bee-agent-framework

Framework for building scalable agentic applications.

Stars: 1550

Visit

The Bee Agent Framework is an open-source tool for building, deploying, and serving powerful agentic workflows at scale. It provides AI agents, tools for creating workflows in Javascript/Python, a code interpreter, memory optimization strategies, serialization for pausing/resuming workflows, traceability features, production-level control, and upcoming features like model-agnostic support and a chat UI. The framework offers various modules for agents, llms, memory, tools, caching, errors, adapters, logging, serialization, and more, with a roadmap including MLFlow integration, JSON support, structured outputs, chat client, base agent improvements, guardrails, and evaluation.

README:

Bee Agent Framework

Open-source framework for building, deploying, and serving powerful multi-agent workflows at scale.

🐝 Bee Agent Framework is an open-source TypeScript library for building production-ready multi-agent systems. Pick from a variety of 🌐 LLM providers, customize the 📜 prompt templates, create 🤖 agents, equip agents with pre-made 🛠️ tools, and orchestrate 🤖🤝🤖 multi-agent workflows! 🪄

Latest updates

🚀 2025-01-09:
- Introduced Workflows, a way of building multi-agent systems.
- Added support for Model Context Protocol, featured on the official page.
🚀 2024-12-09: Added support for LLaMa 3.3.
🚀 2024-11-21: Added an experimental Streamlit agent.

For a full changelog, see the releases page.

Why pick Bee?

⚔️ Battle-tested. Bee Agent Framework is at the core of BeeAI, a powerful platform for building chat assistants and custom AI-powered apps. BeeAI is in a closed beta, but already used by hundreds of users. And it's fully open-source too!
🚀 Production-grade. In an actual product, you have to reduce token spend through memory strategies, store and restore the agent state through (de)serialization, generate structured output, or execute generated code in a sandboxed environment. Leave all that to Bee and focus on building!
🤗 Built for open-source models. Pick any LLM you want – including small and open-source models. The framework is designed to perform robustly with Granite and Llama 3.x. A full agentic workflow can run on your laptop!
😢 Bee cares about the sad path too. Real-world applications encounter errors and failures. Bee lets you observe the full agent workflow through events, collect telemetry, log diagnostic data, and throws clear and well-defined exceptions. Bees may be insects, but not bugs!
🌳 A part of something greater. Bee isn't just a framework, but a full ecosystem. Use Bee UI to chat with your agents visually. Bee Observe collects and manages telemetry. Bee Code Interpreter runs generated code safely in a secure sandbox. The Bee ecosystem also integrates with Model Context Protocol, allowing interoperability with the wider agent ecosystem!

Quick example

This example demonstrates how to build a multi-agent workflow using Bee Agent Framework:

import "dotenv/config";
import { UnconstrainedMemory } from "bee-agent-framework/memory/unconstrainedMemory";
import { OpenMeteoTool } from "bee-agent-framework/tools/weather/openMeteo";
import { WikipediaTool } from "bee-agent-framework/tools/search/wikipedia";
import { AgentWorkflow } from "bee-agent-framework/experimental/workflows/agent";
import { BaseMessage, Role } from "bee-agent-framework/llms/primitives/message";
import { GroqChatLLM } from "bee-agent-framework/adapters/groq/chat";

const workflow = new AgentWorkflow();

workflow.addAgent({
  name: "Researcher",
  instructions: "You are a researcher assistant. Respond only if you can provide a useful answer.",
  tools: [new WikipediaTool()],
  llm: new GroqChatLLM(),
});

workflow.addAgent({
  name: "WeatherForecaster",
  instructions: "You are a weather assistant. Respond only if you can provide a useful answer.",
  tools: [new OpenMeteoTool()],
  llm: new GroqChatLLM(),
  execution: { maxIterations: 3 },
});

workflow.addAgent({
  name: "Solver",
  instructions:
    "Your task is to provide the most useful final answer based on the assistants' responses which all are relevant. Ignore those where assistant do not know.",
  llm: new GroqChatLLM(),
});

const memory = new UnconstrainedMemory();

await memory.add(
  BaseMessage.of({
    role: Role.USER,
    text: "What is the capital of France and what is the current weather there?",
    meta: { createdAt: new Date() },
  }),
);

const { result } = await workflow.run(memory.messages).observe((emitter) => {
  emitter.on("success", (data) => {
    console.log(`-> ${data.step}`, data.response?.update?.finalAnswer ?? "-");
  });
});

console.log(`Agent 🤖`, result.finalAnswer);

Getting started

[!TIP]

🚀 Would you like a fully set-up TypeScript project with Bee, Code Interpreter, and Observability? Check out our Bee Framework Starter.

