Fegis
Compiles YAML specifications into semantic LLM tools with structured memory and an emergent knowledge graph.
Acerca de
Fegis is a semantic tool building framework and compiler that transforms YAML specifications—called Archetypes—into structured, reusable tools for large language models (LLMs). Built on the Model Context Protocol (MCP), Fegis compiles each Archetype into schema-validated interfaces, where field names and parameters act as semantic directives that guide content generation. Every tool invocation is preserved in a hybrid memory system combining vector embeddings with structured metadata—forming an emergent knowledge graph that enables persistent memory, semantic retrieval, and exploration of interconnected data.
Características Principales
- Compiles YAML Archetypes into LLM tools.
- Features a hybrid memory system with vector embeddings and structured metadata.
- Provides a semantic programming framework.
- 16 GitHub stars
- Implements the Model Context Protocol (MCP).
- Enables the creation of an emergent knowledge graph.
Casos de Uso
- Creating web exploration interfaces.
- Building thinking frameworks for LLMs.
- Developing optimization systems inspired by biological networks.
Sponsored