Onboard turns deep Understand analysis data into guided project walkthroughs, architecture explanations, and practical starting points for real engineering work.
Runs fully offline
Self-hosted
No source-code upload required
Why teams trust Onboard
Onboard generates project guidance from Understand's deep statis-analyis data, not just AI context windows.
30+ Years
of code analysis experience
20,000+
developers trust SciTools
Understand- powered
projects grounded in deep static-analysis data
TRUSTED BY ENGINEERING TEAMS WORLDWIDE
Interactive browser demo
Launch a live sample project in your browser and see how Onboard turns Understand analysis data into guided project explanations, architecture context, and onboarding tasks.
Try asking:
Onboard works best on your laptop or monitor
No install
No setup
Runs entirely in your browser
How Onboard Works
Not a chatbot layer on top of source files. Onboard builds a project model first, then uses that model to guide engineers through architecture, workflows, starting points, and deeper code exploration.
AI ANALYSIS
Ask questions in plain language and get answers grounded in real files, relationships, and call paths from the project model.
No token limits
Fully offline
Use your favorite model
QUESTION
Ask like a new engineer
Ask what something does, where a workflow starts, or which files matter first.
Project Model
Grounded by the project model
Answers use relationships, references, metrics, and call paths extracted by Understand.
Evidence
See what the answer is based on
Surface files, symbols, relationships, and reports that support the explanation.
Action
Go deeper when needed
Jump from the AI explanation into navigation, reports, call trees, or specific code areas.
Onboard turns the project model into practical documentation engineers can use to understand architecture, workflows, important files, and where to start.
Help new team members understand the major pieces before they start reading source files.
Explain request paths, subsystems, and common flows in a format the team can share.
Use the documentation page to point engineers toward important files, entry points, and follow-up exploration.
Use generated documentation pages to explain how the codebase is structured, what engineers should understand first, and where they should go next.
Use generated reports to identify important areas of the codebase, review risk signals, and understand where complexity, impact, and project knowledge concentrate.
Onboard is designed for teams that need code intelligence available across the organization while keeping analysis, source, and project context inside their own environment.
Run in restricted or air-gapped workflows where external code upload is not acceptable.
Give engineers access to the same project model instead of isolated local experiments.
Deploy with practical hardware expectations rather than a large cloud or GPU cluster.
Every plan includes unlimited users and unlimited lines of code. Pricing is based on the number of projects your team wants to onboard.
Onboard is built for teams that need code intelligence without sending private source code outside their own environment.
Onboard is designed for local AI. The model, prompts, code context, and answers can run inside the customer environment instead of relying on an external AI service.
No. Onboard is self-hosted, and source code does not need to be uploaded to SciTools or to a third-party cloud service.
Yes. Onboard is meant to be shared by the engineering team, so developers can work from the same project model rather than isolated local notes or one-off AI sessions.
Pricing is based on the number of projects covered. Every tier includes unlimited users and unlimited lines of code.
Onboard uses SciTools Understand analysis data, including relationships, references, dependencies, call paths, metrics, and project structure. It is not limited to searching raw source files.
Yes. Onboard is free for qualifying open source projects and educational use. Eligibility can be reviewed with SciTools.
Recommended specs are 1GB SSD, RTX 3080, and i9.
Try the live demo, schedule a walkthrough with SciTools, or ask about pricing for your project count.
See Onboard explain and navigate a real codebase before setting anything up.
Launch demoMeet with SciTools to discuss your codebase, deployment requirements, and local AI setup.
Book a meetingGet help matching your team to the right project-based pricing tier.
Request pricing
