Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.alquimia.ai/llms.txt

Use this file to discover all available pages before exploring further.

Alquimia is a platform for running AI assistants on your infrastructure. Studio (this app) is where you design and operate agents. InsightHub is the companion product for organizing documents and exploring them in conversation — still using agents and the same execution stack behind the scenes. The Runtime is that shared engine; see Runtime

The ecosystem at a glance

ComponentRole
StudioAgent builder — this app. Design, configure, and manage agents; review agent health in the dashboards here.
RuntimeWhere agents run — configuration, inference, tools, and channels.
InsightHubKnowledge exploration — topics, documents, and streaming chat grounded in your content.
TwydKnowledge service for ingestion and search that backs document-grounded experiences.

The agent lifecycle

When you build an agent in Studio, here’s what happens end-to-end:
Studio          →   Registry API       →    Runtime
(you configure)     (config stored)         (agent executes)
  1. You configure an agent in Studio (model, system prompt, tools, memory, and the rest).
  2. Studio saves the configuration to the Registry API — the central store for all agent configs.
  3. When a user sends a message, the Runtime loads that config and runs the assistant.
  4. Telemetry from the run feeds your observability setup; Studio’s dashboards are the usual place to review agent health and usage.

How Studio fits in

Think of Studio as where you design and operate agents, and the Runtime as where they come to life when someone actually talks to them. InsightHub sits alongside Studio for teams that work mainly from documents rather than only from pre-built channel integrations. Studio is your home for:
  • Designing agents — what you set in the UI becomes the configuration the Runtime executes.
  • Workspace operations — models, integrations, embeddings, sentinels, and boundaries in one place.
  • Operational visibility — metrics and health for the agents you own.
When you use Try Me, Studio is your console; the conversation itself is powered by the Runtime, so what you see matches what end users get on the same stack.
You rarely need to call the Runtime or Registry APIs by hand; Studio talks to them for you. When something misbehaves, it helps to know which layer owns what so you know where to look next.

Next steps

Ecosystem Overview

See every service, its port, and what it does.

Installation

Get the stack running locally with Docker Compose.