{"slug": "neo4j", "name": "Neo4j", "category": "databases", "category_name": "Databases", "description": "", "recommenders": 4, "commenters": 17, "warners": 2, "score": 3.81, "rising": -1.31, "first": "2025-11-13", "latest": "2026-07-31", "why": "you are better off just using JOINs or switch to Neo4j for your graph workloads.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 13, "compare": 1, "warn": 2}, "spark": [2, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "you are better off just using JOINs or switch to Neo4j for your graph workloads.", "kind": "", "icon": true, "domain": "neo4j.com", "github_repo": null, "official_url": "https://neo4j.com", "pricing": "", "aliases": ["Neo4j"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 773741842, "item_id": 48358865, "url": "https://news.ycombinator.com/item?id=48358865", "by": "CharlieDigital", "date": "2026-06-01", "stance": "recommend", "quote": "you are better off just using JOINs or switch to Neo4j for your graph workloads.", "excerpt": "> ...add something like apache AGE, but arguably that is also a small ecosystem (at least IMHO as I never heard it until I actually started looking for Neo4J alternatives) Outside of the most trivial use cases, I've found that AGE will not get anywhere near Neo4j in terms of performance and there's a lot of edge cases that just flat out won't work. The interesting types of queries you'd want to do in the graph end up", "context": "", "use_case": "", "switched_from": "", "story": "Benchmarking SurrealDB 3.x vs. Postgres, Mongo, Neo4j and Redis (With Fsync)"}, {"id": 749724546, "item_id": 46857784, "url": "https://news.ycombinator.com/item?id=46857784", "by": "kirin_memorang", "date": "2026-02-02", "stance": "recommend", "quote": "Our stack is awesome:", "excerpt": "Memorang (Vercel + Shopify for EdTech) | Full-Time | Hybrid - Los Angeles Our mission is to automate learning. We're building the AI stack for education\u2014combining knowledge graphs, agents, and apps so enterprises can build curricula and learning products at scale. We bootstrapped to profitability (now VC-backed), won #1 (of 1,500) in the Vercel AI Accelerator, and have powered 200MM+ assessments for credentialing org", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who is hiring? (February 2026)"}, {"id": 738046805, "item_id": 46127925, "url": "https://news.ycombinator.com/item?id=46127925", "by": "arthurcolle", "date": "2025-12-02", "stance": "recommend", "quote": "Neo4j, Postgres, Redis, K8s", "excerpt": "Location: Washington, D.C. (open to relocation, but preference to initial remote period) Remote: Yes Willing to relocate: Yes (June 2026 and beyond) Technologies: Python, Rust, Elixir | Neo4j, Postgres, Redis, K8s | PyTorch, MLX, LoRA/QLoRA, Modal A100s, H100s | FastAPI, Phoenix, Rails R\u00e9sum\u00e9/CV: https://linkedin.com/in/arthurcolle Email: arthur@distributed.systems Background: Deep knowledge of OpenAI, Anthropic + LL", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (December 2025)"}, {"id": 737465252, "item_id": 46091578, "url": "https://news.ycombinator.com/item?id=46091578", "by": "gregorydickson", "date": "2025-11-29", "stance": "recommend", "quote": "Neo4j - when you need scale", "excerpt": "I built this because Claude Code keeps forgetting what it learned. Every session I'd re-explain the architecture, re-discover the same bugs, re-learn the same solutions. CLAUDE.md helps but it's manual and doesn't capture relationships between things. memory-graph is an MCP server that stores entities, observations, and relationships in a knowledge graph. The key insight: coding agents need to remember what solved pr", "context": "", "use_case": "Graph database backend", "switched_from": "", "story": "Memory-Graph \u2013 Knowledge Graph Memory for Claude Code with SQLite/Neo4j/Memgraph"}, {"id": 734675570, "item_id": 45917223, "url": "https://news.ycombinator.com/item?id=45917223", "by": "kirin_memorang", "date": "2025-11-13", "stance": "recommend", "quote": "Our stack is awesome: Vercel, Supabase, Neo4j, Langchain, Expo", "excerpt": "# Memorang (Vercel + Shopify for EdTech) | Full-Time | Remote # Our mission is impactful: To build the \"AI stack for education.