
Data
Models and relations. Schemas, fields, constraints.
Capabilities
Six things, done properly.
No padding. If it is on this page, it is something Nodeon is being built to do.
MCP server
Your coding agent connects to Nodeon via MCP and pulls task context on demand, node by node, in dependency order. No copy-paste, no file wrangling.
Freebuild web UI
Build and edit your mindmap on a canvas. Drag nodes, draw dependencies, refine specs. AI-assisted editing for splitting nodes, tightening vague descriptions, and reordering.
CLAUDE.md and cursor rules
Nodeon generates .md docs your agent already reads: CLAUDE.md, cursor rules and spec sheets. They stay in sync with your graph because they're derived from it.
Agent write-back
Your agent marks nodes done, adds discovered subtasks, and flags blockers. The graph is live project state, not a static plan.
Dependency-aware ordering
Nodeon figures out what to build first. Screens depend on data models. Features depend on auth. The export is sequenced so your agent doesn't have to guess.
Scoped context per task
Each node gets only the context it needs: what it depends on and what depends on it. Not the whole graph. Computed at edit time, cached for instant reads.
Why planning matters
The brief is the bottleneck.
Agents don't fail because the model is bad. They fail because the input is underspecified and out of order.
Ad-hoc prompting
- Input is structured
- A paragraph in a chat
- Agent sees dependencies
- Only what you remember to mention
- Prompts are ordered
- No. You prompt in whatever order
- Scope is defined upfront
- It isn't
- Agent can write back
- No. Chat is one way
- Agent access method
- Copy-paste into chat
Prompt templates
- Input is structured
- A copy-paste scaffold
- Agent sees dependencies
- Static. Doesn't know your project
- Prompts are ordered
- Partial. Templates have a fixed order
- Scope is defined upfront
- Template-level, not project-level
- Agent can write back
- No. Templates are static
- Agent access method
- Copy-paste into chat
Nodeon
- Input is structured
- A visual graph with typed nodes
- Agent sees dependencies
- Every node includes its connections
- Prompts are ordered
- Yes. Dependency sorted export
- Scope is defined upfront
- Scoped per node, validated across graph
- Agent can write back
- Yes. Marks done, adds subtasks, flags blockers
- Agent access method
- MCP server or file export
Stop re-prompting.
Nodeon launches October 1 at $6 a month. Get CLAUDE.md, cursor rules, and spec sheets that stay in sync with your actual plan.
Nodeon opens on October 1.
Nodeon opens on October 1.