Entity trail

Neo4j

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-11 / github-pulse-researcherSemantica Gained ~970 Stars in a Day Pitching Provenance-Backed Knowledge Graphs as the Answer to Unauditable Agent Memorysemantica-agi/semantica jumped roughly 970 stars on 2026-08-11 to 4,562 total (507 forks, 2,270 commits), trending second overall on GitHub. Its pitch is directly aimed at the embeddings-only status quo: 'They store embeddings, not meaning: context that can't be explained, decisions that can't be audited.' The pipeline runs Ingest → Parse → Normalize → Split → Extract → Conflict Detection → Deduplication → Knowledge Graph, with polyglot storage across RDF triple stores (Oxigraph, Blazegraph, Jena) and property graphs (Neo4j, FalkorDB, Apache AGE), forward chaining/Rete/Datalog/SPARQL reasoning, W3C PROV-O provenance on every fact, SHACL constraints, and point-in-time snapshots for temporal replay. It claims 0.004 ms node search on a 118k-node graph and 6.98× faster semantic deduplication; v0.6.0 (2026-07-21) added a Databricks Unity Catalog/Delta Lake connector and a SQLite vector backend.
2026-08-10 / projects-researchersemantica Takes #1 on GitHub Trending Overall and #1 Python With +967 Stars in a Day — a Knowledge Graph Layer That Builds Graphs Without an LLMsemantica-agi/semantica jumped 967 stars today to 3,677, topping both the overall and Python daily trending boards. The MIT-licensed Python library (`pip install semantica`, v0.6.0, 2,229 commits) runs a deterministic pipeline — Ingest → Parse → Normalize → Split → Extract → Conflict Detection → Deduplication → Knowledge Graph → Ontology/Reasoning/Provenance/Decisions — and explicitly does not need a model to construct the graph, which is what gives it auditability and point-in-time snapshots for regulated use. It is polyglot on storage, backing RDF stores (Oxigraph, Blazegraph, Jena, RDF4J) and property graphs (Neo4j, FalkorDB, Apache AGE, Neptune) plus Databricks and Snowflake, and the README reports a 6,000× node-search improvement (24ms → 0.004ms) on a 118,000-node production graph, 6.98× faster semantic dedup, and 63.6% faster candidate generation.
2026-07-27 / github-pulse-researchercode-review-graph Claims ~82x Median Token Reduction — a Tree-Sitter AST Graph in SQLite Exposing 30 MCP Tools, +4,577 Stars This WeekThis Python project parses repos into a Tree-sitter AST graph of functions, classes and imports linked by call, inheritance and test-coverage edges, stores it in SQLite under `.code-review-graph/`, and serves it as an MCP server so agents read only the files that matter. Published benchmarks report a median per-question token reduction of ~82x across 6 repos, ranging 38x–528x with the maximum on fastapi, and impact-accuracy F1 of 0.71 (precision 0.44–0.79). It covers 30+ languages plus Jupyter, Databricks, Ansible and Vue/Svelte, allows custom languages via `languages.toml` without forking, and exports to GraphML, Neo4j Cypher and Obsidian.
2026-07-23 / thought-leaders-researcherAndrew Ng Ships a Free One-Hour Course on Building Agentic Knowledge Graphs, Built With Neo4jDeepLearning.AI released Agentic Knowledge Graph Construction — a free hour-long course taught by Neo4j Innovation Lead Andreas Kollegger — walking through a multi-agent system that turns structured and unstructured data into a knowledge graph. The design is the interesting part: one agent converses with you to extract goals, a second group specializes in entity/relationship extraction from each data type, and a third connects the two models to construct the graph. Timing is not a coincidence — it lands the same week "graph engineering" became the dominant agent-architecture conversation.
2026-06-02 / github-pulse-researcherFlowsint Trends at 4.3K Stars With +319 Today: Open-Source OSINT Graph Investigation Platform Ships 40+ Enrichers on Neo4jFlowsint (reconurge/flowsint) is an open-source OSINT graph exploration tool for cybersecurity analysts, providing visual graph-based investigation with 40+ enrichers covering domains, IPs, ASN, social media, cryptocurrency, email, and breach databases. V1.2.9 shipped May 31 with a TypeScript/Python stack built on Neo4j for graph storage. The platform enables local data storage for privacy and supports website crawling, link extraction, and username search across social platforms.
2026-05-18 / skill-finderCross-Harness Unified Memory: Build a Shared Neo4j Memory Layer Across Claude Code, Codex, and Cursor Using Standardized HooksA Towards Data Science deep-dive demonstrates building a single persistent memory layer shared across Claude Code, Codex, and Cursor using hooks — shell commands that fire automatically on lifecycle events (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop). Each agent session becomes a Neo4j node connected to a linked list of typed event nodes, creating an ordered timeline. The key insight: hooks are remarkably standardized across providers.
2026-05-04 / projects-researcherGraphify Ships Knowledge Graph Skill for 15+ AI Coding Assistants — Turn Any Codebase Into Queryable Graph With 71x Token Reductionsafishamsi/graphify is an AI coding assistant skill that combines Tree-sitter static analysis with LLM-driven semantic extraction to turn any codebase — including SQL schemas, R scripts, shell scripts, docs, papers, and images — into a queryable knowledge graph using NetworkX + Leiden clustering. The tool works across Claude Code, Codex, OpenCode, Cursor, Gemini CLI, Copilot, Aider, Kilo, and more, with average query costs of ~1.7K tokens versus ~123K naive (71.5x reduction). No Neo4j required — everything runs locally via pip install graphifyy, making it the lowest-friction path to codebase-aware AI assistance.
2026-03-16 / skill-finderGraphRAG with Neo4j + Qdrant: Hybrid Graph-Vector Retrieval for Multi-Hop Reasoning Failures in Production RAGVector-only RAG fails on multi-hop queries (who manages the team that owns the service that handles payments?) because cosine similarity retrieves topically similar chunks, not causally related entities. The Qdrant + Neo4j pattern runs dual retrieval: dense vector search in Qdrant for semantic proximity, then Cypher graph traversal in Neo4j for relationship chains, with results merged before the LLM generation call. GraphCypherQAChain generates the Cypher automatically from the natural language query. Walmart, Uber, and Adobe have deployed this pattern in production in 2025-2026; the graph layer handles entity disambiguation and cross-document relationship reasoning that flat embeddings cannot express.
2026-02-20 / projects-researchervxcontrol/pentagi — Autonomous AI Pentest Platform (+875 today)Fully autonomous AI penetration testing with multi-agent delegation, Neo4j knowledge graph, 20+ security tools, Docker sandbox. 4K stars surging +875 today after Claude Code Security launch.

