Showing 100 skill frameworks sorted by GitHub stars — all open-source with proven community adoption.
Microsoft utility to convert files and documents to Markdown
State-of-the-art ML models for NLP, vision and audio
Framework for building LLM-powered applications
High-throughput LLM serving with PagedAttention
Unified fine-tuning framework for 100+ LLMs with WebUI
2-5x faster LLM fine-tuning with 70% less memory
IBM's document parsing and understanding library
Memory layer for AI agents and assistants
Unified API for 100+ LLMs with OpenAI format
Meta's promptable image segmentation foundation model
Data framework for LLM applications over custom data
Open-source vector database for scalable similarity search
Unified framework for scaling AI and Python applications
Build web demos and UIs for ML models in Python
Microsoft's deep learning optimization library for scale
Facebook's library for efficient similarity search and clustering
Simple and fast RAG system with knowledge graph support
Programming—not prompting—language models
Microsoft's graph-based RAG for complex reasoning over text
HuggingFace library for diffusion model development
OpenAI's contrastive language-image pretraining model
High-performance vector similarity search engine
Industrial-strength natural language processing library
Open-source LLM engineering platform for observability
Fast serving framework for large language and vision models
Official OpenAI Python client library
Deep learning framework to train, deploy and ship AI products
Integration platform for AI agents with 250+ tools
SDK for integrating 250+ tools into AI agents and LLMs
Open-source AI-native vector database
Microsoft SDK integrating LLMs into applications
Multi-type data labeling tool for ML training data
Apple's array framework for ML on Apple Silicon
Platform for ML lifecycle: tracking, registry, deployment
End-to-end NLP framework for search and QA systems
Test and evaluate LLM outputs and prompt quality
Chat with your data using natural language via LLMs
Open-source vector similarity search for PostgreSQL
HuggingFace library for easy ML dataset loading and sharing
Efficient control and templating for language models
Parameter-efficient fine-tuning methods including LoRA
Cross-platform ML inferencing accelerator by Microsoft
Type-safe AI agent framework built on Pydantic
Train LLMs with RLHF, PPO, DPO and reward modeling
Multilingual sentence, paragraph and image embeddings
Fast BPE tokenizer used by OpenAI models
Unit testing framework for LLM outputs and RAG pipelines
Open-source vector database with hybrid semantic search
Topic modelling and document similarity library
ML experiments and data version control system
Structured text generation for language models
Pre-processing library for unstructured data (PDFs, docs, etc.)
Evaluation framework for RAG pipelines
Tensor library for machine learning on edge devices
Structured RAG framework for enterprise LLM applications
Natural Language Toolkit - classic Python NLP library
Approximate nearest neighbors library by Spotify
Open-source implementation of CLIP vision-language models
Structured outputs for LLMs using Pydantic
Pre-train, finetune, and deploy 20+ LLMs on your hardware
Framework for evaluating language models on NLP tasks
Secure sandboxed environments for AI code execution
All-in-one open-source embeddings database
Run LLMs in production with BentoML
Build production-ready conversational AI applications
Streamlined tool for easily fine-tuning AI models
Retrieval and embedding models including BGE series
Data-centric AI library for finding and fixing dataset issues
Build and evaluate LLM-based AI flows
Serverless vector database for AI applications
AI observability platform for LLM tracing and evaluation
Extremely fast tokenizers for modern NLP
Production LLM serving toolkit by HuggingFace
Python bindings for llama.cpp with OpenAI-compatible API
Open-set object detection with language grounding
Training and inference PyTorch at scale with minimal code changes
Build, ship and run AI applications in the cloud
8-bit and 4-bit quantization for LLM memory efficiency
Database for AI data with multimodal vector storage
Efficient LLM compression, deployment and serving toolkit
ML and LLM monitoring and evaluation platform
Add validation and correction guardrails to LLM outputs
Open source AI search and recommendation engine
NVIDIA toolkit for adding programmable guardrails to LLMs
AI toolkit for building natural language interfaces
PyTorch-native finetuning library for LLMs
Easy GPTQ model quantization for LLM deployment
Tensor search engine for text and images
Blazing fast inference for text embeddings
Query language and runtime for large language models
Use ColBERT and late-interaction models in RAG pipelines
Official Python library for Anthropic's Claude API
Superfast AI decision-making and routing layer for LLMs
Evaluation and tracking for LLM-based applications
HuggingFace acceleration and optimization for inference
Security toolkit for LLMs to detect prompt injection and PII
Dataclass for multimodal data representation in ML
Open-source tools for testing and experimenting with prompts
Embedded AI inference library for desktop and edge
Python bindings for GGML/GGUF quantized models