OpenSSA is an open-source neurosymbolic agentic AI framework designed to solve complex, high-stakes problems in industries like semiconductor, energy and finance, where consistency, accuracy and deterministic outcomes are paramount.
At the core of OpenSSA is the Domain-Aware Neurosymbolic Agent (DANA) architecture, advancing generative AI from basic pattern matching and information retrieval to industrial-grade problem solving. By integrating domain-specific knowledge with neural and symbolic planning and reasoning, such as Hierarchical Task Planning (HTP) for structuring programs and Observe-Orient-Decide-Act Reasoning (OODAR) for executing such programs, OpenSSA DANA agents consistently deliver accurate solutions, often using much smaller models.
- Consistent and Accurate Results for complex industrial problems
- Scalable Expertise through AI agents incorporating deep domain knowledge from human experts
- Economical and Efficient Computation thanks to usage of small models
- Full Ownership of intellectual property when used with open-source models such as Llama
-
Install with
pip install openssa(Python 3.12 and 3.13)- For bleeding-edge capabilities:
pip install https://github.com/aitomatic/openssa/archive/main.zip
- For bleeding-edge capabilities:
-
Explore the
examples/directory and developer guides and tutorials on our documentation site
We welcome contributions from the community!
- Join discussions on our Community Forum
- Submit pull requests for bug fixes, enhancements and new features
For detailed guidelines, refer to our Contribution Guide.