[!TIP]

🚀 Would you like to work with Bee in your web browser? See Bee Stack

Installation

npm install bee-agent-framework

yarn add bee-agent-framework

Example

import { BeeAgent } from "bee-agent-framework/agents/bee/agent";
import { OllamaChatLLM } from "bee-agent-framework/adapters/ollama/chat";
import { TokenMemory } from "bee-agent-framework/memory/tokenMemory";
import { DuckDuckGoSearchTool } from "bee-agent-framework/tools/search/duckDuckGoSearch";
import { OpenMeteoTool } from "bee-agent-framework/tools/weather/openMeteo";

const llm = new OllamaChatLLM(); // default is llama3.1 (8B), it is recommended to use 70B model

const agent = new BeeAgent({
  llm, // for more explore 'bee-agent-framework/adapters'
  memory: new TokenMemory({ llm }), // for more explore 'bee-agent-framework/memory'
  tools: [new DuckDuckGoSearchTool(), new OpenMeteoTool()], // for more explore 'bee-agent-framework/tools'
});

const response = await agent
  .run({ prompt: "What's the current weather in Las Vegas?" })
  .observe((emitter) => {
    emitter.on("update", async ({ data, update, meta }) => {
      console.log(`Agent (${update.key}) 🤖 : `, update.value);
    });
  });

console.log(`Agent 🤖 : `, response.result.text);

➡️ See a more advanced example.

➡️ you can run this example after local installation, using the command yarn start examples/agents/simple.ts

[!TIP]

To run this example, be sure that you have installed ollama with the llama3.1 model downloaded.

[!TIP]

Documentation is available at https://i-am-bee.github.io/bee-agent-framework/

Local Installation

[!NOTE]

yarn should be installed via Corepack (tutorial)

Clone the repository git clone [email protected]:i-am-bee/bee-agent-framework.
Install dependencies yarn install --immutable && yarn prepare.
Create .env (from .env.template) and fill in missing values (if any).
Start the agent yarn run start:bee (it runs /examples/agents/bee.ts file).

➡️ All examples can be found in the examples directory.

➡️ To run an arbitrary example, use the following command yarn start examples/agents/bee.ts (just pass the appropriate path to the desired example).

📦 Modules

The source directory (src) provides numerous modules that one can use.

Name	Description
agents	Base classes defining the common interface for agent.
workflows	Build agentic applications in a declarative way via workflows.
llms	Base classes defining the common interface for text inference (standard or chat).
template	Prompt Templating system based on `Mustache` with various improvements.
memory	Various types of memories to use with agent.
tools	Tools that an agent can use.
cache	Preset of different caching approaches that can be used together with tools.
errors	Error classes and helpers to catch errors fast.
adapters	Concrete implementations of given modules for different environments.
logger	Core component for logging all actions within the framework.
serializer	Core component for the ability to serialize/deserialize modules into the serialized format.
version	Constants representing the framework (e.g., latest version)
emitter	Bringing visibility to the system by emitting events.
internals	Modules used by other modules within the framework.

To see more in-depth explanation see overview.

Roadmap

Python version
Multi-agent orchestration patterns
Catalog of agents

Contribution guidelines

The Bee Agent Framework is an open-source project and we ❤️ contributions.

If you'd like to contribute to Bee, please take a look at our contribution guidelines.

Bugs

We are using GitHub Issues to manage our public bugs. We keep a close eye on this, so before filing a new issue, please check to make sure it hasn't already been logged.

Code of conduct

This project and everyone participating in it are governed by the Code of Conduct. By participating, you are expected to uphold this code. Please read the full text so that you can read which actions may or may not be tolerated.

