Neo4j plugins

Apply 33 structured reasoning frameworks — Bayesian analysis, root cause investigation, decision matrices, pre-mortems, and strategic planning — directly inside Claude Code to improve forecasts, valuations, architectural decisions, and problem-solving rigor.

Provides agent skills for comprehensive Neo4j database management: querying, modeling, data ingestion, AI/ML pipelines (GraphRAG, embeddings), graph algorithms, provisioning, security, and performance tuning.

Turn an Obsidian vault into an AI-powered second brain with daily journaling, health-metric tracking, knowledge graph generation, pattern recognition, and meeting workflows — all orchestrated through Claude Code skills and commands.

Develop and manage Memgraph graph databases: write Cypher queries with Memgraph-specific extensions, build custom query modules in C++, Python, or Rust, design graph data models, configure triggers and storage, run graph algorithms, and build GraphRAG systems with hybrid retrieval.

Consult a senior DBA for expert guidance on schema design, database selection from 230+ engines (SQL/NoSQL/vector/time-series/streaming), query optimization, performance troubleshooting, HA/replication setup, migrations, security hardening, monitoring/alerting, capacity planning, backups/recovery, and IaC with Terraform/Kubernetes across relational, document, graph, and cloud-native databases.

Persists deterministic, team-accessible memory across Claude Code sessions with bi-temporal facts, RBAC, and zero-LLM recall. Installs a local MCP server backed by Postgres, Neo4j, and Pinecone, and automatically records file changes, commands, and session summaries.

Run local MCP servers to query Neo4j graph databases with Cypher, traverse graphs, inspect schemas, manipulate data, manage Aura cloud instances, store and retrieve memory, and design graph schemas using your credentials.

Run a full research pipeline that turns any topic into a compact expertise artifact: builds a question tree, discovers and fetches sources to disk (zero context cost), indexes to .mv2, and distills knowledge — all without raw content entering the LLM context. Also executes Python in isolated Docker containers for data analysis, DSPy sub-agents, and REPL-based prototyping.