
fastagency
The fastest way to bring multi-agent workflows to production.
Stars: 421

FastAgency is a powerful tool that leverages the AutoGen framework to quickly build applications with multi-agent workflows. It supports various interfaces like ConsoleUI and MesopUI, allowing users to create interactive applications. The tool enables defining workflows between agents, such as students and teachers, and summarizing conversations. FastAgency aims to expand its capabilities by integrating with additional agentic frameworks like CrewAI, providing more options for workflow definition and AI tool integration.
README:
The fastest way to bring multi-agent workflows to production.
For start, FastAgency is not yet another agentic AI framework. There are many such frameworks available today, the most popular open-source one is AG2 (formerly AutoGen). FastAgency provides you with a unified programming interface for deploying agentic workflows written in AG2 agentic framework in both development and productional settings. With only a few lines of code, you can create a web chat application or REST API service interacting with agents of your choice. If you need to scale-up your workloads, FastAgency can help you deploy a fully distributed system using internal message brokers coordinating multiple machines in multiple datacenters with just a few lines of code changed from your local development setup.
FastAgency is an open-source framework designed to accelerate the transition from prototype to production for multi-agent AI workflows. For developers who use the AG2 (formerly AutoGen) framework, FastAgency enables you to seamlessly scale Jupyter notebook prototypes into a fully functional, production-ready applications. With multi-framework support, a unified programming interface, and powerful API integration capabilities, FastAgency streamlines the deployment process, saving time and effort while maintaining flexibility and performance.
Whether you're orchestrating complex AI agents or integrating external APIs into workflows, FastAgency provides the tools necessary to quickly transition from concept to production, reducing development cycles and allowing you to focus on optimizing your multi-agent systems.
-
Unified Programming Interface Across UIs: FastAgency features a common programming interface that enables you to develop your core workflows once and reuse them across various user interfaces without rewriting code. This includes support for both console-based applications via
ConsoleUI
and web-based applications viaMesopUI
. Whether you need a command-line tool or a fully interactive web app, FastAgency allows you to deploy the same underlying workflows across environments, saving development time and ensuring consistency. -
Seamless External API Integration: One of FastAgency's standout features is its ability to easily integrate external APIs into your agent workflows. With just a few lines of code, you can import an OpenAPI specification, and in only one more line, you can connect it to your agents. This dramatically simplifies the process of enhancing AI agents with real-time data, external processing, or third-party services. For example, you can easily integrate a weather API to provide dynamic, real-time weather updates to your users, making your application more interactive and useful with minimal effort.
-
Tester Class for Continuous Integration: FastAgency also provides a Tester Class that enables developers to write and execute tests for their multi-agent workflows. This feature is crucial for maintaining the reliability and robustness of your application, allowing you to automatically verify agent behavior and interactions. The Tester Class is designed to integrate smoothly with continuous integration (CI) pipelines, helping you catch bugs early and ensure that your workflows remain functional as they scale into production.
-
Command-Line Interface (CLI) for Orchestration: FastAgency includes a powerful command-line interface (CLI) for orchestrating and managing multi-agent applications directly from the terminal. The CLI allows developers to quickly run workflows, pass parameters, and monitor agent interactions without needing a full GUI. This is especially useful for automating deployments and integrating workflows into broader DevOps pipelines, enabling developers to maintain control and flexibility in how they manage AI-driven applications.
FastAgency bridges the gap between rapid prototyping and production-ready deployment, empowering developers to bring their multi-agent systems to life quickly and efficiently. By integrating familiar frameworks like AG2 (formerly AutoGen), providing powerful API integration, and offering robust CI testing tools, FastAgency reduces the complexity and overhead typically associated with deploying AI agents in real-world applications.
Whether you’re building interactive console tools, developing fully-featured web apps, or orchestrating large-scale multi-agent systems, FastAgency is built to help you deploy faster, more reliably, and with greater flexibility.
Currently, the only supported runtime is AG2 (formerly AutoGen).
FastAgency currently supports workflows defined using AG2 (formerly AutoGen) and provides options for different types of applications:
-
Console: Use the
ConsoleUI
interface for command-line based interaction. This is ideal for developing and testing workflows in a text-based environment. -
Mesop: Utilize
MesopUI
for web-based applications. This interface is suitable for creating web applications with a user-friendly interface.
FastAgency can use chainable network adapters that can be used to easily create scalable, production ready architectures for serving your workflows. Currently, we support the following network adapters:
-
REST API via FastAPI: Use the
FastAPIAdapter
to serve your workflow using FastAPI server. This setup allows you to work your workflows in multiple workers and serve them using the highly extensible and stable ASGI server. -
NATS.io via FastStream: Utilize the
NatsAdapter
to use NATS.io MQ message broker for highly-scalable, production-ready setup. This interface is suitable for setups in VPN-s or, in combination with theFastAPIAdapter
to serve public workflows in an authenticated, secure manner.
