CocoIndex

Build your own open-source deep wiki !

Auto-generate wikis for every project that never go stale.

→ Scan codebases
→ Extract info with LLMs
→ Generate docs + Mermaid diagrams
→ Incremental updates

cocoindex.io/examples-v1/multi-codebase-summarization

#OpenSource #DevTools #LLM

Kicking off 2026 with Rust Delhi Meetup #12, and what a way to start. Thanks to Guinnes Singh for accepting my talk proposal & being a great host throughout.

I presented on building incremental data pipelines with @cocoindex.bsky.social, a framework I've been contributing towards.

(1/n)

@cocoindex.bsky.social has a Rust-powered execution engine with Python bindings,so you get the performance without leaving Python. @agriyakhetarp.al was the one who told me about Rust Delhi in the first place, so glad I didn't skip this one.

The meetup was at Aftershoot's office (great dogfooding)!

AI agents understand codebases 🤖

CocoIndex: real-time semantic code indexing

→ Tree-sitter chunking
→ Incremental
→ Vector search
Use:
• MCP for AI editors
• Semantic search
• AI code review
• Auto docs

Query "Find auth" → instant code chunks

cocoindex.io/docs/examples/code_index

#AI #Rust

Tree-sitter powered codebase indexing → real-time semantic search for AI agents 🚀

Index your code with language-aware chunking. Query with vectors in Postgres. Ship context that actually understands your codebase.

cocoindex.io/docs/examples/code_index

#AI #Rust #DevTools

Why build in #opensource?

Best infrastructure is transparent, composable, community-driven.

CocoIndex (Rust + Python): data transformation for AI with incremental sync, schema validation, context extraction.

No vendor lock-in. No black boxes. Fast, type-safe pipelines.

#rustlang #python

cocoindex/examples/patient_intake_extraction_dspy at main · cocoindex-io/cocoindex Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! - cocoindex-io/cocoindex

🚀 CocoIndex + DSPy: structured extraction from patient intake forms

LLMs as typed extractors, not black boxes. Production-ready with incremental sync.

No OCR/regex mess. Clean separation between reasoning (DSPy) & data infra (CocoIndex).

💻 github.com/cocoindex-io/cocoindex

#AI #DataEngineering

GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! - cocoindex-io/cocoindex

🚀 CocoIndex just hit Rust Trending Again! 🦀

Why Rust?
⚡ Speed - C++ speed + memory safety
🔒 Reliability - No GC pauses or segfaults. Predictable performance always
Speed + Fresh data = Critical infra for AI agents

github.com/cocoindex-io...

#Rust #AI #Opensource

Property Graph, Triple extraction and Knowledge Graph with LLM in simple words and examples YouTube video by CocoIndex

Building Knowledge Graphs with LLMs! 🔥

Turn docs into living graphs:
✅ Triple extraction
✅ Real-time entity mapping
✅ Neo4j export with zero pain

CocoIndex handles it all - no manual Cypher ⚡

Perfect for RAG & AI agents!

youtu.be/FKNcv2n4nTg

Extracting Intake Forms with BAML and CocoIndex | CocoIndex How to use BAML and CocoIndex to extract structured data from patient intake forms in PDF/Word with LLM continuous for production.

Tired of fragile LLM prompts? 😤

BAML = typed prompt functions:
✅ Type-safe schemas
✅ Predictable outputs
✅ Production-ready

+ CocoIndex for incremental processing = 🔥

Tutorial: Extract patient data from PDFs
cocoindex.io/blogs/extrac...

#AI #LLM

GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! - cocoindex-io/cocoindex

CocoIndex just hit Rust Trending Again! 🚀
github.com/cocoindex-io...

With all the AI agents development, CocoIndex is becoming critical infra for autonomous driving agents.

Star & share this 🥥 if it resonates!

#Opensource #RustLang

Thinking in Rust: Ownership, Access, and Memory Safety | CocoIndex A mental framework for Rust's memory safety concepts. Think systematically about ownership, references, Send, Sync, and Rc, Arc, RefCell, Mutex, etc.

Why 🦀Rust for CocoIndex Core Engine?
- Memory safety
- Performance
- Reliable from day 0

George wrote a great article on Rust's ownership model:
cocoindex.io/blogs/rust-o...

GitHub: github.com/cocoindex-io...

go rust!!

thanks for the spotlight @astrakernel.bsky.social !

GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! - cocoindex-io/cocoindex

CocoIndex just hit Rust Trending! 🚀
github.com/cocoindex-io...

Simplest way to connect data sources & keep targets fresh for AI transformations.

Becoming critical infra for autonomous AI agents.

