AgentKits Memory
AgentKits Memory provides persistent memory capabilities for AI coding assistants through a comprehensive MCP server implementation that captures, stores, and retrieves project context across coding sessions. Built by AityTech, it automatically hooks into Claude Code sessions to capture tool usage observations, decisions, and patterns, storing them in a local SQLite database with optional vector search capabilities using offline embeddings via Transformers.js. The system includes hybrid search combining keyword and semantic similarity, token economics tracking to measure memory ROI, and multiple interfaces including CLI tools, web viewer, and direct MCP integration.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · 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/aitytech/agentkits-memory
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve AgentKits 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.