We strongly recommend using Cookiecutter for setting up a FastAgency project. It creates the project folder structure, default workflow, automatically installs all the necessary requirements, and creates a devcontainer that can be used with Visual Studio Code for development.
-
Install Cookiecutter with the following command:
pip install cookiecutter
-
Run the
cookiecutter
command:cookiecutter https://github.com/airtai/cookiecutter-fastagency.git
-
Assuming that you used the default values, you should get the following output:
[1/4] project_name (My FastAgency App): [2/4] project_slug (my_fastagency_app): [3/4] Select app_type 1 - fastapi+mesop 2 - mesop 3 - nats+fastapi+mesop Choose from [1/2/3] (1): 1 [4/4] Select python_version 1 - 3.12 2 - 3.11 3 - 3.10 Choose from [1/2/3] (1): [5/5] Select authentication 1 - none 2 - google Choose from [1/2] (1):
-
To run LLM-based applications, you need an API key for the LLM used. The most commonly used LLM is OpenAI. To use it, create an OpenAI API Key and set it as an environment variable in the terminal using the following command:
export OPENAI_API_KEY=openai_api_key_here
-
Open the generated project in Visual Studio Code with the following command:
code my_fastagency_app
-
Once the project is opened, you will get the following option to reopen it in a devcontainer:
-
After reopening the project in devcontainer, you can verify that the setup is correct by running the provided tests with the following command:
pytest -s
You should get the following output if everything is correctly setup.
=================================== test session starts =================================== platform linux -- Python 3.12.7, pytest-8.3.3, pluggy-1.5.0 rootdir: /workspaces/my_fastagency_app configfile: pyproject.toml plugins: asyncio-0.24.0, anyio-4.6.2.post1 asyncio: mode=Mode.STRICT, default_loop_scope=None collected 1 item tests/test_workflow.py . [100%] ==================================== 1 passed in 1.02s ====================================
You need to define the workflow that your application will use. This is where you specify how the agents interact and what they do. Here's a simple example of a workflow definition as it is generated by the cookie cutter under my_fastagency_app/workflow.py
:
import os
from typing import Any
from autogen.agentchat import ConversableAgent
from fastagency import UI
from fastagency.runtimes.ag2 import Workflow
llm_config = {
"config_list": [
{
"model": "gpt-4o-mini",
"api_key": os.getenv("OPENAI_API_KEY"),
}
],
"temperature": 0.8,
}
wf = Workflow()
@wf.register(name="simple_learning", description="Student and teacher learning chat") # type: ignore[misc]
def simple_workflow(ui: UI, params: dict[str, Any]) -> str:
initial_message = ui.text_input(
sender="Workflow",
recipient="User",
prompt="I can help you learn about mathematics. What subject you would like to explore?",
)
student_agent = ConversableAgent(
name="Student_Agent",
system_message="You are a student willing to learn.",
llm_config=llm_config,
)
teacher_agent = ConversableAgent(
name="Teacher_Agent",
system_message="You are a math teacher.",
llm_config=llm_config,
)
chat_result = student_agent.initiate_chat(
teacher_agent,
message=initial_message,
summary_method="reflection_with_llm",
max_turns=3,
)
return str(chat_result.summary)
This code snippet sets up a simple learning chat between a student and a teacher. It defines the agents and how they should interact and specify how the conversation should be summarized.
To ensure that the workflow we have defined is working properly, we can test it locally using MesopUI. The code below can be found under my_fastagency_app/local/main_mesop.py
and imports the defined workflow and sets up MesopUI.
You can run the Mesop application locally with the following command on Linux and MacOS:
gunicorn my_fastagency_app.local.main_mesop:app
On Windows, please use the following command:
waitress-serve --listen=0.0.0.0:8000 my_fastagency_app.local.main_mesop:app
Open the MesopUI URL http://localhost:8000 in your browser. You can now use the graphical user interface to start, run, test and debug the autogen workflow manually.
If you created the project using Cookiecutter, then building the Docker image is as simple as running the provided script, as shown below:
./scripts/build_docker.sh
Similarly, running the Docker container is as simple as running the provided script, as shown below:
./scripts/run_docker.sh
If you created the project using Cookiecutter, there are built-in scripts to deploy your workflow to Fly.io. In Fly.io, the application namespace is global, so the application name you chose might already be taken. To check your application's name availability and to reserve it, you can run the following script:
./scripts/register_to_fly_io.sh
Once you have reserved your application name, you can test whether you can deploy your application to Fly.io using the following script:
./scripts/deploy_to_fly_io.sh
This is only for testing purposes. You should deploy using GitHub Actions{target="_blank"} as explained below.
Cookiecutter generated all the necessary files to deploy your application to Fly.io using GitHub Actions. Simply push your code to your github repository's main branch and GitHub Actions will automatically deploy your application to Fly.io. For this, you need to set the following secrets in your GitHub repository:
FLY_API_TOKEN
OPENAI_API_KEY
To learn how to create keys and add them as secrets, use the following links:
We are actively working on expanding FastAgency’s capabilities. In addition to supporting AG2 (formerly AutoGen), we plan to integrate support for other frameworks, other network providers and other UI frameworks.
Stay up to date with new features and integrations by following our documentation and community updates on our Discord server. FastAgency is continually evolving to support new frameworks, APIs, and deployment strategies, ensuring you remain at the forefront of AI-driven development.
Last but not least, show us your support by giving a star to our GitHub repository.
Your support helps us to stay in touch with you and encourages us to continue developing and improving the framework. Thank you for your support!
Thanks to all of these amazing people who made the project better!
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for fastagency
Similar Open Source Tools

