Jina AI
@jina-ai • Your Search Foundation, Supercharged! (acquired by @elastic 2025/10). Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
84%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
30 repos
Visible snapshot
5 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (14), Unknown (6), TypeScript (4)
Average size
252
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-05-28(89d ago)GitHub API fallback30 repositories
84%
of the visible star count comes from this organization's top three repositories.
252
stars per repository in this same snapshot.
Python
is the most common language here, with 5 repositories updated in the last 90 days.
Why this rank
This organization stands out because one flagship repo drives 69% of its visible star count.
Flagship share 69%Breakout repo: node-DeepResearch
Organization pages work best when you separate portfolio breadth from flagship concentration. In Jina AI's case, the visible top three repositories account for about 84% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (14), Unknown (6), TypeScript (4). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars |
|---|---|---|---|
| 1 | jina-ai/node-DeepResearch Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget) | TypeScript | 5.2K |
| 2 | jina-ai/MCP Official Jina AI Remote MCP Server | TypeScript | 830 |
| 3 | jina-ai/correlations Simple UI for debugging correlations of text embeddings | HTML | 319 |
| 4 | jina-ai/jina-grep-cli Semantic grep powered by Jina embeddings v5 (MLX on Apple Silicon) | Python | 243 |
| 5 | jina-ai/mlx-retrieval Train embedding and reranker models for retrieval tasks on Apple Silicon with MLX | Python | 187 |
| 6 | jina-ai/cli All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes. | Python | 173 |
| 7 | jina-ai/deepsearch-ui Jina DeepSearch UI | JavaScript | 130 |
| 8 | jina-ai/jzip-compressor Compression for unit-norm embedding vectors using spherical coordinates | C | 82 |
| 9 | jina-ai/submodular-optimization Submodular optimization for context engineering: query fan-out, text selection, passage reranking | Jupyter Notebook | 80 |
| 10 | jina-ai/node-serp LLM-as-SERP | TypeScript | 69 |
| 11 | jina-ai/embedding-inversion-demo Embedding Inversion via Conditional Masked Diffusion: recover original text from embedding vectors using parallel denoising. Live demo + training pipeline + technical report. | Python | 60 |
| 12 | jina-ai/jina-embeddings-v4-gguf A collection of GGUF and quantizations for jina-embeddings-v4 | Shell | 38 |
| 13 | jina-ai/jina-vdr Jina VDR is a multilingual, multi-domain benchmark for visual document retrieval | Python | 38 |
| 14 | jina-ai/embedding-fingerprints Identify which embedding model produced a vector using digit-level tokenization and a tiny transformer | Python | 23 |
| 15 | jina-ai/llama.cpp LLM inference in C/C++ | C++ | 15 |
| 16 | jina-ai/jina-on-prem Air-gapped deployment toolkit for Jina AI models | Python | 14 |
| 17 | jina-ai/audio-embedding-kickstarter | Python | 10 |
| 18 | jina-ai/wikipedia-vector-demo | TypeScript | 5 |
| 19 | jina-ai/markitdown Python tool for converting files and office documents to Markdown. | Python | 4 |
| 20 | jina-ai/bof-emnlp2025-embeddings-rerankers-smallLMs-for-better-search Nov. 7 EMNLP2025 BoF: Embeddings, Rerankers, Small LMs for Better Search | 4 | |
| 21 | jina-ai/OmniDocBench [CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation | Python | 3 |
| 22 | jina-ai/olmocr-bench | Python | 2 |
| 23 | jina-ai/MMTEB-MCP | Python | 2 |
| 24 | jina-ai/mteb-jinavdr MTEB: Massive Text Embedding Benchmark | Python | 2 |
| 25 | jina-ai/dataroom-tpu-models | Python | 1 |
| 26 | jina-ai/jina-reranker-m0-gguf A collection of GGUF and quantizations for jina-embeddings-v4 | 1 | |
| 27 | jina-ai/mteb-rteb-news MTEB: Massive Text Embedding Benchmark | 0 | |
| 28 | jina-ai/gpt-oss gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI | 0 | |
| 29 | jina-ai/image-assets | 0 | |
| 30 | jina-ai/multimodal-reranker-test samples to evaluate a multimodal neural reranker | 0 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.