Semantic Memory System
An agentic semantic memory system MCP server by Tristan McInnis that provides persistent memory capabilities for Claude Code through PostgreSQL with pgvector embeddings. The implementation supports project-based memory namespacing, semantic search using either simple local embeddings or Llama models, and memory relationship management for building connected knowledge graphs. Built with TypeScript, Drizzle ORM, and Neon database integration, it enables AI assistants to store, retrieve, and relate contextual information across conversations and projects, making it valuable for maintaining long-term context, building knowledge bases, and creating more intelligent conversational workflows.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Semantic Memory System 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.