CocoIndex
@cocoindex.bsky.social
π€ 39
π₯ 25
π 111
#OpenSource
Transform data for AI π₯₯π΄ β
https://github.com/cocoindex-io/cocoindex
pinned post!
π CocoIndex just hit 1,000 βοΈ on GitHub! Huge thanks to everyone who starred, forked, contributed, or shared the love! Weβre just getting started. π π
github.com/cocoindex-io...
#OpenSource
#DataInfrastructure
#CocoIndex
#LLM
#Buildinpublic
#AIInfrastructure
#ETL
10 months ago
1
10
2
Build your own open-source deep wiki ! Auto-generate wikis for every project that never go stale. β Scan codebases β Extract info with LLMs β Generate docs + Mermaid diagrams β Incremental updates
cocoindex.io/examples-v1/multi-codebase-summarization
#OpenSource
#DevTools
#LLM
28 days ago
0
3
0
reposted by
CocoIndex
Srihari Thyagarajan
about 1 month ago
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)
1
2
1
reposted by
CocoIndex
Srihari Thyagarajan
about 1 month ago
@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)!
1
2
1
AI agents understand codebases π€ CocoIndex: real-time semantic code indexing β Tree-sitter chunking β Incremental β Vector search Use: β’ MCP for AI editors β’ Semantic search β’ AI code review β’ Auto docs Query "Find auth" β instant code chunks
cocoindex.io/docs/examples/code_index
#AI
#Rust
3 months ago
0
2
0
Tree-sitter powered codebase indexing β real-time semantic search for AI agents π 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
3 months ago
0
2
0
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
3 months ago
0
2
0
π 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). π»
github.com/cocoindex-io/cocoindex
#AI
#DataEngineering
loading . . .
cocoindex/examples/patient_intake_extraction_dspy at main Β· cocoindex-io/cocoindex
Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it! - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex/tree/main/examples/patient_intake_extraction_dspy
3 months ago
0
3
0
π CocoIndex just hit Rust Trending Again! π¦ Why Rust? β‘ Speed - C++ speed + memory safety π Reliability - No GC pauses or segfaults. Predictable performance always Speed + Fresh data = Critical infra for AI agents
github.com/cocoindex-io...
#Rust
#AI
#Opensource
loading . . .
GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it!
Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it! - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex/
3 months ago
0
3
0
Building Knowledge Graphs with LLMs! π₯ Turn docs into living graphs: β Triple extraction β Real-time entity mapping β Neo4j export with zero pain CocoIndex handles it all - no manual Cypher β‘ Perfect for RAG & AI agents!
youtu.be/FKNcv2n4nTg
loading . . .
Property Graph, Triple extraction and Knowledge Graph with LLM in simple words and examples
YouTube video by CocoIndex
https://youtu.be/FKNcv2n4nTg
3 months ago
0
1
0
Tired of fragile LLM prompts? π€ BAML = typed prompt functions: β Type-safe schemas β Predictable outputs β Production-ready + CocoIndex for incremental processing = π₯ Tutorial: Extract patient data from PDFs
cocoindex.io/blogs/extrac...
#AI
#LLM
loading . . .
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.
https://cocoindex.io/blogs/extraction-baml
3 months ago
0
1
0
CocoIndex just hit Rust Trending Again! π
github.com/cocoindex-io...
With all the AI agents development, CocoIndex is becoming critical infra for autonomous driving agents. Star & share this π₯₯ if it resonates!
#Opensource
#RustLang
loading . . .
GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it!
Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it! - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
3 months ago
0
3
0
Why π¦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...
loading . . .
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.
https://cocoindex.io/blogs/rust-ownership-access
3 months ago
0
2
0
CocoIndex just hit Rust Trending! π
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! π₯₯
#Opensource
#RustLang
loading . . .
GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it!
Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it! - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
3 months ago
1
6
1
π¦ CocoIndex 0.3.10 drops today! Rust improvements: β’ Async runtime fixes (no deadlocks) β’ Smarter incremental recomputation β’ Optimized embedding batches β’ Robust file/streaming handling Why Rust for data? Memory safety + performance + async = reliable AI infra at scale
loading . . .
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.
https://cocoindex.io/blogs/changelog-0310
3 months ago
0
1
0
Context engineering just got easier π CocoIndex transforms how you build AI systems: β¨ Incremental processing - only recompute what changed π Real-time sync - keep context always fresh π― Data lineage built-in β‘ Rust-powered Perfect for RAG, knowledge graphs & AI agents
github.com/cocoindex-io/cβ¦
loading . . .
GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it!
Data transformation framework for AI. Ultra performant, with incremental processing. π Star if you like it! - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
3 months ago
0
2
0
Custom Sources in CocoIndex π 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...
loading . . .
Bring your own data: Index any data with Custom Sources | CocoIndex
CocoIndex now officially supports custom sources β 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...
https://cocoindex.io/blogs/custom-source
3 months ago
0
2
0
Automatic Batching in CocoIndex π CocoIndex now supports automatic batching for all functions. ~5Γ 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
loading . . .
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 ...
https://cocoindex.io/blogs/batching
3 months ago
0
2
0
CocoIndex v0.3.10 just shipped with automatic batching support! π ~5Γ faster throughput when embedding our codebase. Best part? Zero tuning needed - it's adaptive and knob-free. Just set batching=True. Read the benchmarks π
3 months ago
1
0
0
reposted by
CocoIndex
GitHub Projects
3 months ago
Keep passwords and other sensitive information out of your inboxes and chat logs
1
2
1
reposted by
CocoIndex
Linghua Jin
3 months ago
Improve your ai data pipeline throughput x times by adaptive batching
cocoindex.io/blogs/batching
#ai
#opensource
loading . . .
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 ...
https://cocoindex.io/blogs/batching
0
4
1
reposted by
CocoIndex
Linghua Jin
4 months ago
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 π
#rustlang
#github
#opensource
2
8
3
reposted by
CocoIndex
Linghua Jin
5 months ago
vibe coding, not vibe data
www.youtube.com/watch?v=crV7...
#ai
#youtube
#llm
#data
#opensource
loading . . .
Fast Iterate Your Indexing Strategy π
YouTube video by CocoIndex
https://www.youtube.com/watch?v=crV7odEVYTE
0
5
1
reposted by
CocoIndex
Linghua Jin
7 months ago
CocoIndex -
github.com/cocoindex-io...
- Build fresh knowledge for AI made to the top 3 in trending github in
#rustlang
! π star if you like it! Let's go Rust π¦. Data infra project should be on
#Rustlang
.
#opensource
#buildinpublic
0
8
3
A mental framework to really understand how Rustβs 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
loading . . .
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.
https://cocoindex.io/blogs/rust-ownership-access
7 months ago
0
4
1
reposted by
CocoIndex
Linghua Jin
7 months ago
Multi-dimensional vectors? Thatβs how AI understands everything β text, images, audio, all at once. We broke it down here.
cocoindex.io/blogs/multi-...
πStar the repo if you like it!
github.com/cocoindex-io...
#opensource
#Vision
#LLM
#AI
#buildinpublic
loading . . .
Multi-Dimensional Vector Support in CocoIndex | CocoIndex
CocoIndex natively handles typed multi-dimensional vectors β from simple arrays to multi-vector embeddings, unlocks multimodal AI pipelines at scale.
https://cocoindex.io/blogs/multi-vector
1
7
2
reposted by
CocoIndex
Linghua Jin
7 months ago
#vibecoding
#opensource
#ClaudeCode
#Claude
#GPT5
#GPT
#OPENAI
#GEMINI
0
5
2
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!
loading . . .