Star & share! 🥥

#Opensource #RustLang

CocoIndex Changelog 0.2.21 - 0.3.10 | CocoIndex Featuring batching support for CocoIndex functions, execution robustness, schema & type system improvements, custom source support, and more.

🦀 CocoIndex 0.3.10 drops today!

Rust improvements:
• Async runtime fixes (no deadlocks)
• Smarter incremental recomputation
• Optimized embedding batches
• Robust file/streaming handling

Why Rust for data? Memory safety + performance + async = reliable AI infra at scale

GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it! - cocoindex-io/cocoindex

Context engineering just got easier 🚀

CocoIndex transforms how you build AI systems:
✨ Incremental processing - only recompute what changed
🔄 Real-time sync - keep context always fresh
🎯 Data lineage built-in
⚡ Rust-powered

Perfect for RAG, knowledge graphs & AI agents

github.com/cocoindex-io/c…

Bring your own data: Index any data with Custom Sources | CocoIndex CocoIndex now officially supports custom sources — giving you the power to read data from any system you want. You can use CocoIndex for anything, and enjoy the robust incremental computing to build f...

Custom Sources in CocoIndex 🚀

Pull data from ANY system - APIs, databases, cloud storage. CocoIndex now ingests incrementally, tracks changes efficiently, and integrates seamlessly.

No longer limited by prebuilt connectors. Use CocoIndex for anything.

#opensource

cocoindex.io/blogs/custom...

Adaptive Batching - 5x throughput on your data pipelines | CocoIndex Discover how CocoIndex delivers automatic batch processing for GPU workloads and machine learning pipelines. Framework-level batching optimizes performance for text embeddings and other AI operations ...

Automatic Batching in CocoIndex 🚀

CocoIndex now supports automatic batching for all functions. ~5× higher throughput when embedding our codebase.

Best part? Adaptive and knob-free - no timers, no tuning. Just set batching=True.

#opensource

cocoindex.io/blogs/batching

CocoIndex Changelog 0.2.21 - 0.3.10 | CocoIndex Featuring batching support for CocoIndex functions, execution robustness, schema & type system improvements, custom source support, and more.

cocoindex.io/blogs/change...

CocoIndex v0.3.10 just shipped with automatic batching support! 🚀

~5× faster throughput when embedding our codebase. Best part? Zero tuning needed - it's adaptive and knob-free. Just set batching=True.

Read the benchmarks 👇

Keep passwords and other sensitive information out of your inboxes and chat logs

Adaptive Batching - 5x throughput on your data pipelines | CocoIndex Discover how CocoIndex delivers automatic batch processing for GPU workloads and machine learning pipelines. Framework-level batching optimizes performance for text embeddings and other AI operations ...

Improve your ai data pipeline throughput x times by adaptive batching

cocoindex.io/blogs/batching

#ai #opensource

CocoIndex made to #1 Github trending global in Rust - data transformation engine. Grateful to the Rust open source community and all the amazing Rustaceans for the support 💛

#rustlang #github #opensource

Fast Iterate Your Indexing Strategy 🚀 YouTube video by CocoIndex

vibe coding, not vibe data
www.youtube.com/watch?v=crV7...

#ai #youtube #llm #data #opensource

CocoIndex - github.com/cocoindex-io... - Build fresh knowledge for AI made to the top 3 in trending github in #rustlang!

🌟 star if you like it! Let's go Rust 🦀. Data infra project should be on #Rustlang.

#opensource #buildinpublic

Thinking in Rust: Ownership, Access, and Memory Safety | CocoIndex A mental framework for Rust's memory safety concepts. Think systematically about ownership, references, Send, Sync, and Rc, Arc, RefCell, Mutex, etc.

A mental framework to really understand how Rust’s ownership, borrowing, and memory safety work.

With this - moves, borrows, Send, Sync, and runtime checks become intuitive and predictable tools in your programming toolbox.

cocoindex.io/blogs/rust-o...

#rustlang #opensource #programming

Multi-Dimensional Vector Support in CocoIndex | CocoIndex CocoIndex natively handles typed multi-dimensional vectors — from simple arrays to multi-vector embeddings, unlocks multimodal AI pipelines at scale.

Multi-dimensional vectors? That’s how AI understands everything — text, images, audio, all at once. We broke it down here. cocoindex.io/blogs/multi-...

🌟Star the repo if you like it!
github.com/cocoindex-io...

#opensource #Vision #LLM #AI #buildinpublic

#vibecoding #opensource #ClaudeCode #Claude #GPT5 #GPT #OPENAI #GEMINI

CocoIndex is officially supporting custom targets - cocoindex.io/docs/custom_.... We believe this work will add more flexibility for using coco / bring your own lego for targets as well beyond the flow ops.

Thanks our community for the great suggestions!