The software ecosystem that comes with Jaseci allows a developer to simply articulate the design of a sophisticated AI product while abstracting away and automating the construction of production-grade, scalable, cloud software.
The mission of Jaseci is to accelerate and democratize the development and deployments of end-to-end scalable AI applications. To this end, Jaseci presents a novel set of higher level abstractions for programming sophisticated software in a micro-service/serverless AI and a full stack architecture and programming model that abstracts away and automates much of the complexity of building applications on a distributed compute substrate of potentially thousands of compute nodes. The design of Jaseci includes two major innovations.
Imagine an intuitive programming language used to wield a scalable eco-system of optimized AI models appearing as simple as add, subtract, multiply and divide operations in traditional programming languages.
Jaseci moves away from functions and classes and embraces multi-dimensional graphs as intuitive representations of the complex data structures of modern AI applications. The locality information of your application’s data is inherently encoded in graph nodes and edges.
Jaseci also supports the agent-oriented programming approach. Model your agents using walker classes, give them abilities and put them to work in a graph-based environment.
Jaseci automatically generates RESTful API endpoints and other SDK libraries interface based on the Walkers defined in your application’s Jac code. Without having to worry about the complexity of web service frameworks like Django or Flask, developers can focus their energy on building the best AI features.
Jaseci provides out-of-box production-grade containerization and orchestration so you can stand up a production-ready stack in minutes. With novel load balancing and facilitation techniques, your production Jaseci cluster scales intelligently with your application’s demand.
Jaseci is a completely open source ecosystem that you can build on to include additional specialized libraries and engines to suit your needs for personal use or that of your clients.