
bee-agent-framework
Framework for building scalable agentic applications.
Stars: 1550

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 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! 🪄
- 🚀 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.
- ⚔️ 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!
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(`-> ${data.step}`, data.response?.update?.finalAnswer ?? "-");
});
});
console.log(`Agent 🤖`, result.finalAnswer);
[!TIP]
🚀 Would you like a fully set-up TypeScript project with Bee, Code Interpreter, and Observability? Check out our Bee Framework Starter.
[!TIP]
🚀 Would you like to work with Bee in your web browser? See Bee Stack
npm install bee-agent-framework
or
yarn add bee-agent-framework
import { BeeAgent } from "bee-agent-framework/agents/bee/agent";
import { OllamaChatLLM } from "bee-agent-framework/adapters/ollama/chat";
import { TokenMemory } from "bee-agent-framework/memory/tokenMemory";
import { DuckDuckGoSearchTool } from "bee-agent-framework/tools/search/duckDuckGoSearch";
import { OpenMeteoTool } from "bee-agent-framework/tools/weather/openMeteo";
const llm = new OllamaChatLLM(); // default is llama3.1 (8B), it is recommended to use 70B model
const agent = new BeeAgent({
llm, // for more explore 'bee-agent-framework/adapters'
memory: new TokenMemory({ llm }), // for more explore 'bee-agent-framework/memory'
tools: [new DuckDuckGoSearchTool(), new OpenMeteoTool()], // for more explore 'bee-agent-framework/tools'
});
const response = await agent
.run({ prompt: "What's the current weather in Las Vegas?" })
.observe((emitter) => {
emitter.on("update", async ({ data, update, meta }) => {
console.log(`Agent (${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/
[!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).
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.
- Python version
- Multi-agent orchestration patterns
- Catalog of agents
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.
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.
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.
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.
Special thanks to our contributors for helping us improve Bee Agent Framework.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for bee-agent-framework
Similar Open Source Tools

bee-agent-framework
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.

graphiti
Graphiti is a framework for building and querying temporally-aware knowledge graphs, tailored for AI agents in dynamic environments. It continuously integrates user interactions, structured and unstructured data, and external information into a coherent, queryable graph. The framework supports incremental data updates, efficient retrieval, and precise historical queries without complete graph recomputation, making it suitable for developing interactive, context-aware AI applications.

evidently
Evidently is an open-source Python library designed for evaluating, testing, and monitoring machine learning (ML) and large language model (LLM) powered systems. It offers a wide range of functionalities, including working with tabular, text data, and embeddings, supporting predictive and generative systems, providing over 100 built-in metrics for data drift detection and LLM evaluation, allowing for custom metrics and tests, enabling both offline evaluations and live monitoring, and offering an open architecture for easy data export and integration with existing tools. Users can utilize Evidently for one-off evaluations using Reports or Test Suites in Python, or opt for real-time monitoring through the Dashboard service.

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.

mmore
MMORE is an open-source, end-to-end pipeline for ingesting, processing, indexing, and retrieving knowledge from various file types such as PDFs, Office docs, images, audio, video, and web pages. It standardizes content into a unified multimodal format, supports distributed CPU/GPU processing, and offers hybrid dense+sparse retrieval with an integrated RAG service through CLI and APIs.

mlflow
MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). MLflow's current components are:
* `MLflow Tracking

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

AgentFly
AgentFly is an extensible framework for building LLM agents with reinforcement learning. It supports multi-turn training by adapting traditional RL methods with token-level masking. It features a decorator-based interface for defining tools and reward functions, enabling seamless extension and ease of use. To support high-throughput training, it implemented asynchronous execution of tool calls and reward computations, and designed a centralized resource management system for scalable environment coordination. A suite of prebuilt tools and environments are provided.

agents
The LiveKit Agent Framework is designed for building real-time, programmable participants that run on servers. Easily tap into LiveKit WebRTC sessions and process or generate audio, video, and data streams. The framework includes plugins for common workflows, such as voice activity detection and speech-to-text. Agents integrates seamlessly with LiveKit server, offloading job queuing and scheduling responsibilities to it. This eliminates the need for additional queuing infrastructure. Agent code developed on your local machine can scale to support thousands of concurrent sessions when deployed to a server in production.

evalverse
Evalverse is an open-source project designed to support Large Language Model (LLM) evaluation needs. It provides a standardized and user-friendly solution for processing and managing LLM evaluations, catering to AI research engineers and scientists. Evalverse supports various evaluation methods, insightful reports, and no-code evaluation processes. Users can access unified evaluation with submodules, request evaluations without code via Slack bot, and obtain comprehensive reports with scores, rankings, and visuals. The tool allows for easy comparison of scores across different models and swift addition of new evaluation tools.

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).

atropos
Atropos is a robust and scalable framework for Reinforcement Learning Environments with Large Language Models (LLMs). It provides a flexible platform to accelerate LLM-based RL research across diverse interactive settings. Atropos supports multi-turn and asynchronous RL interactions, integrates with various inference APIs, offers a standardized training interface for experimenting with different RL algorithms, and allows for easy scalability by launching more environment instances. The framework manages diverse environment types concurrently for heterogeneous, multi-modal training.

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.

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.

open-unlearning
OpenUnlearning is an easily extensible framework that unifies LLM unlearning evaluation benchmarks. It provides efficient implementations of TOFU and MUSE unlearning benchmarks, supporting 5 unlearning methods, 3+ datasets, 6+ evaluation metrics, and 7+ LLMs. Users can easily extend the framework to incorporate more variants, collaborate by adding new benchmarks, unlearning methods, datasets, and evaluation metrics, and drive progress in the field.
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

bee-agent-framework
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.

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.

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.

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.

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.

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.

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.
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.