AI Memory
Production-ready MCP server for semantic memory management that enables AI agents to store, retrieve, and manage contextual knowledge across sessions using PostgreSQL with pgvector for vector similarity search and local Transformers.js embeddings. Features intelligent caching with Redis fallback, multi-agent support through user context isolation, memory relationships for connected knowledge graphs, automatic clustering with DBSCAN algorithm, smart compression for large content, and background job processing with BullMQ for async embedding generation and batch operations. Built with TypeScript and Kysely ORM for type safety, it provides soft deletes, input sanitization, token-efficient responses, and flexible embedding dimensions, making it ideal for AI applications requiring persistent memory, knowledge management systems, and multi-session conversational agents.
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
- Repository
- github.com/scanadi/mcp-ai-memory
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve AI 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.