FEGIS (Schema-Driven Memory)
FEGIS is a schema-driven memory engine that gives LLMs cognitive tools and structured persistent memory. Developed by Perry Golden, it uses Qdrant vector database with FastEmbed for efficient storage and retrieval of information based on predefined archetypes. The system allows models to create, store, and search through structured cognitive artifacts like thoughts, reflections, and decisions using a facet-based organization system. This implementation enables LLMs to maintain context across conversations, build knowledge bases with qualitative dimensions, and create meaningful connections between related ideas - making it particularly valuable for applications requiring persistent memory and structured thinking.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/p-funk/fegis
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve FEGIS (Schema-Driven Memory) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.