Custom Targets | CocoIndex
Learn how to create custom targets in CocoIndex to export data to any destination including databases, cloud storage, file systems, and APIs. Build target specs and connectors with setup and data meth...
https://cocoindex.io/docs/custom_ops/custom_targets
7 months ago
0
2
0
π Build Your Own Google Photo Search with Face Indexing at Scale. We just dropped a new tutorial on building a scalable face recognition pipeline using CocoIndex and Qdrant.
cocoindex.io/blogs/face-d...
#opensource
#faceRecognition
#LLM
#AI
#startup
#Qdrant
#CocoIndex
#ColdPlay
loading . . .
Indexing Faces for Scalable Visual Search - Build your own Google Photo Search | CocoIndex
Build a scalable face detection and recognition pipeline using CocoIndex. This tutorial covers extracting and embedding faces from images, structuring data for visual search, and exporting to a vect...
https://cocoindex.io/blogs/face-detection/
7 months ago
0
2
1
A mental framework -- as a simple and natural interpretation -- on Rust's memory safety models
cocoindex.io/blogs/rust-o...
#rustlang
#buildinpublic
loading . . .
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.
https://cocoindex.io/blogs/rust-ownership-access/
8 months ago
0
6
2
reposted by
CocoIndex
Linghua Jin
8 months ago
A holistic, top-down perspective on Rustβs ownership, permission, and memory safety model
cocoindex.io/blogs/rust-o...
#Rustlang
#Programming
#MemorySafty
#Data
loading . . .
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.
https://cocoindex.io/blogs/rust-ownership-access
0
5
1
#windsurf
#cursor
#codingagents
#llm
#coding
#tech
add a skeleton here at some point
8 months ago
0
3
1
reposted by
CocoIndex
HackerNoon
8 months ago
How to index academic research papers by extracting metadata (e.g., title, authors, abstract) for AI agents and AI workflows using LLMs and CocoIndex.
#ai
loading . . .
Turn Your PDF Library into a Searchable Research Database with 100 Lines of Code
https://hackernoon.com/turn-your-pdf-library-into-a-searchable-research-database-with-100-lines-of-code
0
3
2
reposted by
CocoIndex
Linghua Jin
8 months ago
What you get: β LLM-extracted title, authors, abstract β Embeddings for smart search β Build 3 tables in one shot: metadata, authorβpaper, embeddings β Real-time updates via Postgres + PGVector (one-line switch to Qdrant) Appreciate a star on the repo if it is helpful
github.com/cocoindex-io...
loading . . .
GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing.
Data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
0
3
1
reposted by
CocoIndex
Linghua Jin
8 months ago
π Build LLM-ready, metadata-rich indexes from academic papers PDF in minutes. Get started: πhttps://cocoindex.io/blogs/academic-papers-indexing Repo: π
github.com/cocoindex-io...
#LLM
#RAG
#SemanticSearch
#opensource
#DataInfrastructure
#KnowledgeGraphs
#VectorSearch
#DevTools
#OpenSource
1
6
2
reposted by
CocoIndex
Linghua Jin
8 months ago
github.com/cocoindex-io...
Transform data for AI got to
@github.com
Rust Trending this week π!
@github-trending.bsky.social
#rustlang
#opensource
loading . . .
GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing.
Data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
0
4
1
Code ETL like LEGO
#opensource
#rustlang
github.com/cocoindex-io...
8 months ago
0
4
0
Wanna AI to understand your codebase? cocoindex has native support Checkout
github.com/cocoindex-io...
Appreciate a Github star! Step by step tutorial
cocoindex.io/blogs/index-...
to setup codebase indexing for coding agent in 10 min.
8 months ago
0
1
0
#OpenSource
- ideas move faster, together. Build openly, learn from others, and create impact beyond your own code.
8 months ago
0
4
1
way to go -
github.com/cocoindex-io...
2k stars
#OpenSource
#Rustlang
8 months ago
1
4
0
reposted by
CocoIndex
Linghua Jin
8 months ago
CocoIndex - super simple etl to prepare data for ai agents, with dynamic index - cross 2k Github stars today.
github.com/cocoindex-io...
