AMP (Agent Memory Protocol)
AMP (Agent Memory Protocol) provides AI agents with persistent memory capabilities through a three-layer architecture mimicking human cognition: short-term memory for immediate context, long-term memory for consolidated insights, and a graph layer for entity relationships. Built with SQLite for storage and FastEmbed for local embeddings, it features hybrid vector and full-text search without requiring cloud APIs. Includes an interactive web dashboard with real-time semantic cluster visualization using D3.js physics simulation, showing how memory nodes cluster by meaning and topological connections between related concepts. Supports natural language querying with relevance scoring and memory consolidation processes that move thoughts from working memory to long-term storage.
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/akshayaggarwal99/amp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve AMP (Agent Memory Protocol) 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.