fastagency
FastAgency is a powerful tool that leverages the AutoGen framework to quickly build applications with multi-agent workflows. It supports various interfaces like ConsoleUI and MesopUI, allowing users to create interactive applications. The tool enables defining workflows between agents, such as students and teachers, and summarizing conversations. FastAgency aims to expand its capabilities by integrating with additional agentic frameworks like CrewAI, providing more options for workflow definition and AI tool integration.

lighteval
LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron. We're releasing it with the community in the spirit of building in the open. Note that it is still very much early so don't expect 100% stability ^^' In case of problems or question, feel free to open an issue!

sec-parser
The `sec-parser` project simplifies extracting meaningful information from SEC EDGAR HTML documents by organizing them into semantic elements and a tree structure. It helps in parsing SEC filings for financial and regulatory analysis, analytics and data science, AI and machine learning, causal AI, and large language models. The tool is especially beneficial for AI, ML, and LLM applications by streamlining data pre-processing and feature extraction.

inngest
Inngest is a platform that offers durable functions to replace queues, state management, and scheduling for developers. It allows writing reliable step functions faster without dealing with infrastructure. Developers can create durable functions using various language SDKs, run a local development server, deploy functions to their infrastructure, sync functions with the Inngest Platform, and securely trigger functions via HTTPS. Inngest Functions support retrying, scheduling, and coordinating operations through triggers, flow control, and steps, enabling developers to build reliable workflows with robust support for various operations.

unify
The Unify Python Package provides access to the Unify REST API, allowing users to query Large Language Models (LLMs) from any Python 3.7.1+ application. It includes Synchronous and Asynchronous clients with Streaming responses support. Users can easily use any endpoint with a single key, route to the best endpoint for optimal throughput, cost, or latency, and customize prompts to interact with the models. The package also supports dynamic routing to automatically direct requests to the top-performing provider. Additionally, users can enable streaming responses and interact with the models asynchronously for handling multiple user requests simultaneously.

motia
Motia is an AI agent framework designed for software engineers to create, test, and deploy production-ready AI agents quickly. It provides a code-first approach, allowing developers to write agent logic in familiar languages and visualize execution in real-time. With Motia, developers can focus on business logic rather than infrastructure, offering zero infrastructure headaches, multi-language support, composable steps, built-in observability, instant APIs, and full control over AI logic. Ideal for building sophisticated agents and intelligent automations, Motia's event-driven architecture and modular steps enable the creation of GenAI-powered workflows, decision-making systems, and data processing pipelines.