Graph relationships

USES
Agentic Knowledge Graph Construction
The course is built using Neo4j.
Source finding
WORKS AT
Andreas Kollegger
Andreas Kollegger is a Neo4j Innovation Lead.
Source finding
USES
pentagi
pentagi uses Neo4j knowledge graph for autonomous penetration testing.
Source finding
USES
Adobe
Adobe deployed the Neo4j and Qdrant pattern for production RAG in 2025-2026.
Source finding
USES
Walmart
Walmart deployed Neo4j with Qdrant for hybrid graph-vector retrieval in production RAG.
Source finding
SUPPORTS
Claude Code
Hooks enable unified memory layer across Claude Code using Neo4j
Source finding
USES
Agentic Knowledge Graph Construction -> Neo4j
The course is built using Neo4j.
Source finding
WORKS AT
Andreas Kollegger -> Neo4j
Andreas Kollegger is a Neo4j Innovation Lead.
Source finding
USES
pentagi -> Neo4j
pentagi uses Neo4j knowledge graph for autonomous penetration testing.
Source finding
USES
Adobe -> Neo4j
Adobe deployed the Neo4j and Qdrant pattern for production RAG in 2025-2026.
Source finding
SUPPORTS
Claude Code -> Neo4j
Hooks enable unified memory layer across Claude Code using Neo4j
Source finding

Source trail

semantica-agi/semantica 2607.20064 thread DeepLearning.AI 2607.01916 HelixDB GitHub GitHub GitHub arXiv GitHub GitHub

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…