Collection · 213 entries
AI Technology
The frameworks, runtimes, serving stacks and developer tools teams use to train and ship AI.
- Framework
Agent frameworks
Libraries that provide the loop, state, tool registry and control flow needed to build AI agents.
Advanced - Developer Tools
AgentOps Platform
A premier production framework in developer tools providing observability and evaluation for ai agents.
Intermediate - Platform
AI gateway
A proxy layer between applications and model providers that handles routing, keys, caching, limits and logging.
Intermediate - Tooling
Annotation platforms
Software for labelling data and managing the reviewers, guidelines and quality controls around it.
Intermediate - Distributed Computing
Anyscale (2)
The managed platform powered by Ray for scaling AI training and serving workloads.
Intermediate - AI Infrastructure
Anyscale Ray Serve
A premier production framework in ai infrastructure providing distributed python app & model serving engine.
Intermediate - RAG & Vector Search
AnythingLLM Enterprise
A premier production framework in rag & vector search providing all-in-one enterprise local rag suite.
Intermediate - AI Observability
Arize Phoenix
Open-source AI observability tool for tracing, evaluation, and dataset analysis.
Intermediate - Developer Tools
Arize Phoenix Tracing
A premier production framework in developer tools providing open-source ai observability & tracing.
Intermediate - Model Serving & Inference
AutoAWQ Engine
A premier production framework in model serving & inference providing activation-aware weight quantization toolkit.
Intermediate - Agent Orchestration
AutoGen
Microsoft's multi-agent framework enabling conversational interaction between specialized AI agents.
Intermediate - Agent Orchestration
AutoGen 0.4 Framework
A premier production framework in agent orchestration providing microsoft multi-agent conversation protocol.
Intermediate - Model Serving & Inference
AutoGPTQ Engine
A premier production framework in model serving & inference providing gptq 4-bit quantization and execution engine.
Intermediate - Generative WebUI
AUTOMATIC1111
The classic open-source web interface for Stable Diffusion image generation.
Beginner - Fine-Tuning Frameworks
Axolotl
A streamlined tool for fine-tuning LLMs supporting LoRA, QLoRA, FSDP, and DeepSpeed configurations.
Intermediate - Fine-Tuning & Optimization
Axolotl Fine-Tuning
A premier production framework in fine-tuning & optimization providing declarative llm fine-tuning cli tool.
Intermediate - AI Infrastructure
Banana Serverless
A premier production framework in ai infrastructure providing fast gpu serverless api platform.
Intermediate - AI Infrastructure
Baseten Deployment
A premier production framework in ai infrastructure providing production model serving infrastructure.
Intermediate - AI Infrastructure
Beam Cloud GPU
A premier production framework in ai infrastructure providing pythonic cloud infrastructure for machine learning.
Intermediate - Model Deployment
BentoML
An open-source framework for serving, packaging, and deploying machine learning models into microservices.
Intermediate - Software & SDKs
Biconomy Agent Kit
A premier production framework in software & sdks providing on-chain crypto transactions agent sdk.
Intermediate - Quantization Libraries
bitsandbytes
A lightweight CUDA wrapper library providing 8-bit and 4-bit quantization algorithms.
Intermediate - Fine-Tuning & Optimization
bitsandbytes Library
A premier production framework in fine-tuning & optimization providing cuda 8-bit and 4-bit quantization library.
Intermediate - Hardware Acceleration
Cerebras CS-3
Wafer-scale AI supercomputer system designed for massive foundation model training.
Advanced - Hardware & Accelerators
Cerebras CS-3 Engine
A premier production framework in hardware & accelerators providing wafer-scale engine ai compute hardware.
Intermediate - Vector Databases
ChromaDB
An open-source developer-friendly embedding database for AI application prototyping.
Beginner - RAG & Vector Search
ChromaDB Client
A premier production framework in rag & vector search providing embedded vector index client for python.
Intermediate - RAG & Vector Search
ChromaDB Vector Engine
A premier production framework in rag & vector search providing open-source native embedding database.
Intermediate - MLOps
ClearML
An open-source suite of MLOps tools for experiment tracking, orchestration, and data management.
Intermediate - MLOps
Comet ML (2)
Platform for tracking, comparing, and optimizing machine learning models.
Intermediate - Generative Workflows
ComfyUI
A node-based visual workflow GUI for Stable Diffusion and FLUX image generation.
Beginner - On-Device AI
CoreML
Apple's framework for integrating machine learning models directly into iOS and macOS applications.
Beginner - Agent Orchestration
CrewAI
A framework for orchestrating role-playing autonomous AI agents to solve complex workflows collaboratively.
Intermediate - Agent Orchestration
CrewAI Agent Framework
A premier production framework in agent orchestration providing multi-agent role-playing orchestration.
Intermediate - Hardware platform
CUDA
NVIDIA's parallel computing platform, the software layer nearly all GPU-accelerated AI runs on.
Advanced - Developer Tools
Daytona Agent Env
A premier production framework in developer tools providing development environment manager for ai agents.
Intermediate - AI Infrastructure
DeepInfra Cloud
A premier production framework in ai infrastructure providing low-cost serverless inference platform.