\" Our platform combines knowledge graphs, agents, and apps to provide an all-in-one toolkit to rapidly launch new content and apps. We bootstrapped to profitability, won the inaugural Vercel AI Accelerator (out of 1,500 startups), and now power the official content and apps for career sectors", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who is hiring? (November 2025)"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 748751233, "item_id": 46796952, "url": "https://news.ycombinator.com/item?id=46796952", "by": "remy_boutonnet", "date": "2026-01-28", "stance": "warn", "quote": "Neo4j\u2019s record-oriented model performs reasonably for short traversals but degrades sharply on long paths", "excerpt": "***Benchmark summary (TuringDB vs Neo4j)*** We benchmarked TuringDB against Neo4j using the Reactome biological knowledge graph, which is a real-world, highly connected dataset (millions of nodes/edges, deep traversal patterns). - Both systems were run out of the box, cold start. - No manual indexing, tuning, or query rewriting on either side. - Same logical queries, same dataset. - Benchmarks are reproducible via an", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: TuringDB \u2013 The fastest analytical in-memory graph database in C++"}]}], "who": [{"by": "swarcs", "context": "Java software architect, 20+ years; runs SWARCS as B2B contractor", "url": "https://news.ycombinator.com/item?id=48760449", "date": "2026-07-02"}, {"by": "Amarnadh_Dodda", "context": "Master's student in Software Engineering; job seeker", "url": "https://news.ycombinator.com/item?id=47652140", "date": "2026-04-05"}], "tags": [], "use_cases": ["graph database", "graph database for recommendations", "side project: transcript entity graph", "real-time data pipeline", "graph visualization", "backend stack"], "compared": [{"slug": "postgresql", "name": "PostgreSQL", "co": 6, "switched_from": 0, "switched_to": 0}, {"slug": "kubernetes", "name": "Kubernetes", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "redis", "name": "Redis", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "modal", "name": "Modal", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "ruby-on-rails", "name": "Ruby on Rails", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "fastapi", "name": "FastAPI", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "pytorch", "name": "PyTorch", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=46108941", "title": "Ask HN: Who is hiring? (December 2025)", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49124658", "title": "Algorithms on billion-scale graph using 10GB RAM: I love DataFusion", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48902026", "title": "YouTrackDB is a general-use object-oriented graph database", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48782672", "title": "How Memgraph 3.11 Simplifies Multi-Tenancy for Cross-Database Graph Workloads", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48747975", "title": "Ask HN: Who wants to be hired? (July 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48323844", "title": "Benchmarking SurrealDB 3.x vs. Postgres, Mongo, Neo4j and Redis (With Fsync)", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 2, "neutral": 1}, "2025-12": {"neutral": 2, "recommend": 1}, "2026-01": {"neutral": 3, "warn": 1}, "2026-02": {"recommend": 1, "neutral": 2}, "2026-03": {"neutral": 2}, "2026-04": {"neutral": 1}, "2026-05": {}, "2026-06": {"recommend": 1}, "2026-07": {"neutral": 2, "warn": 1, "compare": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 786035297, "item_id": 