TaskingAI
TaskingAI brings Firebase's simplicity to **AI-native app development**. The platform enables the creation of GPTs-like multi-tenant applications using a wide range of LLMs from various providers. It features distinct, modular functions such as Inference, Retrieval, Assistant, and Tool, seamlessly integrated to enhance the development process. TaskingAI’s cohesive design ensures an efficient, intelligent, and user-friendly experience in AI application development.

petals
Petals is a tool that allows users to run large language models at home in a BitTorrent-style manner. It enables fine-tuning and inference up to 10x faster than offloading. Users can generate text with distributed models like Llama 2, Falcon, and BLOOM, and fine-tune them for specific tasks directly from their desktop computer or Google Colab. Petals is a community-run system that relies on people sharing their GPUs to increase its capacity and offer a distributed network for hosting model layers.

kalavai-client
Kalavai is an open-source platform that transforms everyday devices into an AI supercomputer by aggregating resources from multiple machines. It facilitates matchmaking of resources for large AI projects, making AI hardware accessible and affordable. Users can create local and public pools, connect with the community's resources, and share computing power. The platform aims to be a management layer for research groups and organizations, enabling users to unlock the power of existing hardware without needing a devops team. Kalavai CLI tool helps manage both versions of the platform.

RAGEN
RAGEN is a reinforcement learning framework designed to train reasoning-capable large language model (LLM) agents in interactive, stochastic environments. It addresses challenges such as multi-turn interactions and stochastic environments through a Markov Decision Process (MDP) formulation, Reason-Interaction Chain Optimization (RICO) algorithm, and progressive reward normalization strategies. The framework consists of MDP formulation, RICO algorithm with rollout and update stages, and reward normalization strategies to stabilize training. RAGEN aims to optimize reasoning and action strategies for LLM agents operating in complex environments.

RAGEN
RAGEN is a reinforcement learning framework designed to train reasoning-capable large language model (LLM) agents in interactive, stochastic environments. It addresses challenges such as multi-turn interactions and stochastic environments through a Markov Decision Process (MDP) formulation, Reason-Interaction Chain Optimization (RICO) algorithm, and progressive reward normalization strategies. The framework enables LLMs to reason and interact with the environment, optimizing entire trajectories for long-horizon reasoning while maintaining computational efficiency.

Upsonic
Upsonic offers a cutting-edge enterprise-ready framework for orchestrating LLM calls, agents, and computer use to complete tasks cost-effectively. It provides reliable systems, scalability, and a task-oriented structure for real-world cases. Key features include production-ready scalability, task-centric design, MCP server support, tool-calling server, computer use integration, and easy addition of custom tools. The framework supports client-server architecture and allows seamless deployment on AWS, GCP, or locally using Docker.

mindnlp
MindNLP is an open-source NLP library based on MindSpore. It provides a platform for solving natural language processing tasks, containing many common approaches in NLP. It can help researchers and developers to construct and train models more conveniently and rapidly. Key features of MindNLP include: * Comprehensive data processing: Several classical NLP datasets are packaged into a friendly module for easy use, such as Multi30k, SQuAD, CoNLL, etc. * Friendly NLP model toolset: MindNLP provides various configurable components. It is friendly to customize models using MindNLP. * Easy-to-use engine: MindNLP simplified complicated training process in MindSpore. It supports Trainer and Evaluator interfaces to train and evaluate models easily. MindNLP supports a wide range of NLP tasks, including: * Language modeling * Machine translation * Question answering * Sentiment analysis * Sequence labeling * Summarization MindNLP also supports industry-leading Large Language Models (LLMs), including Llama, GLM, RWKV, etc. For support related to large language models, including pre-training, fine-tuning, and inference demo examples, you can find them in the "llm" directory. To install MindNLP, you can either install it from Pypi, download the daily build wheel, or install it from source. The installation instructions are provided in the documentation. MindNLP is released under the Apache 2.0 license. If you find this project useful in your research, please consider citing the following paper: @misc{mindnlp2022, title={{MindNLP}: a MindSpore NLP library}, author={MindNLP Contributors}, howpublished = {\url{https://github.com/mindlab-ai/mindnlp}}, year={2022} }

