Documentation
Learn how to build and execute AI coding workflows with AgenticNode.
Getting Started
Build your first workflow in 4 steps
Open the Editor
Navigate to the visual editor. You will see a canvas where you can drag and drop nodes to build your workflow.
Add Nodes
Open the node palette on the left sidebar. Drag RALPIVD phase nodes, tool nodes, or AI nodes onto the canvas. Each node represents one step in your workflow.
Connect Nodes
Click and drag from one node's output handle to another node's input handle to create edges. Edges define the execution order of your workflow.
Run the Workflow
Click the Run button. The Glass Window will open, showing every step's execution in real time -- tool calls, AI responses, token usage, and timing.
Quick start with templates
Instead of building from scratch, load a pre-built template. Visit the Marketplace or append ?template=bug-fix to the editor URL to load a specific template. AgenticNode includes 17 built-in templates covering debugging, code review, testing, security, DevOps, and more.
API Keys
AgenticNode does not charge for AI model usage. You bring your own API keys and pay providers directly. Saved keys live in the encrypted server-side vault, and normal editor execution loads them server-side.
Configuring API keys
- 1.Open the editor and navigate to Settings (gear icon in the toolbar).
- 2.Enter your API key for one or more providers.
- 3.Select your default model. This model will be used for all AI agent steps unless overridden per-node.
- 4.Signed-in users can save keys to the encrypted vault. Keys are not persisted in browser storage.
Ollama (free, local models): Install Ollama on your machine, pull a model (e.g., ollama pull llama3.2), and set the Ollama endpoint in Settings (defaults to http://localhost:11434). No API key required. All computation runs on your hardware.
Available Tools
AgenticNode ships with 14 built-in tools that workflows can invoke. Non-AI tools (bash, file operations, git, grep) work without API keys. AI-dependent tools (ai_agent, RALPIVD phases) require a configured API key.
bashShellExecute shell commands in the project directory. Supports any CLI tool available on the system. Configurable working directory and timeout (default 30 seconds).
file_readFile OperationsRead the contents of a single file. Returns the content (up to 50KB), file path, and size. Used in most workflows to inspect source code before making changes.
file_writeFile OperationsWrite content to a file. Automatically creates parent directories if they do not exist. Used by implementation phases to create or modify source files.
file_readerFile OperationsRead multiple files at once by passing comma-separated paths. Returns each file's content and size, or an error if a file cannot be read. Useful for batch code inspection.
file_listFile OperationsList files and directories in a given path. Supports recursive listing up to 3 levels deep. Skips hidden files and node_modules by default. Returns up to 500 entries.
grepSearchSearch file contents using regex patterns. Returns up to 50 matching lines with file paths. Works cross-platform using native grep on Linux/macOS and findstr on Windows.
gitGitExecute any git subcommand (status, diff, log, commit, branch, etc.). Used by workflows to inspect repository state, create commits, and manage branches.
test_runnerTestingRun the project's test suite. Defaults to npm test but accepts any test command. Extended timeout of 60 seconds for larger test suites. Returns stdout, stderr, and exit code.
ai_agentAIInvoke an AI model for a specific task. Supports OpenAI (GPT-4o), Anthropic (Claude), Google (Gemini), and Ollama (local models). Uses your configured API keys. Each call is a standalone prompt with a specialized system prompt based on the agent role.
report_generatorDocumentationGenerate structured Markdown reports from data. Supports templates: bug_fix, security_audit, code_review, performance, and general. Optionally writes the report to a file.
linterCode AnalysisRun ESLint on a project or specific file. Supports auto-fix mode. Returns linting issues in JSON format when available. 60-second timeout for large codebases.
browserSearchFetch a URL and return its content. Supports GET and other HTTP methods. 15-second timeout. Returns status code, content type, and body (up to 20KB). Useful for API testing and web scraping.
github_cloneGitFetch files or directory listings from a GitHub repository via the API. Supports specific file paths, branches, and authentication with a GitHub token. No local clone needed.
github_prGitCreate a pull request on a GitHub repository. Can optionally create or update files on the branch before opening the PR. Requires a GitHub personal access token.