49127206, "url": "https://news.ycombinator.com/item?id=49127206", "by": "lmeyerov", "date": "2026-07-31", "stance": "compare", "quote": "benchmarks vs neo4j, memgraph, kuzu, etc", "excerpt": "Related, we recently release the polars version of GFQL, the only oss cypher property graph query engine for CPU+GPU, and even better, no database nor outside process needed. We started doing LDBC benchmarks vs neo4j, memgraph, kuzu, etc, and are already starting to outperform them both on latency for small OLTP graph searches and $, speed for big graph OLAP ones, especially in GPU mode. The cool in the original post", "context": "", "use_case": "", "switched_from": "", "story": "Algorithms on billion-scale graph using 10GB RAM: I love DataFusion"}, {"id": 782483680, "item_id": 48905230, "url": "https://news.ycombinator.com/item?id=48905230", "by": "codelikeawolf", "date": "2026-07-14", "stance": "neutral", "quote": "load them into a Neo4j database (via Cypher queries)", "excerpt": "I'm a bit of a Forensic Files nerd, so I worked on a little side project a while back to pull the transcripts from several episodes, use entity recognition to categorize people, places, things, etc, and load them into a Neo4j database (via Cypher queries). It turns out there's something called the POLE data model[1] that can be used by law enforcement to help solve crimes. You load all the details into a graph databa", "context": "", "use_case": "Side project: transcript entity graph", "switched_from": "", "story": "YouTrackDB is a general-use object-oriented graph database"}, {"id": 780572865, "item_id": 48785804, "url": "https://news.ycombinator.com/item?id=48785804", "by": "mbuda", "date": "2026-07-04", "stance": "warn", "quote": "", "excerpt": "Memgraph's CTO here, thanks for the feedback under Memgraph's implementation of multi-tenancy each database is isolated, meaning that vector search indices are also isolated per database (each db has it's own set of vector indices) the same limitations apply as to multi-tenancy or vector search (e.g. multitenancy includes some kind of routing, but that's minimal overhead because database is picked per session; import", "context": "", "use_case": "", "switched_from": "Neo4j", "story": "How Memgraph 3.11 Simplifies Multi-Tenancy for Cross-Database Graph Workloads"}, {"id": 780167191, "item_id": 48760449, "url": "https://news.ycombinator.com/item?id=48760449", "by": "swarcs", "date": "2026-07-02", "stance": "neutral", "quote": "Neo4j", "excerpt": "Location: Novi Sad, Serbia (Europe) Remote: Yes (CET/GMT+2, highly experienced with US time zones) Willing to relocate: No Technologies: Java (Modern LTS / JDK 21-26), Spring Boot/Cloud, PostgreSQL, Apache Kafka, Kubernetes (MicroK8s), Elasticsearch, Neo4j, Redis, Hibernate, Linux, Infrastructure & Platform Engineering. Website: https://swarcs.com GitHub: https://github.com/boskomijin LinkedIn: https://linkedin.com/i", "context": "Java software architect, 20+ years; runs SWARCS as B2B contractor", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (July 2026)"}, {"id": 773741842, "item_id": 48358865, "url": "https://news.ycombinator.com/item?id=48358865", "by": "CharlieDigital", "date": "2026-06-01", "stance": "recommend", "quote": "you are better off just using JOINs or switch to Neo4j for your graph workloads.", "excerpt": "> ...add something like apache AGE, but arguably that is also a small ecosystem (at least IMHO as I never heard it until I actually started looking for Neo4J alternatives) Outside of the most trivial use cases, I've found that AGE will not get anywhere near Neo4j in terms of performance and there's a lot of edge cases that just flat out won't work. The interesting types of queries you'd want to do in the graph end up", "context": "", "use_case": "", "switched_from": "", "story": "Benchmarking SurrealDB 3.x vs. Postgres, Mongo, Neo4j and Redis (With Fsync)"}, {"id": 762434243, "item_id": 