Claude Memory
Claude Memory Server provides persistent long-term memory storage for AI conversations using SQLite database with full-text search and optional semantic search capabilities through Ollama embeddings. The implementation offers comprehensive memory management tools including storage, retrieval, categorization, and similarity-based search across predefined categories like facts, preferences, conversations, and projects, with support for hybrid text and semantic search algorithms using cosine similarity. Built with TypeScript and the Model Context Protocol SDK, it includes an optional memory hook script for automatically capturing important information from Claude sessions, making it valuable for users who want to maintain context and accumulated knowledge across multiple AI interactions without losing conversational history.
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 2026-09-01.
Scan details: Circle-IR · 2026-09-01 · 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/xiy/claude-memory-server
- Author type
- human
- Last scanned
- 2026-09-01
- Updated
- 2026-09-01
Use via MCP
Resolve Claude 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.