Understand unfamiliar code
Find your way through older projects, even when the documentation is missing.
“Where does an incoming request reach the persistence layer?”
Private AI. Local by default.
Understand your codebase faster.
Keep your code private.
AndesCode helps developers understand unfamiliar code, see how features work, and prepare changes. Run AI on your own computer and review the code behind each answer.
Current: repository intelligence · Experimental: local coding agent and document knowledge
Example question
“How does a command-line option become a typed value?”
decorators.pycore.pytypes.py
Follow the flow. Inspect the source.
Illustrative workflow · not a live product response
Your repository. Your compute. Your control.
Built for code you need to keep private.
Proprietary systemsClient code under NDARestricted environmentsGet answers from your own code
Understand the code.
Know what to change.
Ask questions about your codebase. AndesCode helps you find relevant files, follow how features work, and check answers against your source code.
Find connected code
See where a library is used and which files may depend on it.
“Where is this library declared, and which modules use it?”
Prepare your next change
Follow a feature across files. Find the code and tests you should review before making a change.
“How does a failed upload reach the retry path?”
Evidence before confidence
See the code behind
each answer.
AndesCode points you toward relevant source code. You can check the evidence yourself. AI can miss important context, so an engineer should review each answer.
Inspect the evidence
Find the files that support an answer. Open them and check the details.
Keep the task in context
Break large problems into smaller questions to help the tool find the right code.
Make changes reviewable
An experimental command-line agent can suggest or make controlled edits when enabled. Always review changes and test them yourself.
What you can use today
Start with your codebase.
Explore what comes next.
The desktop app focuses on understanding code. Other capabilities are in testing or planned for later.
Available now: understand code
Ask questions about one repository and find code to inspect before you make a change.
In testing: code edits and documents
Separate command-line tools are being tested for controlled code edits and questions about local text documents. They are not ready for team-wide production use.
Planned: shared private AI
Future work may add team access, connections to business tools, and approved actions. These features are not available today.
Your code stays in your control
Run AI on
your computer.
In local mode, your code and AI questions stay on your computer during use.
Review deployment boundariesPrepare once. Run locally.
Initial setup downloads dependencies and model files. Once provisioned, LOCAL inference can operate offline.
Remote inference is an explicit choice.
Optional private-server inference sends your question, selected source chunks, and metadata to the server you configure. Review that data flow before enabling it.
Validate against your own requirements.
No formal compliance certification is claimed. Network restrictions, deployment controls, and security approval belong in the evaluation.
What to know before you start
Local mode can work offline after setup. If you choose remote AI, your question and selected code are sent to the server you configure. The experimental agent can run project commands, so use it only in an environment you trust. AndesCode does not claim a security certification.
See whether AndesCode fits
Start with one project.
See the results.
We can discuss a small, paid trial with one approved codebase. Start with questions your developers already know how to answer. Agree on the scope, price, and success criteria before starting.
Choose your questions
Pick a repository and a few questions that matter to your team.
Try it on your computer
Run a read-only trial and compare its answers with your source code.
Review the results
Check what worked, what did not, and whether a wider trial makes sense.
What you receive: a short report with answers, source references, limitations, and next steps.
Before we talk
A few practical details.
What hardware should we plan for?
Apple Silicon with 32 GB or more of unified memory is the recommended starting point. Plan for 20–30 GB of free disk space and Python 3.10+. We confirm the model and hardware fit before agreeing to an evaluation. Windows and Linux with NVIDIA GPUs are documented paths; platform suitability should be checked for your setup.
Will it automatically change our code?
The initial evaluation is read-only. An experimental local coding-agent CLI already exists and is under active development. With editing and validation explicitly enabled, it can inspect source, apply controlled edits, attempt allowed checks, and inspect the final diff. It is separate from the desktop chat interface; reliable real-task performance remains to be established.
How can we evaluate it?
We can discuss a bounded, read-only evaluation using public or otherwise authorized code, subject to hardware and readiness checks. The AndesCode source repository is private and is not included in standard evaluations. No installation or usage rights are granted by an enquiry. Read the public technical overview.
Is this a hosted service or IDE plugin?
AndesCode is a standalone desktop app. There is no official hosted SaaS or current IDE plugin. Private remote inference is optional and must be explicitly configured and operated by your team.
Let’s see if it fits
Have a code question?
Let's talk.
Tell us what language you use and what you want to understand. We can discuss whether AndesCode is a good fit. Do not send private code or passwords by email.
Discuss an evaluation andescode@datalogic.techOpens your email app. You can also write directly to the address above.
Built in the Andes.
Designed for your environment.
Andrés Garrido
Independent software engineer · Chile