Top all-time · #13838
CocoIndex
Company blog · cocoindex.io/blogsaiprogrammingdata
CocoIndex is the company blog at cocoindex.io, writing about ai, programming and data. Since 2025, 5 different Hacker News readers have linked it 34 times, most often “Thinking in Rust: Ownership, Access, and Memory Safety”. It is still writing: the last post was on 2026-10-07, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link CocoIndex's product pages and a dev.to tutorial on building an index with text embeddings. The CocoIndex pages describe an open-source incremental ETL framework for AI workloads.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Open-source incremental data framework for AI agents. Keep codebases, docs, and knowledge continuously indexed — fresh context, zero re-processing. Python API.
Most-linked posts?
- Thinking in Rust: Ownership, Access, and Memory Safety3 people · 3 mentions · first linked 2025-07-15
- Lessons learned – 5x throughput on data pipelines with adaptive batching2 people · 3 mentions · first linked 2025-11-05
- Cocoindex: Data Transformation for AI2 people · 2 mentions · first linked 2025-07-10
What Hacker News says?
Have you tried cocoindex? [1] https://cocoindex.io/ [2] https://dev.to/cocoindex/how-to-build-index-with-text-embedd...
Comment linking /
on “The Case Against PGVector”Submitted Build real-time knowledge graph for documents with LLM as a story · 181 points
HN discussionbtw, Neo4j supports vector properties and building vector index out of it. It's supported in cocoindex to configure a vector index: https://cocoindex.io/docs/ops/storages#neo4j Neo4j also supports building embedding leveraging more information in the graph in addition to single node's property: https://neo4j.com/docs/graph-data-science/current/machine-le... (It's hard to incrementally compute them, but users can sti…
Comment linking /docs/ops/storages
on “Build real-time knowledge graph for documents with LLM”Submitted Show HN: Open-Source Codebase Index with Tree-sitter as a story · 6 points
HN discussionhttps://github.com/cocoindex-io/cocoindex is built for building fresh knowledge base. Detects delta of data sources, apply any transformations, and refresh knowledge, at any scale. It is open source. Examples: https://cocoindex.io/docs/examples
Comment linking /docs/examples
on “Ask HN: Best way to create a searchable knowledge base?”Submitted Thinking in Rust: Ownership, Access, and Memory Safety as a story · 5 points
HN discussionWe have a few here, https://cocoindex.io/blogs/tags/examples/ . more coming soon, thanks for the great question
Comment linking /blogs/tags/examples/
on “Show HN: CocoIndex – Open-Source Data framework for AI, built for data freshness”Submitted Thinking in Rust: Ownership, Access, and Memory Safety as a story · 4 points
HN discussionAbsolutely! CocoIndex is an ETL framework not limited to RAG. You can use it to do transformation as you need, including parsing documents and extracting information you need using your model or code. We have a similar example, and welcome to checkout: https://cocoindex.io/blogs/patient-intake-form-extraction-wi...
Comment linking /blogs/patient-intake-form-extraction-with-llm/
on “Show HN: CocoIndex – Open-Source Data framework for AI, built for data freshness”Submitted Build Real-Time Knowledge Graph for Documents with LLM as a story · 4 points
HN discussionHi everyone, would love to share my recent work on extracting structured data from PDF/Markdown with Ollama 's local LLM models. All running on premise without sending data to external APIs. I wrote detailed steps on how it worked https://cocoindex.io/blogs/cocoindex-ollama-structured-extra... You can pull any of your favorite LLM models by the ollama pull command. Would love some feedback!
Comment linking /blogs/cocoindex-ollama-structured-extraction-from-pdf/
on “Show HN: Open-Source Structured Extraction with LLM Using Ollama”Submitted Lessons learned – 5x throughput on data pipelines with adaptive batching as a story · 3 points
HN discussionHi HN, I’m George — I left Google after 10 years working on infrastructure and am building CocoIndex https://cocoindex.io with my friend Linghua. CocoIndex is an open source ETL framework that does incremental processing designed for AI workloads. We cut >90% of compute costs by processing only what’s changed — effortless fresh context for AI. It is easy to build scalable, production-grade pipelines like Lego in hou…
Comment linking /blogs/tags/examples
on “CocoIndex – open-source ETL saves you >90% compute for AI workloads”Submitted Extract structured information from Hacker News and keep in sync with Postgres as a story · 2 points
HN discussionHi HN community, I've worked on real-time knowledge graph to turn docs in to knowledge in this project and got very popular [1]. I've received feature request to integrated with Kuzu from CocoIndex users. So I've rolled out the integration with Kuzu + CocoIndex. CocoIndex is written in Rust to help with real-time data transformation for AI, for example knowledge graphs. Kuzu is written in C++ and is high performance…
Comment linking /blogs/kuzu-integration
on “Real-time knowledge graph with Kuzu and CocoIndex, performant open source stack”Submitted How to perform adaptive batching for massive remote LLM calls as a story · 2 points
HN discussionHi I've been working on adding multi-vector support natively in cocoindex for multi-modal RAG at scale. I wrote blog to help understand the concept of multi-vector and how it works underneath. The framework itself automatically infers types, so when defining a flow, we don’t need to explicitly specify any types. Felt these concept are fundamental to multimodal data processing so just wanted to share. This unlocks at…
Comment linking /blogs/multi-vector/
on “Multi-Dimensional Vector Support in CocoIndex – Underneath Explained”Submitted Multi-Format RAG with ColPali: PDFs, Images, Slides – No OCR as a story · 2 points
HN discussionSubmitted Thinking in Rust: Ownership, Access, and Memory Safety as a story · 2 points
HN discussionSubmitted Realtime codebase indexing for coding agents with – 50 lines of Python as a story · 2 points
HN discussionSubmitted Cocoindex: Data Transformation for AI as a story · 2 points
HN discussionSubmitted Real-time knowledge graph with Kuzu and CocoIndex, performant open source stack as a story · 2 points
HN discussionSubmitted Build image search and query with natural language with vision model CLIP as a story · 2 points
HN discussionSubmitted Build Real-Time Product Recommendation Engine with LLM and Graph Database as a story · 2 points
HN discussionSubmitted Building an Invisible Daemon: Architecture Patterns for Local Developer Tools as a story · 1 points
HN discussionSubmitted Streamline Structured and Unstructured Data Flows from Postgres with AI as a story · 1 points
HN discussionSubmitted Adaptive Batching – 5x throughput on your data pipelines as a story · 1 points
HN discussionSubmitted Automated invoice processing with AI and incremental processing as a story · 1 points
HN discussionSubmitted Incrementally Transform Structured and Unstructured Data from Postgres with AI as a story · 1 points
HN discussionSubmitted Multi-Dimensional Vector Support in CocoIndex – Underneath Explained as a story · 1 points
HN discussion
