OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Infrastructure & Serving

Llmaker

Llmaker is an open-source Go command-line platform for provisioning and operating self-hosted language models and supporting services in Docker. It networks models, vector databases, embeddings, caching, observability and retrieval or agent components so they can be managed as a stack.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Llmaker — OpenViST project profile in AI Infrastructure & Serving.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Llmaker when building a self-hosted AI application requires coordinating a model with Docker-based retrieval and supporting services, or when you want terminal-based management of those components as one fleet.

Who it is for

  • Developers assembling local retrieval-augmented chatbots or document Q&A systems.
  • Teams that want to manage self-hosted models and their supporting services together.
  • Builders creating FAQ assistants or recommendation engines on local infrastructure.

Documented uses

  • Provision a model together with vector search, embeddings, caching or observability services.
  • Scaffold or apply a declarative stack configuration.
  • Ingest documents and query an agent for grounded answers with sources.
  • Inspect service status, logs and resource use across a managed fleet.
  • Run a local model with an OpenAI-compatible endpoint.
Before you choose

Requirements & limits

The README requires Docker and lists Linux and macOS for prebuilt binaries. It also documents installation through Go or from source. The project is labeled alpha.

  • Docker is a required dependency.
  • The agent image must be built locally for stacks that include the agent; the assistant template is documented as not needing it.
  • The README identifies the project as alpha.
  • The CLI is written in Go; the agent uses Python and FastAPI, with LangGraph among its documented components.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Provision and query a document Q&A stack

Set up a retrieval-augmented stack and submit a document and question to its agent.

Before you start

  • Docker
  • Llmaker installed
  • A locally buildable agent image for stacks that include the agent
  • A document to ingest

Steps

  1. Run llmaker stack init rag to generate a stack configuration, or use the documented rag template.

  2. Build the agent image with the command below.

    Documented command
    make image-agent

  3. Apply the configuration with llmaker apply -f stack.yaml and inspect the provisioned services with llmaker ls.

  4. Resolve the agent URL from llmaker service ls --json, then submit the document to /api/ingest and a question to /api/chat.

Expected outcome

A provisioned retrieval stack whose agent accepts document ingestion and returns answers with sources.

Guide limitations

  • The agent image must be built locally for stacks that include the agent.
  • The README describes setup and request examples; this guide does not represent an independent execution test.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
LlmakerProvision a model together with vector search, embeddings, caching or observability services.CLI, Docker, Self-hostedThe README requires Docker and lists Linux and macOS for prebuilt binaries. It also documents installation through Go or from source. The project is labeled alpha.
Weaviate — weaviateStore application objects alongside vectors and retrieve similar items.Cloud, Self-hosted, ServerThe repository describes Weaviate as open source and lists Docker, Kubernetes and Weaviate Cloud deployment options.
Qdrant Multi Node ClusterDeploy Qdrant across multiple nodes using Docker Compose.Docker, Self-hosted, ServerThe repository is public and specifies an MIT license. The documented deployment requires Docker, Docker Compose, Python 3.8+, and Git.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
raiyanyahya/llmaker · Official homepage title · retained in its source language
How we review sourcesSuggest a correction