neo4j
tool judged 0% likely a named technique or architecture
See how it has spread across media tiers
Mentions over time
Table view
| Week | Articles | Sources |
|---|---|---|
| 2025-W24 | 1 | 1 |
| 2026-W09 | 1 | 1 |
| 2026-W11 | 1 | 1 |
| 2026-W29 | 4 | 1 |
| 2026-W30 | 1 | 1 |
| 2026-W31 | 3 | 1 |
| 2026-W32 | 1 | 1 |
| 2026-W33 | 2 | 1 |
| 2026-W34 | 2 | 1 |
| 2026-W35 | 1 | 1 |
| 2026-W36 | 4 | 1 |
| 2026-W37 | 2 | 1 |
| 2026-W38 | 3 | 1 |
| 2026-W39 | 1 | 1 |
| 2026-W40 | 3 | 2 |
In their words
Your data lives in a graph database such as Neo4j , as nodes.
Neo4j has built a broad library of documented, working integrations across the agent frameworks agent platforms you’re already building on: AWS, Google, Microsoft, Vercel, Salesforce, and more.
Today, we are announcing the upcoming release to general availability (GA) of Document Intelligence in Neo4j AuraDB on the Free, Professional, and Business Critical tiers.
With Neo4j Agent Memory , a simple function can bring together relevant short-term, long-term, and reasoning memory from the context graph for the current query: context = await client.get_context( query=user_message, session_id=session_id, limit=5, ) As the interaction continues, the agent stores new messages, facts, tool activity, and reasoning traces in the context graph for later use.
From memory to behavior: skills, user profiles, and the consolidation loop was originally published in Neo4j Developer Blog on Medium, where people are continuing the conversation by highlighting and responding to this story.
In our benchmarks, Neo4j 2026.09 delivers approximately both five times better throughput and also query latency than Neo4j 2026.08.
And it’s what we set out to solve at Neo4j.
Navigating an existing Neo4j knowledge graph, with real data, real schema, a task where you can see whether the thing actually works or just sounds convincing.