superduper
superduper.io is a Python framework that integrates AI models, APIs, and vector search engines directly with existing databases. It allows hosting of models, streaming inference, and scalable model training/fine-tuning. Key features include integration of AI with data infrastructure, inference via change-data-capture, scalable model training, model chaining, simple Python interface, Python-first approach, working with difficult data types, feature storing, and vector search capabilities. The tool enables users to turn their existing databases into centralized repositories for managing AI model inputs and outputs, as well as conducting vector searches without the need for specialized databases.

colors_ai
Colors AI is a cross-platform color scheme generator that uses deep learning from public API providers. It is available for all mainstream operating systems, including mobile. Features: - Choose from open APIs, with the ability to set up custom settings - Export section with many export formats to save or clipboard copy - URL providers to other static color generators - Localized to several languages - Dark and light theme - Material Design 3 - Data encryption - Accessibility - And much more
For similar tasks

python-tutorial-notebooks
This repository contains Jupyter-based tutorials for NLP, ML, AI in Python for classes in Computational Linguistics, Natural Language Processing (NLP), Machine Learning (ML), and Artificial Intelligence (AI) at Indiana University.

open-parse
Open Parse is a Python library for visually discerning document layouts and chunking them effectively. It is designed to fill the gap in open-source libraries for handling complex documents. Unlike text splitting, which converts a file to raw text and slices it up, Open Parse visually analyzes documents for superior LLM input. It also supports basic markdown for parsing headings, bold, and italics, and has high-precision table support, extracting tables into clean Markdown formats with accuracy that surpasses traditional tools. Open Parse is extensible, allowing users to easily implement their own post-processing steps. It is also intuitive, with great editor support and completion everywhere, making it easy to use and learn.

MoonshotAI-Cookbook
The MoonshotAI-Cookbook provides example code and guides for accomplishing common tasks with the MoonshotAI API. To run these examples, you'll need an MoonshotAI account and associated API key. Most code examples are written in Python, though the concepts can be applied in any language.

AHU-AI-Repository
This repository is dedicated to the learning and exchange of resources for the School of Artificial Intelligence at Anhui University. Notes will be published on this website first: https://www.aoaoaoao.cn and will be synchronized to the repository regularly. You can also contact me at [email protected].

modern_ai_for_beginners
This repository provides a comprehensive guide to modern AI for beginners, covering both theoretical foundations and practical implementation. It emphasizes the importance of understanding both the mathematical principles and the code implementation of AI models. The repository includes resources on PyTorch, deep learning fundamentals, mathematical foundations, transformer-based LLMs, diffusion models, software engineering, and full-stack development. It also features tutorials on natural language processing with transformers, reinforcement learning, and practical deep learning for coders.

Building-AI-Applications-with-ChatGPT-APIs
This repository is for the book 'Building AI Applications with ChatGPT APIs' published by Packt. It provides code examples and instructions for mastering ChatGPT, Whisper, and DALL-E APIs through building innovative AI projects. Readers will learn to develop AI applications using ChatGPT APIs, integrate them with frameworks like Flask and Django, create AI-generated art with DALL-E APIs, and optimize ChatGPT models through fine-tuning.

examples
This repository contains a collection of sample applications and Jupyter Notebooks for hands-on experience with Pinecone vector databases and common AI patterns, tools, and algorithms. It includes production-ready examples for review and support, as well as learning-optimized examples for exploring AI techniques and building applications. Users can contribute, provide feedback, and collaborate to improve the resource.

lingoose
LinGoose is a modular Go framework designed for building AI/LLM applications. It offers the flexibility to import only the necessary modules, abstracts features for customization, and provides a comprehensive solution for developing AI/LLM applications from scratch. The framework simplifies the process of creating intelligent applications by allowing users to choose preferred implementations or create their own. LinGoose empowers developers to leverage its capabilities to streamline the development of cutting-edge AI and LLM projects.
For similar jobs

sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.