[opensourcedex]

AgentPilot is a free, open source orchestration & scheduling project written in Python and released under AGPL-3.0. It has 571 GitHub stars, 80 forks and 2 open issues, and was last pushed 7 months ago. On this registry it ranks #127 of 130 tracked projects in Orchestration & Scheduling, with 5 head-to-head comparisons available. It gained 3 stars over the last 30 tracked days.

What is AgentPilot?

AgentPilot is a Python workflow automation platform, licensed under AGPL-3.0, that lets users create, organize, and execute AI workflows ranging from a single LLM conversation to complex multi-member AI-driven pipelines.

What it is

AgentPilot is a versatile workflow automation system built in Python and distributed primarily as a desktop application for Linux, Windows, and Mac Intel. It sits in the Infrastructure and Operations / Orchestration and Scheduling category, and it presents itself as a GUI-driven environment where a workflow is assembled from members, then chatted with in real time. The interface is not a hard-coded shell: the entire application is built on a framework of base classes for hierarchical configuration interfaces, so pages can be modified or created while the application is running. Agents, chats, blocks, tools, and modules are all first-class objects inside the same runtime, and they can be nested into one another.

The concrete problem it solves is fragmentation. A user who wants to talk to one model, then string together several models with code, prompts, and human input steps, normally ends up with a chat client in one window and bespoke orchestration scripts in another. AgentPilot replaces that split with a single application in which a workflow can contain User, Agent, Text, Code, Prompt, Module, and Workflow members, and in which any combination of those can be saved as a single agent and nested infinitely. Multi-member workflows can be created, edited, and re-run in place, and conversations with them are stored and organized into folders rather than discarded.

Key capabilities

  • Graph workflows built from member types: User, Agent, Text, Code, Prompt, Module, and Workflow. Members aligned vertically are executed in parallel.
  • Branching workflows where messages, tools, and code can be edited and re-run, producing branch points that can be cycled through. Branching works with all plugins and multi-member chats.
  • Reusable, nestable blocks that can be dropped into any workflow or referenced inside text fields such as a system message by writing the block name in curly braces, for example {block-name}.
  • Tools assignable to agents that share the functionality of blocks but default to a single Code member; a tool can also be an entire workflow, so an agent can run code or a whole workflow.
  • Runtime-modifiable tool parameters that are accessible from all workflow member types and can be changed and re-executed without restarting.
  • Python modules that are imported at runtime for toolkits, daemons, memory, custom pages, or anything else requiring persistence.
  • Scheduled and recurring workflows driven by natural language expressions of time, ranging from every second to every leap year.

Who uses it and how

  • Individual users running the prebuilt desktop binaries on Linux, Windows, or Mac Intel, working locally through the GUI rather than operating a server.
  • Builders of multi-member workflows who save an entire workflow as a single agent, organize agents and chats into folders, and nest those agents further.
  • Developers writing Python modules for memory, daemons, toolkits, or custom pages that need to persist across sessions.
  • Users automating recurring jobs, where schedule cadence is expressed in natural language instead of cron syntax.
  • People working against multiple model providers, with Claude, OpenAI, Gemini, and Copilot among the topics associated with the project.

Getting started

Download the version 0.5.1 binary for the platform: AgentPilot_0.5.1_Linux.tar.gz, AgentPilot_0.5.1_Windows.zip, or AgentPilot_0.5.1_Mac_Intel.tar.gz, each published with MD5 and SHA1 checksums. Building from source is documented in docs/guides/how_to_build.md. To migrate an old database, replace the executable with the new one before starting the application.

How it compares

The supplied facts name no comparable or paid products that this project replaces, and they list no competing orchestration tools. On the available evidence, AgentPilot stands alone in this registry.

When to use it — and when not to

Pick AgentPilot when the work is interactive and single-operator: designing multi-member workflows in a GUI, branching and re-running steps, and scheduling recurring runs. Be aware that it is distributed as platform binaries plus a Python source build, that Python modules are the extension path and therefore assume a Python-literate maintainer, and that the AGPL-3.0 licence imposes source-availability obligations on anyone distributing a modified version. The facts show a young project at version 0.5.1 with a modest following, no hosted or containerized deployment option, and no stated database, storage, or mail infrastructure requirements, so teams expecting a managed multi-tenant service or a non-copyleft licence should look elsewhere.

project readme (upstream, from github) — read inline

💬 Agent Pilot

️

A versatile workflow automation system. Create, organize, and execute complex AI-driven tasks. Agent Pilot provides a seamless experience, whether you want to chat with a single LLM or a complex multi-member workflow.

With an intuitive and feature-rich interface, you can effortlessly design AI workflows and chat with them in real-time. Branching chats are supported, allowing flexible interactions and iterative refinement.

Agent Pilot offers generative and customizable UI, allowing creation of custom pages and hierarchical configs. This flexibility gives you the freedom to design an interface that aligns with your specific needs and effortlessly integrate into your workflows.

The system supports scheduled and recurring workflows that can be set to run based on natural language expressions of time, enabling automation that ranges from every second to every leap year.

Discord X (formerly Twitter) Follow

Quickstart

Binaries

Platform Downloads
Linux AgentPilot_0.5.1_Linux.tar.gz
MD5: e74e736e3efbd459b411ecffc45e936e
SHA1: 93b12bd208095f8d8b34395446de23d233a1baed
Windows AgentPilot_0.5.1_Windows.zip
MD5: 17079a8f2faf9683c59d11d0b67a8092
SHA1: c5a30c02f17782ead98c24098e874c9ba2edc950
Mac Intel AgentPilot_0.5.1_Mac_Intel.tar.gz
MD5: 2e1e03e5305ea279df1b76d1a8074cb7
SHA1: 9369152f1b69ff2a4ca476ecf1b377b5ce0e072b

Building from source: How to build from source

[!TIP] You can migrate your old database to the new version by replacing your executable with the new one before starting the application.