Legal notice

All content in these repositories including code has been provided by IBM under the associated open source software license and IBM is under no obligation to provide enhancements, updates, or support. IBM developers produced this code as an open source project (not as an IBM product), and IBM makes no assertions as to the level of quality nor security, and will not be maintaining this code going forward.

Contributors

Special thanks to our contributors for helping us improve Bee Agent Framework.

For Tasks:

Click tags to check more tools for each tasks

build workflows optimize memory trace workflows control production debug performance

For Jobs:

ai engineer data scientist machine learning engineer software developer research scientist

Alternative AI tools for bee-agent-framework

Similar Open Source Tools

bee-agent-framework

github

: 1.6k

inferable

Inferable is an open source platform that helps users build reliable LLM-powered agentic automations at scale. It offers a managed agent runtime, durable tool calling, zero network configuration, multiple language support, and is fully open source under the MIT license. Users can define functions, register them with Inferable, and create runs that utilize these functions to automate tasks. The platform supports Node.js/TypeScript, Go, .NET, and React, and provides SDKs, core services, and bootstrap templates for various languages.

github

: 340

beeai-framework

BeeAI Framework is a versatile tool for building production-ready multi-agent systems. It offers flexibility in orchestrating agents, seamless integration with various models and tools, and production-grade controls for scaling. The framework supports Python and TypeScript libraries, enabling users to implement simple to complex multi-agent patterns, connect with AI services, and optimize token usage and resource management.

github

: 2.1k

sophia

Sophia is an open-source TypeScript platform designed for autonomous AI agents and LLM based workflows. It aims to automate processes, review code, assist with refactorings, and support various integrations. The platform offers features like advanced autonomous agents, reasoning/planning inspired by Google's Self-Discover paper, memory and function call history, adaptive iterative planning, and more. Sophia supports multiple LLMs/services, CLI and web interface, human-in-the-loop interactions, flexible deployment options, observability with OpenTelemetry tracing, and specific agents for code editing, software engineering, and code review. It provides a flexible platform for the TypeScript community to expand and support various use cases and integrations.

github

: 909

typedai

TypedAI is a TypeScript-first AI platform designed for developers to create and run autonomous AI agents, LLM based workflows, and chatbots. It offers advanced autonomous agents, software developer agents, pull request code review agent, AI chat interface, Slack chatbot, and supports various LLM services. The platform features configurable Human-in-the-loop settings, functional callable tools/integrations, CLI and Web UI interface, and can be run locally or deployed on the cloud with multi-user/SSO support. It leverages the Python AI ecosystem through executing Python scripts/packages and provides flexible run/deploy options like single user mode, Firestore & Cloud Run deployment, and multi-user SSO enterprise deployment. TypedAI also includes UI examples, code examples, and automated LLM function schemas for seamless development and execution of AI workflows.

github

: 966

nous

Nous is an open-source TypeScript platform for autonomous AI agents and LLM based workflows. It aims to automate processes, support requests, review code, assist with refactorings, and more. The platform supports various integrations, multiple LLMs/services, CLI and web interface, human-in-the-loop interactions, flexible deployment options, observability with OpenTelemetry tracing, and specific agents for code editing, software engineering, and code review. It offers advanced features like reasoning/planning, memory and function call history, hierarchical task decomposition, and control-loop function calling options. Nous is designed to be a flexible platform for the TypeScript community to expand and support different use cases and integrations.

github

: 766

starwhale

Starwhale is an MLOps/LLMOps platform that brings efficiency and standardization to machine learning operations. It streamlines the model development lifecycle, enabling teams to optimize workflows around key areas like model building, evaluation, release, and fine-tuning. Starwhale abstracts Model, Runtime, and Dataset as first-class citizens, providing tailored capabilities for common workflow scenarios including Models Evaluation, Live Demo, and LLM Fine-tuning. It is an open-source platform designed for clarity and ease of use, empowering developers to build customized MLOps features tailored to their needs.

