Inferable
Open-source platform for creating AI agents with humans in the loop
About
Inferable is an open-source platform designed for building production-ready AI agents. It offers a delightful developer experience, enabling fast-moving engineering teams to go from zero to production in hours using its SDKs. The platform focuses on providing deterministic controls that wrap existing functions and APIs, allowing for customizable agents without codebase modifications. Key features include distributed function orchestration, human-in-the-loop capabilities, on-premise execution, and built-in observability. Inferable supports Node.js, Golang, and C# SDKs, with more languages planned. It's designed for enterprise use, adapting to existing architectures, allowing for the use of custom models, and offering managed cloud services with auto-scaling and high availability. The platform is completely open-source and self-hostable.
Features & Capabilities
- —Build customizable AI agents without modifying your codebase.
- —Manage agent state and execution deterministically.
- —Utilize a distributed message queue for scalable and reliable automations.
- —Integrate human-in-the-loop capabilities for complex tasks.
- —Leverage SDKs for rapid development across multiple languages.
- —Utilize a built-in ReAct agent for complex problem-solving.