| Date | Language | Update Description |
|---|---|---|
| 2025/08/25 | Python | 🚀 ACP is now part of A2A under the Linux Foundation! 👉 Learn more |
| 2025/06/03 | Python | Release experimental Requirement Agent. |
| 2025/05/15 | Python | New protocol integrations: ACP and MCP. |
| 2025/02/19 | Python | Launched Python library alpha. See getting started guide. |
| 2025/02/07 | TypeScript | Introduced Backend module to simplify working with AI services (chat, embedding). |
| 2025/01/28 | TypeScript | Added support for DeepSeek R1, check out the Competitive Analysis Workflow example. |
| 2025/01/09 | TypeScript | Introduced Workflows, a way of building multi-agent systems. Added support for Model Context Protocol. |
| 2024/12/09 | TypeScript | Added support for LLaMa 3.3. See multi-agent workflow example using watsonx or explore other available providers. |
| 2024/11/21 | TypeScript | Added an experimental Streamlit agent. |
For a full changelog, see our releases page.
BeeAI Framework is a comprehensive toolkit for building intelligent, autonomous agents and multi-agent systems. It provides everything you need to create agents that can reason, take actions, and collaborate to solve complex problems.
Tip
Get started quickly with the beeai-framework-py-starter [Python] or beeai-framework-ts-starter [TypeScript] template.
| Feature | Description |
|---|---|
| 🤖 Requirement Agent | Create predictable, controlled behavior across different LLMs by setting rules the agent must follow. |
| 🤖 Agents | Create intelligent agents that can reason, act, and adapt |
| 🔌 Backend | Connect to any LLM provider with unified interfaces |
| 🔧 Tools | Extend agents with built in tools (web search, weather, code execution, and more) or custom tools |
| 🔍 RAG | Build retrieval-augmented generation systems with vector stores and document processing |
| 📝 Templates | Build dynamic prompts with enhanced Mustache syntax |
| 🧠 Memory | Manage conversation history with built in memory strategies |
| 📊 Observability | Monitor agent behavior with events, logging, and robust error handling |
| 🚀 Serve | Host agents in servers with support for multiple protocols such as A2A and MCP |
| 💾 Cache | Optimize performance and reduce costs with intelligent caching |
| 💿 Serialization | Save and load agent state for persistence across sessions |
| 🔄 Workflows | Orchestrate multi-agent systems with complex execution flows |
To install the Python library:
pip install beeai-framework
To install the TypeScript library:
npm install beeai-framework
import asyncio
from beeai_framework.agents.requirement import RequirementAgent
from beeai_framework.agents.requirement.requirements.conditional import ConditionalRequirement
from beeai_framework.backend import ChatModel
from beeai_framework.errors import FrameworkError
from beeai_framework.middleware.trajectory import GlobalTrajectoryMiddleware
from beeai_framework.tools import Tool
from beeai_framework.tools.handoff import HandoffTool
from beeai_framework.tools.search.wikipedia import WikipediaTool
from beeai_framework.tools.think import ThinkTool
from beeai_framework.tools.weather import OpenMeteoTool
async def main() -> None:
knowledge_agent = RequirementAgent(
llm=ChatModel.from_name("ollama:granite3.3:8b"),
tools=[ThinkTool(), WikipediaTool()],
requirements=[ConditionalRequirement(ThinkTool, force_at_step=1)],
role="Knowledge Specialist",
instructions="Provide answers to general questions about the world.",
)
weather_agent = RequirementAgent(
llm=ChatModel.from_name("ollama:granite3.3:8b"),
tools=[OpenMeteoTool()],
role="Weather Specialist",
instructions="Provide weather forecast for a given destination.",
)
main_agent = RequirementAgent(
name="MainAgent",
llm=ChatModel.from_name("ollama:granite3.3:8b"),
tools=[
ThinkTool(),
HandoffTool(
knowledge_agent,
name="KnowledgeLookup",
description="Consult the Knowledge Agent for general questions.",
),
HandoffTool(
weather_agent,
name="WeatherLookup",
description="Consult the Weather Agent for forecasts.",
),
],
requirements=[ConditionalRequirement(ThinkTool, force_at_step=1)],
# Log all tool calls to the console for easier debugging
middlewares=[GlobalTrajectoryMiddleware(included=[Tool])],
)
question = "If I travel to Rome next weekend, what should I expect in terms of weather, and also tell me one famous historical landmark there?"
print(f"User: {question}")
try:
response = await main_agent.run(question, expected_output="Helpful and clear response.")
print("Agent:", response.last_message.text)
except FrameworkError as err:
print("Error:", err.explain())
if __name__ == "__main__":
asyncio.run(main())
Source: python/examples/agents/experimental/requirement/handoff.py
Note
To run this example, be sure that you have installed ollama with the granite3.3:8b model downloaded.
To run projects, use:
python [project_name].py
Explore more in our examples for Python and TypeScript.
BeeAI framework is open-source and we ❤️ contributions.
To help build BeeAI, take a look at our:
We use GitHub Issues to manage bugs. 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 know 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.
For information about maintainers, see MAINTAINERS.md.
Special thanks to our contributors for helping us improve BeeAI framework.
Developed by contributors to the BeeAI project, this initiative is part of the Linux Foundation AI & Data program. Its development follows open, collaborative, and community-driven practices.