47652140, "url": "https://news.ycombinator.com/item?id=47652140", "by": "Amarnadh_Dodda", "date": "2026-04-05", "stance": "neutral", "quote": "Developed a real-time data pipeline with Kafka + Neo4j", "excerpt": "Location: Phoenix, AZ (open to US roles) Remote: Yes Willing to relocate: Yes Technologies: Python, SQL (PostgreSQL), Apache Airflow, Kafka, Spark, AWS (S3), Azure, Docker, Kubernetes, React, Node.js, Neo4j, Supabase, Vector DBs (pgvector), REST APIs Resume/CV: https://drive.google.com/file/d/1rOI_TsGfxGi6WLB5tXA47AqHG5gy7auE/view About me: I\u2019m a Master\u2019s student in Software Engineering at ASU (GPA: 4.0) with hands-o", "context": "Master's student in Software Engineering; job seeker", "use_case": "Real-time data pipeline", "switched_from": "", "story": "Ask HN: Who wants to be hired? (April 2026)"}, {"id": 758738336, "item_id": 47421146, "url": "https://news.ycombinator.com/item?id=47421146", "by": "kingcauchy", "date": "2026-03-17", "stance": "neutral", "quote": "I guessed that neo4j gets this question a lot", "excerpt": "I guessed that neo4j gets this question a lot so I went to see if they had a good blog post and this one is pretty good https://neo4j.com/blog/cypher-and-gql/10-things-you-can-do-with-cypher/", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Antfly: Distributed, Multimodal Search and Memory and Graphs in Go"}, {"id": 756929665, "item_id": 47308104, "url": "https://news.ycombinator.com/item?id=47308104", "by": "btylke", "date": "2026-03-09", "stance": "neutral", "quote": "building a full graph of each component in Neo4j", "excerpt": "I'm developing a system that uses graph differentials to understand what has changed between library versions and upgrades the target system without breaking things. [0] Because source isn\u2019t always available, it scans the bytecode of an application and the new library, building a full graph of each component in Neo4j to determine what breaking changes impact the target application. This is then translated into ticket", "context": "", "use_case": "Graph database", "switched_from": "", "story": "Ask HN: What Are You Working On? (March 2026)"}, {"id": 753249907, "item_id": 47078119, "url": "https://news.ycombinator.com/item?id=47078119", "by": "elvismdev", "date": "2026-02-19", "stance": "neutral", "quote": "Optional Neo4j adds a knowledge graph", "excerpt": "Author here. I built this because Claude Code's built-in memory (CLAUDE.md, Auto Memory, Session Memory) works well for static rules and compressed summaries, but loses the detailed reasoning behind decisions between sessions. The server uses mem0ai as a library, Qdrant for vector storage, and Ollama for local embeddings (bge-m3, 1024 dims). Optional Neo4j adds a knowledge graph. Everything including the LLM fact ext", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Giving Claude Code persistent memory with a self-hosted MCP server"}, {"id": 749862480, "item_id": 46866405, "url": "https://news.ycombinator.com/item?id=46866405", "by": "arthurcolle", "date": "2026-02-02", "stance": "neutral", "quote": "Neo4j, Postgres, Redis, K8s", "excerpt": "Location: Washington, D.C. (open to relocation, but preference to initial remote period) Remote: Yes Willing to relocate: Yes (June 2026 and beyond) Technologies: Python, Rust, Elixir | Neo4j, Postgres, Redis, K8s | PyTorch, MLX, LoRA/QLoRA, Modal A100s, H100s | FastAPI, Phoenix, Rails R\u00e9sum\u00e9/CV: https://linkedin.com/in/arthurcolle Email: arthur@distributed.systems Background: Deep knowledge of OpenAI, Anthropic + LL", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (February 2026)"}, {"id": 749724546, "item_id": 46857784, "url": "https://news.ycombinator.com/item?id=46857784", "by": "kirin_memorang", "date": "2026-02-02", "stance": "recommend", "quote": "Our stack is awesome:", "excerpt": "Memorang (Vercel + Shopify for EdTech) | Full-Time | Hybrid - Los Angeles Our mission is to automate learning. We're building the AI stack for education\u2014combining knowledge