Features

👤 Create Agents

Create new agents, edit their configuration and organise them into folders.
Multi-member workflows can be saved as a single agent and nested infinitely.

📝 Manage Chats

View, continue and delete previous workflow chats and organise them into folders.

🌱 Branching Workflows

Messages, tools and code can be edited and re-run, allowing a more practical way to chat with your workflow.
Branching works with all plugins and multi-member chats.

👥 Graph Workflows

Seamlessly add other members or blocks to a workflow and configure how they interact with each other.
Members aligned vertically are executed in parallel.

Available members:

  • User - This is you and will await your input.
  • Agent - Gets an LLM response with integrated tools and messages.
  • Text - A simple text block that can nest other blocks.
  • Code - Gets the output of any given code.
  • Prompt - Gets an LLM response from a single prompt.
  • Module - Runs or retrieves a method or variable from any module.
  • Workflow - Any combination of the above types.

📦 Blocks

Manage a collection of nestable blocks available to use in any workflow or text field, allowing reusability and consistency.
By default a block is a simple text block, but it can be any of the above member types, even a multi-member workflow.
These can be quickly dropped into any workflow, or used in text fields (such as system message) by using the block name in curly braces, e.g. {block-name}.

🔨 Tools

Create and manage tools which can be assigned to agents.
Tools share the same functionality as blocks, except by default they are a single Code member.
They can also be an entire workflow, this allows your agents to not only run code but an entire workflow if you wish.
Configure their parameters, which can be accessed from all workflow member types. These parameters can be modified at runtime and re-executed, this creates a branch point which you can cycle through.

💻 Modules

Modules are python files which are imported at runtime.
These are useful for things like toolkits, daemons, memory, custom pages or anything that needs persistence.

📐 Customizable UI

Includes a flexible and powerful set of base classes for building complex hierarchical configuration interfaces. The entire app is built on this framework. Developers can modify or create configuration pages easily, even while the app is running.

🕒 Scheduler (Premium)

Schedule workflows to run at specific times or intervals.
Natural language expressions are supported, allowing for flexible scheduling.
For example, you can schedule a workflow to run every 5 minutes, every day at 3pm, or every 2nd Tuesday of the month.

📄 Structured Outputs

Members can be configured to output structured data, thanks to Instructor.

📦 Addons

Create and import custom addons to extend the functionality of Agent Pilot.

💻 Code Interpreter

Open Interpreter is integrated into Agent Pilot, and can either be used standalone as a plugin or used to execute code in 9 languages (Python, Shell, AppleScript, HTML, JavaScript, PowerShell, R, React, Ruby)

Code can be executed in multiple ways:

  • From any 'Code' member in any workflow (Chat, Block, Tool).
  • From a message with the role 'Code'

You should always understand the code that is being run, any code you execute is your own responsibility.

For code messages, auto-run can be enabled in the settings. To see code messages in action talk to the pre-configured Open Interpreter agent.

🪄 AI Generation

Blocks under the 'System Blocks' folder are used for generating or enhancing fields. Claude's prompt generator is included by default, you can tweak it or create your own.

  • Prompt - AI enhanced user input
  • Agent - AI generated agent (Coming soon)
    • System message - AI generated system message (Coming soon)
  • Page - AI generated page (Coming soon)

🔌 Plugins

Agent Pilot supports the following plugins:

👄 Voice

Coming back soon
Agents can be linked to a text-to-speech service, combine with a personality context block and make your agent come to life!

🔠 Models

LiteLLM is integrated and supports the following providers:

  • AI21
  • AWS Bedrock
  • AWS Sagemaker
  • Aleph Alpha
  • Anthropic
  • Anyscale
  • Azure OpenAI
  • Baseten
  • Cloudflare
  • Cohere
  • Custom API Servers
  • DeepInfra
  • DeepSeek
  • Gemini
  • Github
  • Groq
  • Huggingface
  • Mistral
  • NLP Cloud
  • Nvidia NIM
  • Ollama
  • OpenAI
  • OpenRouter
  • PaLM API Google
  • Perplexity AI
  • Petals
  • Replicate
  • Together AI
  • VLLM
  • VertexAI Google
  • Voyage

Contributions

Contributions to Agent Pilot are welcome and appreciated. Please feel free to submit a pull request.

Known Issues

  • Be careful using auto run code and open interpreter, any chat you open, if code is the last message it will start auto running, I'll add a flag to remember if the countdown has been stopped.
  • Windows exe must have console visible due to a strange bug.
  • Issue on linux, creating venv does not install pip
  • Changing the config of an OpenAI Assistant won't reload the assistant, for now close and reopen the chat.

If you find this project useful please consider showing support by giving a star or leaving a tip :)

BTC:
ETH:

Frequently asked questions

Is AgentPilot free to use?

AgentPilot is open source under the AGPL-3.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does AgentPilot do?

A versatile workflow automation platform to create, organize, and execute AI workflows, from a single LLM to complex AI-driven workflows.

What is AgentPilot written in?

AgentPilot is primarily written in Python. Its source is publicly available at https://github.com/jbexta/AgentPilot, and it has 571 GitHub stars.