hellojwilde/energetic-ai
EnergeticAI is TensorFlow.js, optimized for serverless environments, with fast cold-start, small module size, and pre-trained models.
Achieves dramatic performance improvements through aggressive tree-shaking and WebAssembly backend optimization, reducing bundle size to ~3 MB and cold-start latency to ~50 ms. Provides modular, composable packages (@energetic-ai/embeddings, @energetic-ai/classifiers) with pre-trained weights, allowing developers to cherry-pick only needed functionality rather than loading full TensorFlow.js distributions. Built as a drop-in TensorFlow.js replacement using Lerna monorepo structure, maintaining API compatibility while targeting AWS Lambda, Google Cloud Functions, and similar serverless platforms.
No commits in the last 6 months.
Stars
36
Forks
—
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Nov 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/hellojwilde/energetic-ai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
awinml/voyage-embedders-haystack
Custom components for Haystack for creating embeddings and reranking documents using the VoyageAI Models.
estebanpdl/osintgpt
An open-source intelligence (OSINT) analysis tool leveraging GPT-powered embeddings and vector...
voyage-ai/voyageai-python
Voyage AI Official Python Library
calebevans/cordon
Reduce logs to their semantic anomalies
FullStackWithLawrence/openai-embeddings
OpenAI chatGPT hybrid search and retrieval augmented generation