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

Codefuse Muagent

Codefuse Muagent is a Python framework for building LLM agents driven by eventic knowledge graphs. It combines knowledge-graph-based workflow structures with multi-agent coordination, function calling, code interpretation, memory and tool-management capabilities.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Codefuse Muagent — 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 workflow benefits from explicit knowledge-graph structure, tool nodes, and a path for human-guided execution. The repository offers a Python SDK route and a separate Docker Compose setup for EKG services.

Who it is for

  • Developers building LLM agent applications around knowledge graphs and structured procedures.
  • Teams modelling workflows that involve tool selection, memory, or human participation.

Documented uses

  • Model agent workflows with intention, workflow, tool and character nodes.
  • Coordinate multi-agent tasks, including parallel EKG execution.
  • Import and parse text or diagram documents as inputs to knowledge-graph design.
  • Register and organize tools for agent function calling.
  • Debug and monitor knowledge-graph execution paths.
Before you choose

Requirements & limits

The repository is public and provides a Python SDK installation command and Docker Compose setup instructions.

  • The framework’s central model is an eventic knowledge graph with intention, workflow, tool and character node types.
  • SDK code-answer examples require LLM and embedding-model configuration.
  • The EKG service quick start uses Docker Compose and specifies a local interface at https://localhost:8000.
  • The README describes Swagger-based tool registration, categorization and permission management.
  • The README reports parallel EKG execution in its v2.2 release notes. Runtime behavior is not verified here.

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

Set up the EKG services with Docker Compose

Start the documented EKG service stack and open its local interface.

Before you start

  • Git
  • Docker and Docker Compose

Steps

  1. Clone the CodeFuse-muAgent repository.

  2. Change into the CodeFuse-muAgent directory.

  3. Create the Docker network with the command below.

    Documented command
    docker network create ekg-net

  4. Start the container services with the command below, then open https://localhost:8000.

    Documented command
    docker compose up -d

Expected outcome

The repository’s quick-start instructions identify the local EKG interface at https://localhost:8000 after the services start.

Guide limitations

  • The README says starting all services may take some time.
  • The guide covers service setup, not configuring or running a specific agent workflow.
Documentation 1 ↗
Source-based practical guide

Install the muAgent SDK and prepare model configuration

Install the Python SDK and identify the model configuration needed for the documented code-answer examples.

Before you start

  • Python package installer
  • Related LLM and embedding-model configuration for code-answer examples

Steps

  1. Install the SDK with the command below.

    Documented command
    pip install codefuse-muagent

  2. Prepare the related LLM and embedding-model configurations for code-answer use.

  3. Refer to the linked custom examples and repository examples for the next stage.

Expected outcome

The SDK package is installed, and the stated model-configuration prerequisite for code-answer examples is identified.

Guide limitations

  • The README does not provide the configuration values or full execution steps in this quick start.
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
Codefuse MuagentModel agent workflows with intention, workflow, tool and character nodes.Linux, macOS, WindowsThe repository is public and provides a Python SDK installation command and Docker Compose setup instructions.
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
17 October 2026
Original website title
codefuse-ai/CodeFuse-muAgent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction