Showcase
Mapped in seconds, on a laptop
We pointed IngestMD at six of the most-used open-source codebases. Six languages, 67,301 files, each turned into a named map in single-digit seconds, with nothing leaving the machine.
Big or small, all in single-digit seconds
Source files per repository, with the first run measured on a laptop. The biggest, Node.js at 33,429 files, finished fastest because a tree that large groups structurally; the small ones lean on semantic clustering, which costs a little more. Either way, none took longer than about ten seconds.
Pick a codebase you already know
Clean Architecture
C#A reference .NET solution. IngestMD's namer landed on real concepts: Behaviours, the Application layer, the CreateTodoItem command and its tests.
See the map »PostgreSQL
CThe database engine, 2,574 files of C. Grouped along its source tree: the backend (910 files), the interfaces, bin, and tests.
See the map »Zulip
PythonA large Django application. The areas track the modules: Zerver and its migrations, webhooks, tests, and management, plus the web frontend.
See the map »VS Code
TypeScript11,452 TypeScript files. The editor core lands in one large area, with the Copilot and language-feature extensions broken out on their own.
See the map »Kubernetes
Go17,212 Go files into 33 areas: the staging tree, the end-to-end and integration test suites, kubeadm, and the command tree.
See the map »Node.js
JavaScript / C / C++33,429 files in under three seconds. This maps the whole tree, vendored dependencies and all: V8 (16,939 files), OpenSSL, ICU. Node's own JavaScript sits in Lib, 383 files.
See the map »Salesforce-aware
Salesforce, grouped by metadata type
IngestMD knows Salesforce. Point it at a force-app project and it groups the org by metadata type: Apex Classes, Lightning Web Components, Aura, Custom Objects, Flows, Permission Sets, and the rest. Here it is on Salesforce's own public sample apps and tooling, 6 repositories and 1,103 files, all on the laptop.
LWC Recipes
Apex / LWCSalesforce's official Lightning Web Components recipes. Mapped by metadata type: the components, custom objects, Lightning pages, and supporting Apex.
See the map »Apex Recipes
Apex / LWCSalesforce's official Apex recipes. The Apex classes, custom objects, and LWC, grouped by what they are.
See the map »DreamHouse
Apex / LWCThe DreamHouse sample app. LWC components, custom objects, and Apex, in a clean named map.
See the map »E-Bikes
Apex / LWCThe E-Bikes sample app. The same metadata-type map: components, objects, Apex.
See the map »Easy Spaces
Apex / LWC / AuraEasy Spaces, an LWC and Aura sample. Grouped by metadata type, on the laptop.
See the map »Source Deploy Retrieve
TypeScriptThe TypeScript library behind the Salesforce CLI's deploy and retrieve. Not an org, but IngestMD reads the tooling too, into 41 named areas.
See the map »Name and describe areas with your own model
The structural map is the start. Point a local model at an area and it writes a readable name and a short description, on your machine, with no cloud. Here is a real one from Clean Architecture, named by a 6 GB model running on the laptop:
CreateTodoItem This area contains the core logic for performing CRUD operations on todo lists and individual items. It implements the Command pattern, defining specific requests (CreateTodoItemCommand) and their handlers. Start with the command files in src/Application/TodoItems/Commands. All persistence relies on the injected IApplicationDbContext interface.
Honest note: this works best on focused areas, where the whole area fits the model's view. On a very large area, say a 900-file backend, the model reads a sample and describes that slice, so reach for it on coherent areas rather than whole subtrees. It is opt-in, and the model is one you run yourself.
After the map
A map is step one. Here is what you do with it.
Focused context for your assistant
Ask for a task and IngestMD assembles exactly the files needed, semantically ranked and packed. On a 2,800-file repo, one real task pulled 5 files with the right one on top.
Fits your model's window
It packs context to a token budget you set, so it fits whatever model you run, instead of a repo that overflows a context window dozens of times over.
Review the change, not the repo
From your git changes it builds a review bundle: the files you touched, their tests, and what depends on them, behind a short review prompt.
Curate and reuse
Drop areas and files into a collection, then export it as a folder, a zip, or a single file with an index. Reusable context, saved by name.
Not just code
It turns PDFs, Word docs, spreadsheets, and Confluence pages into the same clean Markdown, so the workflow covers documents and confidential folders too.
Scrubbed, reproducible, yours
Secrets are redacted before anything is bundled, the output is the same every run, and it works in your editor, the terminal, or as an MCP server your assistant talks to.
Why this matters
One tool, every stack
C#, Go, JavaScript, C, TypeScript, Python. The same command read all of them. IngestMD is not a language-specific tool.
It does not choke at scale
Node.js is 33,429 files. Kubernetes is 17,212. Both mapped on a laptop in single-digit seconds, no cloud anywhere.
Nothing left the machine
Discovery runs on-device. We measured zero non-loopback network connections during it. Your code is none of our business.
Honest note: on the largest monorepos the biggest area can stay coarse, and on flat trees the area names follow the directories. A local model renames them in seconds. Each repository page shows exactly what IngestMD produced, warts and all.
Run it on your own codebase
Free to download, with a 3-day full Pro trial. No account, no card, nothing leaves your machine.
Download IngestMD