gacjie/agent_flow

★ 18GoAudience · developerComplexity · 3/5Setup · easy

Mindmap

mindmap
  root((AgentFlow))
    Agents
      Roles and rules
      Tool permissions
      Agent to agent calls
    Built-in Tools
      File operations
      Shell commands
      Browser automation
      Web search
    AI Models
      OpenAI
      Anthropic
      Google Gemini
    Workspaces
      Project isolation
      Own database
      Access control
    Deployment
      Single binary
      SQLite storage
      Embedded UI

mindmap root((AgentFlow)) Agents Roles and rules Tool permissions Agent to agent calls Built-in Tools File operations Shell commands Browser automation Web search AI Models OpenAI Anthropic Google Gemini Workspaces Project isolation Own database Access control Deployment Single binary SQLite storage Embedded UI

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Run AI agents on your own server that can read and write files, execute shell commands, and automate browser tasks without sending data to a third-party service.

USE CASE 2

Set up a team AI assistant with role-based permissions so different people have different levels of access to what the agents can do.

USE CASE 3

Manage multiple projects in isolated workspaces so AI agents working on one project never see files or context from another.

USE CASE 4

Extend agent capabilities by plugging in external tools via the Model Context Protocol without modifying the core system.

Tech stack

GoSQLiteOpenAI APIAnthropic APIGoogle GeminiMCPHeadless BrowserEmbedded Web UI

Getting it running

Difficulty · easy Time to first run · 30min

Download a pre-built binary for Windows, Linux x86-64, or ARM. Point at a config file or set AF_ env vars. Default login is admin/admin123, change before exposing to the internet.

License not mentioned in the explanation.

In plain English

AgentFlow is a self-hosted system for running AI agents on a server. You install it as a single binary, open a browser, and interact with AI assistants that can actually do things on your server, such as reading and writing files, running shell commands, searching the web, and controlling a headless browser. It is written in Go, stores everything in SQLite, and embeds its own web interface, so there is no separate database server or frontend build step to manage. The core idea is that you configure agents, each with a defined role, rules, and set of tools it is allowed to use, and then those agents carry out tasks autonomously through a chat interface. Agents can also call other agents for subtasks. The system includes 28 built-in tools grouped into categories: file operations, command execution, browser automation, web search, memory management, task planning, and workspace document management. You can extend this further through the Model Context Protocol, which lets you plug in additional external tools over a standard interface. It connects to AI models from OpenAI, Anthropic, and Google Gemini, or any API that follows the OpenAI-compatible format. The workbench streams responses in real time and keeps a buffer of recent events so the conversation can resume cleanly if your browser tab disconnects. Workspaces isolate projects from each other. Each workspace has its own database and file directory, so agents working on different projects do not share context. There is also a role-based access control system with 34 permission nodes, which is relevant if you are running this for a team rather than just yourself. Deployment is straightforward: download or build the binary, point it at a config file or set environment variables with an AF_ prefix, and run it. The README provides pre-built binaries for Windows, Linux x86-64, and Linux ARM. You can also build from source with Go 1.25. The default login is admin with password admin123, which the README implies you should change before exposing the service.

Copy-paste prompts

Prompt 1

I just installed AgentFlow. Walk me through creating my first agent with file-read and web-search tools enabled, and show me an example config file.

Prompt 2

Explain how workspaces work in AgentFlow. How do I create a new workspace for a project and make sure agents in it can't access files from my other workspace?

Prompt 3

I want to let an AgentFlow agent run shell commands on my Linux server. What are the security risks and what permission settings or rules should I put in place first?

Prompt 4

How do I connect AgentFlow to a self-hosted OpenAI-compatible model instead of using OpenAI directly? What config values do I need to change?

Prompt 5

Walk me through setting up role-based access control in AgentFlow for a small team of three people with different permission levels.

Open on GitHub → Explain another repo

← gacjie on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.