graphs, agents, and apps so enterprises can build curricula and learning products at scale. We bootstrapped to profitability (now VC-backed), won #1 (of 1,500) in the Vercel AI Accelerator, and have powered 200MM+ assessments for credentialing org", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who is hiring? (February 2026)"}, {"id": 748751233, "item_id": 46796952, "url": "https://news.ycombinator.com/item?id=46796952", "by": "remy_boutonnet", "date": "2026-01-28", "stance": "warn", "quote": "Neo4j\u2019s record-oriented model performs reasonably for short traversals but degrades sharply on long paths", "excerpt": "***Benchmark summary (TuringDB vs Neo4j)*** We benchmarked TuringDB against Neo4j using the Reactome biological knowledge graph, which is a real-world, highly connected dataset (millions of nodes/edges, deep traversal patterns). - Both systems were run out of the box, cold start. - No manual indexing, tuning, or query rewriting on either side. - Same logical queries, same dataset. - Benchmarks are reproducible via an", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: TuringDB \u2013 The fastest analytical in-memory graph database in C++"}, {"id": 745965360, "item_id": 46622835, "url": "https://news.ycombinator.com/item?id=46622835", "by": "jberto", "date": "2026-01-14", "stance": "neutral", "quote": "the Neo4j-based graph behind personalization", "excerpt": "Adobe | Senior Software Engineer (Behance \u2013 Graph & Recommendations) | $173,500 \u2013 $331,050 base (US) | Full-time | New York, NY (onsite) / Remote-friendly (US) Behance is Adobe\u2019s network for creatives. We\u2019re hiring a senior backend/graph engineer to own and evolve recommended content, creator discovery, and the social networking graph across Behance and other flagship Adobe products. You will: - Design, build, and op", "context": "", "use_case": "Graph database for recommendations", "switched_from": "", "story": "Ask HN: Who is hiring? (January 2026)"}, {"id": 745354609, "item_id": 46584663, "url": "https://news.ycombinator.com/item?id=46584663", "by": "akshay326", "date": "2026-01-11", "stance": "neutral", "quote": "created a 3D Neo4J visualizer tool for YC advice + my quotes collection", "excerpt": "This is pretty cool, I wanted to do something with my Readwise Reader too. Jinx today claude code created a 3D Neo4J visualizer tool for YC advice + my quotes collection. Code here - https://github.com/akshay326/quote-viz", "context": "", "use_case": "graph visualization", "switched_from": "", "story": "Show HN: I used Claude Code to discover connections between 100 books"}, {"id": 743540992, "item_id": 46471312, "url": "https://news.ycombinator.com/item?id=46471312", "by": "arthurcolle", "date": "2026-01-02", "stance": "neutral", "quote": "Neo4j", "excerpt": "Location: Washington, D.C. (open to relocation, but preference to initial remote period) Remote: Yes Willing to relocate: Yes (June 2026 and beyond) Technologies: Python, Rust, Elixir | Neo4j, Postgres, Redis, K8s | PyTorch, MLX, LoRA/QLoRA, Modal A100s, H100s | FastAPI, Phoenix, Rails R\u00e9sum\u00e9/CV: https://linkedin.com/in/arthurcolle Email: arthur@distributed.systems Background: Deep knowledge of OpenAI, Anthropic + LL", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (January 2026)"}, {"id": 738467776, "item_id": 46154236, "url": "https://news.ycombinator.com/item?id=46154236", "by": "jberto", "date": "2025-12-04", "stance": "neutral", "quote": "Design, build, and operate the Neo4j-based graph behind personalization, discovery, and monetization.", "excerpt": "Adobe | Senior Software Engineer (Behance \u2013 Graph & Recommendations) | $170,500 \u2013 $320,000 base (US) | Full-time | New York, NY (onsite) / Remote-friendly (US) Behance is Adobe\u2019s network for creatives. We\u2019re hiring a senior backend/graph engineer to own and evolve recommended content, creator discovery, and the social networking graph