> 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/help/changelog.md).

# Changelog

What's new in Algenta — the engine and the four ways to reach it (HTTP API, SDKs, MCP, self-hosted deployment), newest first. Each entry is dated and tagged; follow the links for the full detail.

{% hint style="info" %}
We call out behavior changes with a **Changed** tag — pin your SDK version and read these before upgrading.
{% endhint %}

## Reworked documentation and a single licensing model

A full documentation refresh on a shared, audited docs system — plus a simpler licensing model.

**New**

* A live, interactive [API explorer](/http-api/explorer.md) — set your key and base URL, then call every endpoint from the browser.
* A friendlier, help-center-style [Troubleshooting](/help/troubleshooting.md) page: a quick-fix table plus expandable cards by symptom.
* A [Connectors](/connectors/overview.md) section — overview, full reference, and per-source guides (Snowflake, BigQuery, ClickHouse, REST).
* Agentic and long-running guides: [run an agent](/guides/agent-runs.md), [async jobs](/guides/async-jobs.md), and [repository intelligence](/guides/repository-intelligence.md).
* Deploy-and-integrate guides: [BYOK](/guides/byok.md), [device binding](/guides/device-binding.md), [air-gapped](/guides/air-gapped.md), and [CI/CD](/guides/ci-cd.md).
* [Testing with Algenta](/sdks/testing.md) and deeper SDK coverage, plus operate guides for [monitoring](/deploy-and-operate/monitoring.md) and [encryption at rest](/deploy-and-operate/byok-kms.md).
* [Using these docs with AI](/help/ai-access.md) — the `llms.txt` context files, per-page Markdown, and the docs MCP server.

**Improved**

* A cleaner landing page and consistent navigation across every page.

**Changed**

* Licensing now uses a **single v2 format** — install the v2 license file Algenta provides. The legacy v1 format was retired. See [Licensing](/deploy-and-operate/licensing.md).

## Self-hosted install, privacy proof, and end-to-end checks

Everything needed to run Algenta on your own infrastructure — and to prove it stays private.

**New**

* One-command [self-hosted install](/deploy-and-operate/self-hosting.md) (Docker Compose: api + worker + Postgres + Redis + object storage).
* A **privacy report** (`GET /v1/admin/privacy-report`) that proves a deployment is cloud-free, with a 24-hour egress summary.
* Smoke and persistence proof scripts that exercise the full stack end to end (`self_host_smoke.sh`, `self_host_persistence_proof.sh`).
* The strict **air-gapped** profile (`ALGENTA_DEPLOYMENT_MODE=air_gapped`) and a telemetry-disable switch.

## The engine, four surfaces, and offline licensing

The Algenta engine and every surface that reaches it.

**New**

* The **HTTP API** under `/v1` — Monte Carlo simulation, decisions, governed data, and async jobs.
* **Python and TypeScript SDKs** (`algenta-sdk`, `AlgentaClient`) plus the in-process [`algenta-core` runtime](/sdks/python.md).
* The [MCP server](/sdks/mcp.md) (`algenta-mcp`) — governed datasets, exact queries, simulations, and agent runs exposed as tools for Cursor, Claude Desktop, and more.
* Durable, fully **offline RS256 licensing** with product entitlements and capacity caps, plus BYOK provider keys.

## Keep going

{% content-ref url="/pages/dC5uSbQw5pwjOTPP9AWU" %}
[Install](/getting-started/install.md)
{% endcontent-ref %}

{% content-ref url="/pages/CK7XoiUcZM7OhbPHhEZq" %}
[API explorer (live)](/http-api/explorer.md)
{% endcontent-ref %}


---

# 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/help/changelog.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.