In addition to the 14 tools above, 7 RALPIVD phase tools (ralpivd_recognize through ralpivd_decision) are registered automatically. Each wraps an AI agent call with a phase-specific system prompt.
RALPIVD Protocol
RALPIVD is AgenticNode's 7-phase autonomous execution protocol. It structures how AI agents approach complex coding tasks, ensuring systematic analysis before implementation and verification after. The protocol can iterate -- if the Decision phase determines that requirements are not met, it loops back to an earlier phase (up to a configurable maximum, default 5 iterations).
Recognize
Understand the task requirements, constraints, and success criteria. The agent reads the task description and outputs a structured analysis of what needs to be done.
Analyze
Examine the codebase, architecture, and context. The agent identifies patterns, potential issues, dependencies, and relevant components in the existing code.
Locate
Find the specific files, functions, and code sections that need attention. The agent produces a prioritized list of locations to modify based on the analysis.
Plan
Create a detailed, step-by-step implementation plan. Includes what to change, in what order, and how to verify each step. This phase produces an actionable roadmap.
Implement
Execute the plan by writing or modifying code. The agent follows best practices, includes error handling, and maintains code style consistency with the existing codebase.
Verify
Test and validate that the implementation meets requirements. The agent checks for bugs, edge cases, and regressions. Runs tests and linting to confirm correctness.
Decision
Based on verification results, decide whether to: complete (all criteria met), iterate (go back to a previous phase for refinement), or escalate (needs human input).
Using RALPIVD in workflows:Drag RALPIVD phase nodes from the node palette onto the canvas. Connect them in order (R → A → L → P → I → V → D) or use a subset of phases for simpler tasks. The Decision node can loop back to any earlier phase by connecting its output to that phase's input, enabling iterative refinement.
Workflow Templates
AgenticNode includes 17 built-in workflow templates that cover common development tasks. Each template is a pre-configured graph of nodes and edges. Load any template into the editor with one click, then customize it or run it as-is.
Bug Fix
DebuggingCode Review
ReviewQuick Code Review
ReviewNew Project
ProjectRefactor
RefactoringTest Coverage
TestingTest Generation
TestingSecurity Audit
SecurityDependency Audit
DevOpsGenerate Docs
DocumentationPerformance Audit
PerformanceRelease Prep
DevOpsAPI Integration
IntegrationDatabase Migration
DatabaseCI/CD Pipeline
DevOpsCode Explainer
DocumentationBrowse all templates in the Marketplace. Pro and Team users can create custom templates and publish them for the community.
YAML Format
Every workflow in AgenticNode is represented as a YAML file. You can import and export workflows as YAML, edit them in any text editor, and version control them with git. The visual editor generates and parses this format automatically.
Workflow YAML structure
name: bug-fix
description: Investigate and fix a bug with tests
version: "1.0"
steps:
- id: recognize
type: ralpivd
phase: recognize
config:
task: "Understand the bug report and reproduction steps"
- id: analyze
type: ralpivd
phase: analyze
depends_on: [recognize]
config:
task: "Examine the codebase for the root cause"
- id: read_files
type: tool
tool: file_reader
depends_on: [analyze]
config:
files: "src/index.ts,src/utils.ts"
- id: implement
type: ralpivd
phase: implement
depends_on: [read_files]
config:
task: "Write the fix based on analysis"
- id: run_tests
type: tool
tool: test_runner
depends_on: [implement]
config:
test_command: "npm test"
- id: decide
type: ralpivd
phase: decision
depends_on: [run_tests]
config:
task: "Verify tests pass. If not, iterate."
on_iterate: analyzeKey fields
name-- Identifier for the workflowsteps[].type-- One ofralpivd,tool, oraisteps[].depends_on-- Array of step IDs that must complete before this step runssteps[].config-- Parameters passed to the tool or phaseon_iterate-- (Decision phase only) Which step ID to loop back to if iteration is needed
Pricing
Start free with BYOK execution and upgrade to Pro ($29/mo) or Team ($79/mo per seat) for more runs, workflow persistence, execution history, and team features.
View Pricing