flowx

flowx

Introduction

flowx is the ai framework of ai-flowx written in Go.

Prerequisites

• Go >= 1.22.0

Build

version=latest make build

Usage

Usage:
  flowx [flags]

Flags:
  -c, --config-file string   config file
  -h, --help                 help for flowx
  -l, --listen-port string   listen port (default ":8080")
  -v, --version              version for flowx

Settings

flowx parameters can be set in the directory config.

An example of configuration in config.yml:

cache:
  provider: cachex
  host: 127.0.0.1
  port: 8081
  user: user
  pass: pass
flow:
  channel: wechat
gpt:
  provider: doubao-chat
  api: https://ark.cn-beijing.volces.com/api/v3/chat/completions
  model: ep-*
  key: 8429f8ab-*
memory:
  type: shortterm
store:
  provider: vecx
  host: 127.0.0.1
  port: 8082
  path: /path/to/file
  user: user
  pass: pass
tool:
  - name: decorator
  - name: gerrit
  - name: hello
  - name: structuredtool

Architecture

Features

• Role-Based Agents

  Create specialized agents with defined roles, expertise, and goals

• Flexible Tools

  Equip agents with custom tools and APIs to interact with external services and data sources

• Intelligent Collaboration

  Agents work together, sharing insights and coordinating tasks to achieve complex objectives

• Task Management

  Define sequential or parallel workflows, with agents automatically handling task dependencies

License

Project License can be found here.

Reference

Binding

• gopy

Chat

• dify-on-wechat
• dify-on-wechat
• openwechat

Framework

• autogen
• cobra-cli
• crewai
• dockerfile
• fabric
• langchain-agents
• langgraph
• llama-agents
• modelfile
• semantic-kernel

Memory

• memoryrepository-for-ai-npc
• memoryrepository-for-ai-npc

Protocol

• claude-mcp
• claude-mcp-servers
• langgraph-agent-protocol

Store

• chroma-go
• setting-up-postgresql-server-in-docker-container-on-ubuntu

Tools

• crewai-tools
• crewai-tools
• langchain-tools
• langchaingo