OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Agentmaker

Agentmaker is an open-source Python framework for building LLM agents and multi-agent systems with tools, memory, retrieval, context controls, guardrails, human-in-the-loop workflows and observability.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agentmaker — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an agent application needs composable capabilities and Python-level control over models, tools, memory, retrieval, workflows and backend integrations.

Who it is for

  • Python developers building agent applications
  • Teams composing tool-using or multi-agent workflows
  • Developers integrating memory, RAG or MCP into LLM applications

Documented uses

  • Create an LLM agent that can call typed Python functions
  • Add long-term memory and hybrid retrieval to an agent
  • Coordinate specialized agents in a multi-agent workflow
  • Connect agent tools through MCP
  • Trace and diagnose agent runs during development
Before you choose

Requirements & limits

The repository is public and identified with an MIT license. The documented installation uses PyPI and requires Python 3.12 or later.

  • Python 3.12+ is required.
  • The core package includes local hybrid retrieval and uses SQLite defaults for local storage.
  • MCP, document loading, reranking, OpenTelemetry and development UI capabilities are provided through optional extras.
  • The framework supports multiple hosted and local model connection patterns.
  • Backend components such as embeddings, vector stores, session stores and trace exporters can be replaced through interfaces.

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

Install Agentmaker and create a tool-using agent

Set up the Python package and define an agent that can call a typed function.

Before you start

  • Python 3.12 or later
  • A supported LLM provider configuration
  • The agentmaker package

Steps

  1. Install the package with pip install agentmaker.

  2. Define a typed Python function and decorate it with agentmaker's tool decorator.

  3. Create an LLMClient and pass the function in the Agent tools list.

  4. Call the agent's run method with a natural-language request.

Expected outcome

A Python agent is configured to invoke the declared function when the model determines it is needed.

Guide limitations

  • The documented example uses a model client and does not establish provider account, pricing or deployment requirements.
  • The source documents setup and invocation patterns but does not provide a compatibility guarantee for every provider or model.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

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
AgentmakerCreate an LLM agent that can call typed Python functionsCLI, Cloud, Self-hosted, ServerThe repository is public and identified with an MIT license. The documented installation uses PyPI and requires Python 3.12 or later.
AgeniteDefine typed tools with JSON Schema validation and error handling.CLI
VeldraCreate an agent with a policy, tools, skills, knowledge base and reasoning method.Self-hostedThe documented deployment is self-hosted and uses a sign-in gate after a first-run administrator account is created.
Evidence and transparency

Sources & review

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