An Open-source Framework for Autonomous Language Agents
Project description
An Open-source Framework for Autonomous Language Agents
[📄 Paper] [📄 Doc] [🌐 Website] [🤖️ Demos] [🔥 Discord] [🔥 Wechat Group]
Overview
Agents is an open-source library/framework for building autonomous language agents. The library is carefully engineered to support important features including long-short term memory, tool usage, web navigation, multi-agent communication, and brand new features including human-agent interaction and symbolic control. With Agents, one can customize a language agent or a multi-agent system by simply filling in a config file in natural language and deploy the language agents in a terminal, a Gradio interface, or a backend service.
One major difference between Agents and other existing frameworks for language agents is that our framework allows users to provide fine-grained control and guidance to language agents via an SOP (Standard Operation Process). An SOP defines subgoals/subtasks for the overall task and allows users to customize a fine-grained workflow for the language agents.
📢 Updates
[x] 2023.10.7 Support LLM-based SOP generation🎉🎉🎉🎉
- SOP Generation for Multi-Agent[on Huggingface Space]
- SOP Generation for Single-Agent[on Huggingface Space]
- We recommend strongly that you can create your OWN DEMO by clicking the three dots at the top right and selecting Duplicate this Space on Huggingface Space.
[x] 2023.9.20 Deploy Demos on Huggingface Space
[x] 2023.9.12 Official Release
💡 Highlights
- Long-short Term Memory: Language agents in the library are equipped with both long-term memory implemented via VectorDB + Semantic Search and short-term memory (working memory) maintained and updated by an LLM.
- Tool Usage: Language agents in the library can use any external tools via function-calling and developers can add customized tools/APIs here.
- Web Navigation: Language agents in the library can use search engines to navigate the web and get useful information.
- Multi-agent Communication: In addition to single language agents, the library supports building multi-agent systems in which language agents can communicate with other language agents and the environment. Different from most existing frameworks for multi-agent systems that use pre-defined rules to control the order for agents' action, Agents includes a controller function that dynamically decides which agent will perform the next action using an LLM by considering the previous actions, the environment, and the target of the current states. This makes multi-agent communication more flexible.
- Human-Agent interaction: In addition to letting language agents communicate with each other in an environment, our framework seamlessly supports human users to play the role of the agent by himself/herself and input his/her own actions, and interact with other language agents in the environment.
- Symbolic Control: Different from existing frameworks for language agents that only use a simple task description to control the entire multi-agent system over the whole task completion process, Agents allows users to use an SOP (Standard Operation Process) that defines subgoals/subtasks for the overall task to customize fine-grained workflows for the language agents.
🛠 Installation
Option 1. Build from source
git clone https://github.com/aiwaves-cn/agents.git
cd agents
pip install -e .
Option 2. Install via PyPI
pip install ai-agents
📦 Usage
🛠️ Generate the config file
Option 1. Fill in the config template manually
Modify example/{Muti|Single_Agent}/{target_agent}/config.json
Option 2. Try our WebUI for customizing the config file.
Haven't figured out how to write the JSON file yet? Check out our documentation!
Option 3. Try Huggingface Space for generating the SOP automatically.
- SOP Generation for Multi-Agent[on Huggingface Space]
- SOP Generation for Single-Agent[on Huggingface Space]
- We recommend strongly that you can create your OWN DEMO by clicking the three dots at the top right and selecting Duplicate this Space on Huggingface Space.
🤖️ The Agent Hub
We provide an AgentHub, where you can search for interesting Agents shared by us or other developers, try them out or use them as the starting point to customize your own agent. We encourage you to share your customized agents to help others build their own agents more easily! You can share your customized agents by submitting PRs that adds configs and customized codes here. You can also send us your own config files and codes for customized agents by email, and we will share your examples and acknowledge your contribution in future updates!
📷 Examples and Demos
We have provided exemplar config files, code, and demos for both single-agent and multi-agent systems here.
Web demos
Note
1.Due to massive traffic, our online demos may suffer from long queue time and unstable issues. Please follow our quick start guide) and deploy language agents locally for testing. Or checkout our website. 2.Software Company is unable to generate executable code online, if you wish to generate executable code directly, please run it locally :)
- Customer Service Agent
- Debate[now on Huggingface Space]
- Software Company[now on Huggingface Space]
- Fiction Studio
Contributing to Agents
We appreciate your interest in contributing to our open-source initiative. Please feel free to submit a PR or share your thoughts on how to improve the library in Issues!
Note:
- When running the code, we will download an embedding model, which will cause the code to run slowly. We will adjust it to the API interface later
- Currently, the shopping assistant cannot be used. We will replace the API later. Stay tuned
📚 Documentation
Please check our documentation for detailed documentation of the framework.
⭐ Star History
Citation
If you find our repo useful in your research, please kindly consider cite:
@misc{zhou2023agents,
title={Agents: An Open-source Framework for Autonomous Language Agents},
author={Wangchunshu Zhou and Yuchen Eleanor Jiang and Long Li and Jialong Wu and Tiannan Wang and Shi Qiu and Jintian Zhang and Jing Chen and Ruipu Wu and Shuai Wang and Shiding Zhu and Jiyu Chen and Wentao Zhang and Ningyu Zhang and Huajun Chen and Peng Cui and Mrinmaya Sachan},
year={2023},
eprint={2309.07870},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file ai-agents-0.0.52.tar.gz
.
File metadata
- Download URL: ai-agents-0.0.52.tar.gz
- Upload date:
- Size: 40.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8d0c799e9fdb437f7a776038640efdc8fb61e91b8c1e76d40003713484d3fadc |
|
MD5 | 69cbcba482154fabbca8986144b1c9e2 |
|
BLAKE2b-256 | 6543b22aa3a1c8e5b722bb2dcba949a07c59d83b86e4b69b0200f720e9603465 |
File details
Details for the file ai_agents-0.0.52-py3-none-any.whl
.
File metadata
- Download URL: ai_agents-0.0.52-py3-none-any.whl
- Upload date:
- Size: 42.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 02398f0cdd738ae85fab7ef0e16fadcb645a0d74c7af045cb0fe08a8033588b3 |
|
MD5 | 8b1994ea01a6111c393aaab1a55cf05a |
|
BLAKE2b-256 | c9c1643b1689e7a66a9288e4b418064e9cc702368ea65d56390414fadebb78e7 |