agents
An open-source, self-evolving autonomous language agent framework oriented toward data.
- Region
- Domestic
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 5.9k
- Source
- GitHub
- Added
- 2026-06-06
- Last verified
- 2026-06-06
Overview
Agents is an open-source, autonomous language agent framework oriented toward data. It trains language agents by mimicking the connectionist learning process of neural networks, enabling agents to self-evolve and optimize. Users can define prompt pipelines to implement loss functions, backpropagation, and weight optimization, thereby training more efficient language agents. Suitable for developers who need to build and optimize complex language processing systems.
Key features
- ▪Self-evolving language agents
- ▪Symbolic learning-based system framework
- ▪Mimics neural network learning processes
- ▪Provides detailed documentation and examples
Use cases
Pros
- +Easy to extend and customize
- +Supports optimization of multi-agent systems
- +Comprehensive documentation and examples
Limitations / notes
- -Requires some programming background
- -Dependent on high-quality prompt design
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
How to install Agents?
Install via pip: pip install git+https://github.com/aiwaves-cn/agents@master
What are the main features of Agents?
Supports self-evolving language agent training and optimization
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.