Explosion
@explosion • Software company specializing in developer tools and tailored solutions for AI and Natural Language Processing. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
75%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
30 repos
Visible snapshot
3 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (24), Unknown (2), Cython (2)
Average size
143
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-08-24(1d ago)GitHub API fallback30 repositories
75%
of the visible star count comes from this organization's top three repositories.
143
stars per repository in this same snapshot.
Python
is the most common language here, with 3 repositories updated in the last 90 days.
Why this rank
This organization stands out because its public portfolio is relatively balanced across 30 repositories.
Balanced portfolio across 30 reposTop 3 share 75%
Organization pages work best when you separate portfolio breadth from flagship concentration. In Explosion's case, the visible top three repositories account for about 75% 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 (24), Unknown (2), Cython (2). 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 | explosion/spacy-llm 🦙 Integrating LLMs into structured NLP pipelines | Python | 1.4K |
| 2 | explosion/spacy-layout 📚 Process PDFs, Word documents and more with spaCy | Python | 909 |
| 3 | explosion/curated-transformers 🤖 A PyTorch library of curated Transformer models and their composable components | Python | 890 |
| 4 | explosion/prodigy-openai-recipes ✨ Bootstrap annotation with zero- & few-shot learning via OpenAI GPT-3 | Python | 320 |
| 5 | explosion/confection :candy: Confection: the sweetest config system for Python | Python | 193 |
| 6 | explosion/radicli 🕊️ Radically lightweight command-line interfaces | Python | 110 |
| 7 | explosion/weasel 🦦 weasel: A small and easy workflow system | Python | 93 |
| 8 | explosion/spacy-huggingface-pipelines 💥 Use Hugging Face text and token classification pipelines directly in spaCy | Python | 65 |
| 9 | explosion/assets 💥 Explosion Assets | 45 | |
| 10 | explosion/wikid Generate a SQLite database from Wikipedia & Wikidata dumps. | Python | 40 |
| 11 | explosion/prodigy-pdf A Prodigy plugin for PDF annotation | Python | 38 |
| 12 | explosion/spacy-curated-transformers spaCy entry points for Curated Transformers | Python | 32 |
| 13 | explosion/spacy-vscode spaCy extension for Visual Studio Code | Python | 31 |
| 14 | explosion/prodigy-hf Train huggingface models on top of Prodigy annotations | Python | 22 |
| 15 | explosion/os-signpost Wrapper for the macOS signpost API | Cython | 18 |
| 16 | explosion/conll-2012 A slightly cleaned up version of the scripts & data for the CoNLL 2012 Coreference task. | Python | 14 |
| 17 | explosion/prodigy-evaluate 🔎 A Prodigy plugin for evaluating spaCy pipelines | Python | 13 |
| 18 | explosion/curated-tokenizers Lightweight piece tokenization library | Cython | 12 |
| 19 | explosion/prodigy-segment Select pixels in Prodigy via Facebook's Segment-Anything model. | Python | 10 |
| 20 | explosion/prodigy-whisper Audio transcription with OpenAI's whisper model in the loop. | Python | 5 |
| 21 | explosion/prodigy-ann A Prodigy pluging for ANN techniques | Python | 5 |
| 22 | explosion/prodigy-lunr A Prodigy plugin for document search via LUNR | Python | 4 |
| 23 | explosion/princetondh Code for our presentation in Princeton DH 2023 April. | Jupyter Notebook | 4 |
| 24 | explosion/ec2buildwheel | Python | 3 |
| 25 | explosion/span-labeling-datasets Loaders for various span labeling datasets | Python | 2 |
| 26 | explosion/ellf-terraform-cluster Terraform definitions for self-hosted Ellf clusters | HCL | 1 |
| 27 | explosion/spacy-biaffine-parser | Python | 1 |
| 28 | explosion/aiGrunn-2023 Materials for the aiGrunn 2023 talk on spaCy Transformer pipelines | Python | 1 |
| 29 | explosion/gha-cibuildwheel | 0 | |
| 30 | explosion/curated-transformers-addons Add-ons for Curated Transformers | Python | 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.