across Behance and other flagship Adobe products. You will: - Design, build, and op", "context": "", "use_case": "Graph database for recommendations", "switched_from": "", "story": "Ask HN: Who is hiring? (December 2025)"}, {"id": 738046805, "item_id": 46127925, "url": "https://news.ycombinator.com/item?id=46127925", "by": "arthurcolle", "date": "2025-12-02", "stance": "recommend", "quote": "Neo4j, Postgres, Redis, K8s", "excerpt": "Location: Washington, D.C. (open to relocation, but preference to initial remote period) Remote: Yes Willing to relocate: Yes (June 2026 and beyond) Technologies: Python, Rust, Elixir | Neo4j, Postgres, Redis, K8s | PyTorch, MLX, LoRA/QLoRA, Modal A100s, H100s | FastAPI, Phoenix, Rails R\u00e9sum\u00e9/CV: https://linkedin.com/in/arthurcolle Email: arthur@distributed.systems Background: Deep knowledge of OpenAI, Anthropic + LL", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (December 2025)"}, {"id": 737844720, "item_id": 46115295, "url": "https://news.ycombinator.com/item?id=46115295", "by": "gh-llm-in-loop", "date": "2025-12-01", "stance": "neutral", "quote": "Stack includes Golang, Neo4j, AWS (Lambda, SQS, S3, DynamoDB), GraphQL, Typescript/React", "excerpt": "Bedrock Data | Backend Engineer | Menlo Park, CA (Onsite) | bedrockdata.ai At Bedrock Data, we are building next-generation data security platforms. Our backend engineering team is responsible for: Large-scale distributed systems to handle petabytes of data in a scale-out architecture. Stack includes Golang, Neo4j, AWS (Lambda, SQS, S3, DynamoDB), GraphQL, Typescript/React Please apply here: https://jobs.ashbyhq.com/", "context": "", "use_case": "Backend stack", "switched_from": "", "story": "Ask HN: Who is hiring? (December 2025)"}, {"id": 737465252, "item_id": 46091578, "url": "https://news.ycombinator.com/item?id=46091578", "by": "gregorydickson", "date": "2025-11-29", "stance": "recommend", "quote": "Neo4j - when you need scale", "excerpt": "I built this because Claude Code keeps forgetting what it learned. Every session I'd re-explain the architecture, re-discover the same bugs, re-learn the same solutions. CLAUDE.md helps but it's manual and doesn't capture relationships between things. memory-graph is an MCP server that stores entities, observations, and relationships in a knowledge graph. The key insight: coding agents need to remember what solved pr", "context": "", "use_case": "Graph database backend", "switched_from": "", "story": "Memory-Graph \u2013 Knowledge Graph Memory for Claude Code with SQLite/Neo4j/Memgraph"}, {"id": 735350112, "item_id": 45959382, "url": "https://news.ycombinator.com/item?id=45959382", "by": "babelfish", "date": "2025-11-17", "stance": "neutral", "quote": "it seems like Neo4j should be able to support 1 trillion edges", "excerpt": "I don't have any experience on graph modeling, but it seems like Neo4j should be able to support 1 trillion edges, based on this (admittedly marketing) post of theirs? https://neo4j.com/press-releases/neo4j-scales-trillion-plus-relationship-graph/", "context": "", "use_case": "graph database", "switched_from": "", "story": "A graph explorer of the Epstein emails"}, {"id": 734675570, "item_id": 45917223, "url": "https://news.ycombinator.com/item?id=45917223", "by": "kirin_memorang", "date": "2025-11-13", "stance": "recommend", "quote": "Our stack is awesome: Vercel, Supabase, Neo4j, Langchain, Expo", "excerpt": "# Memorang (Vercel + Shopify for EdTech) | Full-Time | Remote # Our mission is impactful: To build the \"AI stack for education.\" Our platform combines knowledge graphs, agents, and apps to provide an all-in-one toolkit to rapidly launch new content and apps. We bootstrapped to profitability, won the inaugural Vercel AI Accelerator (out of 1,500 startups), and now power the official content and apps for career sectors", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who is hiring? (November 2025)"}]}