> For the complete documentation index, see [llms.txt](https://docs.algenta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.algenta.ai/overview.md).

# What Algenta is

Algenta is compiler-driven AI infrastructure — self-hosted building blocks for AI applications: 6,000+ deterministic functions on custom Mojo kernels, run on your own infrastructure and reached over the HTTP API, the typed SDKs, or MCP. You write the Python and TypeScript you already ship — the kernels carry the speed, and there is no new language to learn. Feed it scenarios and governed data; get results you can audit.

## Start here

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Run your first decision</strong></td><td>Install the engine, mint a key, and make your first call in minutes.</td><td><a href="/pages/bx4Gl5he2wFYtNEG4rAq">/pages/bx4Gl5he2wFYtNEG4rAq</a></td></tr></tbody></table>

## Build with Algenta

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Python SDK</strong></td><td>A typed client for the engine, plus the in-process runtime.</td><td><a href="/pages/9i6iZAg7l3UEawtf7i4b">/pages/9i6iZAg7l3UEawtf7i4b</a></td></tr><tr><td><strong>TypeScript SDK</strong></td><td>The same engine from Node and the browser, fully typed.</td><td><a href="/pages/OF5vPGpTFlUCu9cANi4Y">/pages/OF5vPGpTFlUCu9cANi4Y</a></td></tr><tr><td><strong>MCP / IDE</strong></td><td>Give Cursor or Claude Desktop direct access to the engine.</td><td><a href="/pages/9l598Hwbo4aGEvKi96R8">/pages/9l598Hwbo4aGEvKi96R8</a></td></tr></tbody></table>

## Choose an outcome

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Fix a repository</strong></td><td>Triage a repo, prove a patch, and open a pull request.</td><td><a href="/pages/Zov8aY5VMsceL76PEBiW">/pages/Zov8aY5VMsceL76PEBiW</a></td></tr><tr><td><strong>Call models &#x26; embeddings</strong></td><td>Chat, responses, embeddings, and live model discovery over BYOK keys.</td><td><a href="/pages/NQEnllpibbqN6mDWhUXj">/pages/NQEnllpibbqN6mDWhUXj</a></td></tr><tr><td><strong>Use every MCP tool</strong></td><td>All 140 engine tools, grouped and documented for your AI client.</td><td><a href="/pages/ZHmoXvADTGBmIZthNjE0">/pages/ZHmoXvADTGBmIZthNjE0</a></td></tr><tr><td><strong>Authenticate a client</strong></td><td>Mint, scope, rotate, and revoke API keys.</td><td><a href="/pages/UvGGKnKB6EqDONoxZRyB">/pages/UvGGKnKB6EqDONoxZRyB</a></td></tr></tbody></table>

## Deploy and operate

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Self-host the engine</strong></td><td>Run Algenta on your own infrastructure in one command.</td><td><a href="/pages/tWtESdNlxR5ZqT7F3czC">/pages/tWtESdNlxR5ZqT7F3czC</a></td></tr><tr><td><strong>Authenticate requests</strong></td><td>Mint, scope, and rotate API keys; bind devices.</td><td><a href="/pages/UvGGKnKB6EqDONoxZRyB">/pages/UvGGKnKB6EqDONoxZRyB</a></td></tr><tr><td><strong>Licensing</strong></td><td>Offline RS256 licenses, capacity, and product entitlements.</td><td><a href="/pages/lPXYo9UbsnGKPrpnU4FQ">/pages/lPXYo9UbsnGKPrpnU4FQ</a></td></tr></tbody></table>

## Understand and explore

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>How Algenta works</strong></td><td>The engine, runtime, decisions, and simulations — and how the surfaces fit.</td><td><a href="/pages/kcfbhqaXfwEHWksFdtMC">/pages/kcfbhqaXfwEHWksFdtMC</a></td></tr><tr><td><strong>HTTP API</strong></td><td>Base URL, conventions, the full reference, and a live explorer.</td><td><a href="/pages/7stbYFWr2YSgMNff3QuV">/pages/7stbYFWr2YSgMNff3QuV</a></td></tr><tr><td><strong>Troubleshooting</strong></td><td>Recognizable errors and the shortest fix for each.</td><td><a href="/pages/RaQHf2GXLycvWnyQW0hI">/pages/RaQHf2GXLycvWnyQW0hI</a></td></tr></tbody></table>

{% hint style="info" %}
You run the Algenta engine yourself and reach it over one universal surface — the HTTP API, the Python and TypeScript SDKs, or the MCP server. See **How Algenta works** for the model and **Self-host the engine** to run it.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.algenta.ai/overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.