github

: 196

ludwig

Ludwig is a declarative deep learning framework designed for scale and efficiency. It is a low-code framework that allows users to build custom AI models like LLMs and other deep neural networks with ease. Ludwig offers features such as optimized scale and efficiency, expert level control, modularity, and extensibility. It is engineered for production with prebuilt Docker containers, support for running with Ray on Kubernetes, and the ability to export models to Torchscript and Triton. Ludwig is hosted by the Linux Foundation AI & Data.

github

: 11.0k

kernel-memory

Kernel Memory (KM) is a multi-modal AI Service specialized in the efficient indexing of datasets through custom continuous data hybrid pipelines, with support for Retrieval Augmented Generation (RAG), synthetic memory, prompt engineering, and custom semantic memory processing. KM is available as a Web Service, as a Docker container, a Plugin for ChatGPT/Copilot/Semantic Kernel, and as a .NET library for embedded applications. Utilizing advanced embeddings and LLMs, the system enables Natural Language querying for obtaining answers from the indexed data, complete with citations and links to the original sources. Designed for seamless integration as a Plugin with Semantic Kernel, Microsoft Copilot and ChatGPT, Kernel Memory enhances data-driven features in applications built for most popular AI platforms.

github

: 1.7k

mem0

Mem0 is a tool that provides a smart, self-improving memory layer for Large Language Models, enabling personalized AI experiences across applications. It offers persistent memory for users, sessions, and agents, self-improving personalization, a simple API for easy integration, and cross-platform consistency. Users can store memories, retrieve memories, search for related memories, update memories, get the history of a memory, and delete memories using Mem0. It is designed to enhance AI experiences by enabling long-term memory storage and retrieval.

github

: 26.5k

mobius

Mobius is an AI infra platform including realtime computing and training. It is built on Ray, a distributed computing framework, and provides a number of features that make it well-suited for online machine learning tasks. These features include: * **Cross Language**: Mobius can run in multiple languages (only Python and Java are supported currently) with high efficiency. You can implement your operator in different languages and run them in one job. * **Single Node Failover**: Mobius has a special failover mechanism that only needs to rollback the failed node itself, in most cases, to recover the job. This is a huge benefit if your job is sensitive about failure recovery time. * **AutoScaling**: Mobius can generate a new graph with different configurations in runtime without stopping the job. * **Fusion Training**: Mobius can combine TensorFlow/Pytorch and streaming, then building an e2e online machine learning pipeline. Mobius is still under development, but it has already been used to power a number of real-world applications, including: * A real-time recommendation system for a major e-commerce company * A fraud detection system for a large financial institution * A personalized news feed for a major news organization If you are interested in using Mobius for your own online machine learning projects, you can find more information in the documentation.

github

: 78

oat

Oat is a simple and efficient framework for running online LLM alignment algorithms. It implements a distributed Actor-Learner-Oracle architecture, with components optimized using state-of-the-art tools. Oat simplifies the experimental pipeline of LLM alignment by serving an Oracle online for preference data labeling and model evaluation. It provides a variety of oracles for simulating feedback and supports verifiable rewards. Oat's modular structure allows for easy inheritance and modification of classes, enabling rapid prototyping and experimentation with new algorithms. The framework implements cutting-edge online algorithms like PPO for math reasoning and various online exploration algorithms.

github

: 87

Eco2AI

Eco2AI is a python library for CO2 emission tracking that monitors energy consumption of CPU & GPU devices and estimates equivalent carbon emissions based on regional emission coefficients. Users can easily integrate Eco2AI into their Python scripts by adding a few lines of code. The library records emissions data and device information in a local file, providing detailed session logs with project names, experiment descriptions, start times, durations, power consumption, CO2 emissions, CPU and GPU names, operating systems, and countries.

github

: 245

TornadoVM

TornadoVM is a plug-in to OpenJDK and GraalVM that allows programmers to automatically run Java programs on heterogeneous hardware. TornadoVM targets OpenCL, PTX and SPIR-V compatible devices which include multi-core CPUs, dedicated GPUs (Intel, NVIDIA, AMD), integrated GPUs (Intel HD Graphics and ARM Mali), and FPGAs (Intel and Xilinx).