When sources get updates, it automatically syncs to targets with minimal computation needed. Open source & on-prem ready. βοΈ Star if it is helpful :)
1
3
1
reposted by
CocoIndex
Linghua Jin
8 months ago
Homepage v2 -
cocoindex.io
Ultra performant ETL for AI, within 100 lines of python code. Appreciate a star π on
github.com/cocoindex-io...
1
2
1
reposted by
CocoIndex
Linghua Jin
8 months ago
π Introducing CocoInsight - Make your AI data pipeline exceptionally easy to understand β step-by-step. πWorks with CocoIndex:
github.com/cocoindex-io...
πNow live:
youtube.com/watch?v=MMrp...
#AI
#DataEngineering
#LLM
#RAG
#OpenSource
#VibeCoding
#AIInfrastructure
#MLOps
#LLMInfra
#CocoIndex
loading . . .
0
5
2
reposted by
CocoIndex
Linghua Jin
9 months ago
π CocoIndex now officially supports LiteLLM. You can now plug any LiteLLM-supported model directly into your Coco AI data pipelines β making it even easier to run, experiment, and scale with your favorite LLMs.
cocoindex.io/docs/ai/llm#...
πGithub:
github.com/cocoindex-io...
#LLM
#data
#AI
#etl
loading . . .
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
0
3
1
reposted by
CocoIndex
Linghua Jin
9 months ago
Real-time updates, syntax-aware chunking. Production-ready. Ultra-performant. Fully
#OpenSource
.
#LLM
#RAG
#AIForCode
#CodeSearch
#DevTools
#RealtimeAI
#OpenSource
#AIInfra
#Rust
#Python
#TreeSitter
#VectorDB
#Embeddings
#AIEngineering
#GenerativeAI
#Codex
#CodingAgents
#Claude
#Cursor
0
5
1
reposted by
CocoIndex
Linghua Jin
9 months ago
π Build Real-Time
#Codebase
Indexing for LLMs with Tree-sitter for coding agents. ~100 lines of Python get started: π
cocoindex.io/blogs/index-...
repo: π
github.com/cocoindex-io...
1
4
1
Still duct-taping Python scripts to move data around? π©Ήπ Itβs 2025. Time to upgrade. Meet CocoIndex β real-time data transformation built in Rust, for devs who like things fast, fresh, and composable. π¦β‘π π
github.com/cocoindex-io...
#RustLang
#DataInfra
#OpenSourceTools
#LLMops
#BuildInPublic
loading . . .
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
9 months ago
0
2
0
Tired of clunky ETL pipelines and stale data? Meet CocoIndexβthe ultra-performant, open-source framework built in Rust for real-time data transformation.
github.com/cocoindex-io...
#Data
#technology
#Opensource
#Buildinpublic
loading . . .
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
9 months ago
1
6
0
reposted by
CocoIndex
Linghua Jin
9 months ago
Most user-facing AI agents need data freshness. When users update documents, it's unexpected to see stale information in search results. If the search result is fed into an AI agent, it may mean unexpected response to users. It's more dangerous - users may take unexpected response without noticing.
0
3
1
reposted by
CocoIndex
HackerNoon
9 months ago
Learn how to build a real-time, incremental ETL pipeline using Amazon S3, SQS, and CocoIndex for efficient, low-latency data transformation and vector embedding
#ai
loading . . .
Real-Time S3 Processing Arrives on CocoIndex via AWS SQS Integration
https://hackernoon.com/real-time-s3-processing-arrives-on-cocoindex-via-aws-sqs-integration
1
6
2
Prototype: "Does it work?" Production: "Will it keep working?" CocoIndex is built for production from day 0 β no hacks, no hand-waving.
github.com/cocoindex-io...
loading . . .
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
https://github.com/cocoindex-io/cocoindex
9 months ago
0
4
0
Load more
feeds!
log in