Frequently asked questions

Short answers to what people ask us most, grouped by topic.

Using it

What does Nehemvix do?

You paste a Git repository link and choose an AI model with your own key. Nehemvix reads the whole codebase and writes a complete guide for beginners, senior engineers and architects, with architecture diagrams, setup steps, a glossary and citations to the exact lines of code.

How is Nehemvix different from asking a chat assistant about my code?

Nehemvix reads the whole repository at one exact commit instead of the few files you paste into a chat. It then checks every file path, function and class name against the code, lists the names it could not verify, and gives the guide a grounding score.

Which repositories and languages can it read?

Any Git repository over HTTPS, on GitHub, GitLab, Bitbucket or your own server. For a private one you give a read-only access token for that run; it is used once and never stored, and secrets found in the code are removed before anything is sent to a model. Nehemvix recognises more than 40 languages and file types, checking names exactly in Python and by pattern matching in JavaScript, TypeScript, Vue, Svelte, Go, Java, Kotlin, C#, Rust, Ruby, PHP and Swift. In other languages the guide is still written, with less name checking.

How long does a guide take?

Small repositories take a minute or two; large ones longer. The estimate shows the expected time, and the job keeps running on the server if you close the tab.

Which formats can I export?

Markdown, HTML, PDF, Word and PowerPoint in your own brand colours, with diagrams as editable draw.io files.

Cost and keys

Is Nehemvix free, and which models can I use?

Yes, Nehemvix is free. You bring your own key for Google Gemini, Vertex AI, Anthropic Claude, OpenAI, AWS Bedrock, Microsoft Foundry or any OpenAI-compatible service, so you pay only your model provider and see the likely cost before anything is spent. Free models on OpenRouter are shown at $0. Setting up your provider takes a minute.

Is my API key stored?

No. Your key stays in your browser tab's memory and is sent only with the request that needs it. It is never written to a database, a log or a file, and it is gone when you close the tab.

Accuracy

How does Nehemvix avoid hallucinations?

Every file path, function and class name in a guide is checked against the real code. Sections with names that can't be found are rewritten once and kept only if they improve; anything still unverified is listed under "Names we couldn't find in the code". Each guide gets a grounding score from 0 to 100 for how closely it sticks to the code, and its citations link to the exact lines at the analysed commit.

How accurate is it?

In blind tests written by a reviewer who never saw the checker, it found 94.3% of the invented names in the first round and 83.3% in a harder second one, and it never flagged a real name. The names we plant ourselves are all caught. The method and the results are on how we check every guide.

New to the terms? Learn explains what an AI hallucination is and what prompt injection is.

Agents and connections

Can AI assistants and agents use my guides?

Yes, with read-only access. Claude or any assistant that speaks MCP can read and search your guides with a token you create, another agent can ask over A2A, and your own agents can run Nehemvix locally. Connecting an assistant and AI agents show the setup, and MCP vs A2A explains the two protocols.

Does it help with an agentic AI or LangGraph project?

Yes. It documents any repository, and agent code gets the same checks as other code. What to look for by hand is in understanding an agentic AI codebase and documenting a LangGraph project.

About AELSHA™

Who makes Nehemvix, and where does the name come from?

AELSHA™ makes Nehemvix, and the registered company is AELSHA INNOVATIONS (OPC) PRIVATE LIMITED. AELSHA™ designs and builds AI agents for companies, and Nehemvix is its free tool. The name comes from Nehemiah, who inspected a city's broken walls before rebuilding them, as the story behind the name tells.

What is AELSHA™ ASTRA?

AELSHA™ ASTRA is AELSHA™'s engineering framework for taking AI agents to production, and Nehemvix is built with it. Every guide goes through gated steps, every model and tool call is recorded, with the cost of each model call, and spending, consent and the choice of model stay with you (how ASTRA works in Nehemvix).