github

: 1.2k

AgentBench

AgentBench is a benchmark designed to evaluate Large Language Models (LLMs) as autonomous agents in various environments. It includes 8 distinct environments such as Operating System, Database, Knowledge Graph, Digital Card Game, and Lateral Thinking Puzzles. The tool provides a comprehensive evaluation of LLMs' ability to operate as agents by offering Dev and Test sets for each environment. Users can quickly start using the tool by following the provided steps, configuring the agent, starting task servers, and assigning tasks. AgentBench aims to bridge the gap between LLMs' proficiency as agents and their practical usability.

github

: 2.1k

gpt4all

GPT4All is an ecosystem to run powerful and customized large language models that work locally on consumer grade CPUs and any GPU. Note that your CPU needs to support AVX or AVX2 instructions. Learn more in the documentation. A GPT4All model is a 3GB - 8GB file that you can download and plug into the GPT4All open-source ecosystem software. Nomic AI supports and maintains this software ecosystem to enforce quality and security alongside spearheading the effort to allow any person or enterprise to easily train and deploy their own on-edge large language models.

github

: 72.9k

For similar tasks

activepieces

Activepieces is an open source replacement for Zapier, designed to be extensible through a type-safe pieces framework written in Typescript. It features a user-friendly Workflow Builder with support for Branches, Loops, and Drag and Drop. Activepieces integrates with Google Sheets, OpenAI, Discord, and RSS, along with 80+ other integrations. The list of supported integrations continues to grow rapidly, thanks to valuable contributions from the community. Activepieces is an open ecosystem; all piece source code is available in the repository, and they are versioned and published directly to npmjs.com upon contributions. If you cannot find a specific piece on the pieces roadmap, please submit a request by visiting the following link: Request Piece Alternatively, if you are a developer, you can quickly build your own piece using our TypeScript framework. For guidance, please refer to the following guide: Contributor's Guide

github

: 12.3k

bee-agent-framework

github

: 1.6k

mastra

Mastra is an opinionated Typescript framework designed to help users quickly build AI applications and features. It provides primitives such as workflows, agents, RAG, integrations, syncs, and evals. Users can run Mastra locally or deploy it to a serverless cloud. The framework supports various LLM providers, offers tools for building language models, workflows, and accessing knowledge bases. It includes features like durable graph-based state machines, retrieval-augmented generation, integrations, syncs, and automated tests for evaluating LLM outputs.

github

: 11.0k

otto-m8

otto-m8 is a flowchart based automation platform designed to run deep learning workloads with minimal to no code. It provides a user-friendly interface to spin up a wide range of AI models, including traditional deep learning models and large language models. The tool deploys Docker containers of workflows as APIs for integration with existing workflows, building AI chatbots, or standalone applications. Otto-m8 operates on an Input, Process, Output paradigm, simplifying the process of running AI models into a flowchart-like UI.

github

: 65

flows-ai

Flows AI is a lightweight, type-safe AI workflow orchestrator inspired by Anthropic's agent patterns and built on top of Vercel AI SDK. It provides a simple and deterministic way to build AI workflows by connecting different input/outputs together, either explicitly defining workflows or dynamically breaking down complex tasks using an orchestrator agent. The library is designed without classes or state, focusing on flexible input/output contracts for nodes.

github

: 168

LangGraph-learn

LangGraph-learn is a community-driven project focused on mastering LangGraph and other AI-related topics. It provides hands-on examples and resources to help users learn how to create and manage language model workflows using LangGraph and related tools. The project aims to foster a collaborative learning environment for individuals interested in AI and machine learning by offering practical examples and tutorials on building efficient and reusable workflows involving language models.

github

: 74

xorq

Xorq (formerly LETSQL) is a data processing library built on top of Ibis and DataFusion to write multi-engine data workflows. It provides a flexible and powerful tool for processing and analyzing data from various sources, enabling users to create complex data pipelines and perform advanced data transformations.

github

: 93

beeai-framework

github

: 2.1k

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.

github

: 7.1k

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.

github

: 502

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.

github

: 159

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.

github

: 620

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.

github

: 27.7k

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

github

: 953

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.

github

: 1.3k

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.

github

: 2.1k