Neural Memory
A knowledge graph-powered memory system that transforms developer interactions into structured entities stored in Neo4j, using Gemini LLM for intelligent extraction of goals, constraints, preferences, pain points, and strategies from natural language requests. The system provides context-aware retrieval through graph traversal, fulltext search, and impact analysis to help AI assistants maintain long-term project memory and understand relationships between code artifacts, user preferences, and project objectives. Built with FastMCP and designed for IDE integration, it enables persistent knowledge accumulation across coding sessions while supporting code indexing, entity linking, and automated relationship inference.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/hexecu/mcp-neuralmemory
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Neural 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.