AI Alliance forges agent-native language, knowledge base

"With Dana ( Domain-Aware Neurosymbolic Agent), formally announced in late-June, users get AI-powered programming with intent-driven development, where developers can describe what they want to build and the language will handle the implementation. Dana features native support for agent workflows, memory grounding, and concurrency. Designed to run locally or in the cloud, the language is designed around domain-specific knowledge from human expertise and industry-specific workflows. It leverages large language models (LLMs) with symbolic grounding for deterministic, reliable outputs."

"Semiont, meanwhile, enables humans and agents to co-create shared knowledge. Offering an AI-native wiki, Semiont features high-accuracy context retrieval, according to AI Alliance. Integrating via Model Context Protocol (MCP), Semiont enables locally owned knowledge bases, which are deployable on demand. Other projects from the alliance include Open Trusted Data for AI models and AI agents, as well as the Deep Research agent architecture with MCP."

Dana (Domain-Aware Neurosymbolic Agent) enables intent-driven programming by letting developers describe desired behavior while the language implements it. Dana supports agent workflows, memory grounding, concurrency, and runs locally or in the cloud. The language uses domain-specific human and industry knowledge and combines large language models with symbolic grounding for deterministic outputs. Semiont provides an AI-native wiki for human/agent co-creation with high-accuracy context retrieval and Model Context Protocol (MCP) integration, enabling locally owned, on-demand knowledge bases. Open Trusted Data specifies metadata for provenance, lineage, and utility and catalogs open data sets with trust scores. Deep Research explores production-quality agents accessing data and tools only through MCP servers and plans a reference implementation.

Read at InfoWorld