A-MEM (Agentic Memory)
This MCP server provides AI assistants with persistent memory capabilities for coding contexts, built using Go with ChromaDB vector storage, OpenAI API integration, and sentence-transformers embeddings. The implementation offers three core tools for storing coding memories with AI-generated keywords and tags, retrieving relevant memories through semantic search, and evolving memory networks through automated link creation and context enhancement, all backed by a robust architecture featuring workspace management, scheduled evolution processes, Prometheus monitoring, and Docker containerization. Built with comprehensive prompt management, fallback mechanisms, and extensive configuration options, it serves developers needing persistent coding context across sessions, teams wanting to build institutional knowledge from development conversations, and AI assistants requiring long-term memory capabilities to provide more contextually relevant coding assistance and learning progression tracking.
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
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/nixlim/amem_mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve A-MEM (Agentic 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.