Intermediate - Distributed Training
DeepSpeed
Microsoft's deep learning optimization library enabling multi-billion parameter model training via ZeRO memory sharding.
Advanced - Model Architecture
DeepSpeed ZeRO-3
A premier production framework in model architecture providing distributed optimizer memory partitioning.
Intermediate - Generative Libraries
Diffusers
Hugging Face's modular library for state-of-the-art pretrained diffusion models.
Beginner - Generative Tools
Diffusers WebUI
Interface framework for managing diffusion pipeline settings.
Beginner - AI App Builders
Dify
An open-source LLM application development platform for building RAG and AI workflows.
Beginner - Data Extraction
Docling
IBM's open-source document parsing library rendering complex PDFs into structured formats.
Intermediate - Database Tools
Drizzle ORM
A lightweight, type-safe TypeScript ORM used in modern web and AI backend stacks.
Beginner - Prompt Optimization
DSPy
Stanford's framework that compiles declarative LM pipelines into optimized prompts and model weights.
Advanced - RAG & Vector Search
DuckDB Spatial & Vector
A premier production framework in rag & vector search providing in-process analytical vector database.
Intermediate - Developer Tools
E2B Code Sandbox
A premier production framework in developer tools providing secure cloud microvms for agent execution.
Intermediate - Tooling
Evaluation frameworks
Tooling for defining, running and tracking automated tests of AI system quality.
Intermediate - Model Serving & Inference
EXL2 Format
A premier production framework in model serving & inference providing exllamav2 variable bitrate quantization format.
Intermediate - Tooling
Experiment tracking
Recording the code, data, configuration and results of every training run so outcomes can be reproduced and compared.
Intermediate - Vector Search
Faiss
Meta's library for efficient dense vector similarity search and GPU-accelerated clustering.
Intermediate - RAG & Vector Search
FAISS Facebook AI
A premier production framework in rag & vector search providing meta gpu-accelerated vector similarity library.
Intermediate - Speech Libraries
faster-whisper
Re-implementation of OpenAI's Whisper using CTranslate2 for 4x faster transcription.
Beginner - Inference Hosting
Fireworks AI (3)
A fast inference engine platform serving open models with low latency and function calling support.
Beginner - AI Infrastructure
Fireworks LoRA API
A premier production framework in ai infrastructure providing dynamic multi-tenant lora serving gateway.
Intermediate - Hardware & Accelerators
FlashAttention-3 Kernel
A premier production framework in hardware & accelerators providing hopper gpu fp8 attention accelerator.
Intermediate - Inference Optimization
FlashInfer
A kernel library customizing attention acceleration for LLM serving engines.
Advanced - Visual Agent Builders
Flowise
A drag-and-drop visual interface for constructing LangChain agents and RAG pipelines.
Beginner - Generative WebUI
Fooocus
An intuitive image generation software simplifying Stable Diffusion XL prompting.
Beginner - AI Safety & Governance
Garak Scanner
A premier production framework in ai safety & governance providing llm vulnerability and security scanner.
Intermediate - Machine Learning Libraries
ggml
C tensor library for machine learning underlying llama.cpp and whisper.cpp engines.
Intermediate - Format
GGUF format
A file format for distributing quantised models for local inference, carrying weights and metadata in one file.
Advanced - AI Safety & Governance
Giskard Inspection
A premier production framework in ai safety & governance providing ai model evaluation and quality control tool.
Intermediate - Platform
GPU cloud
Rented accelerator capacity for training and inference, from hyperscalers and specialist providers.
Intermediate - UI Prototyping
Gradio
Python library for creating interactive web demos for machine learning models in minutes.
Beginner - Hardware Acceleration
Groq LPU
Language Processing Unit architecture delivering instant, 500+ token/sec LLM inference speed.
Intermediate - Hardware & Accelerators
Groq LPU Engine
A premier production framework in hardware & accelerators providing language processing unit hardware accelerator.
Intermediate - AI Safety & Governance
Guardrails AI Framework
A premier production framework in ai safety & governance providing input and output validation engine for llms.
Intermediate - Prompt Control
Guidance
A guidance language from Microsoft for controlling LLM output generation using interleaved templates.
Intermediate - Software & SDKs
Guidance Syntax Engine
A premier production framework in software & sdks providing microsoft interleaved control logic for llms.
Intermediate - RAG & Vector Search
Haystack 2.0 RAG
A premier production framework in rag & vector search providing deepset modular production rag framework.
Intermediate - AI Gateway
Helicone
Open-source LLM observability gateway providing caching, rate limiting, and cost tracking.
Beginner - Developer Tools
Helicone LLM Proxy
A premier production framework in developer tools providing open-source llm gateway & monitoring.
Intermediate - Algorithm
HNSW indexing
A graph-based approximate nearest-neighbour index that gives vector search its speed.
Advanced - Model Serving & Inference
Hugging Face TGI
A premier production framework in model serving & inference providing text generation inference container engine.
Intermediate - Library
Hugging Face Transformers (2)
The standard open-source library for loading, fine-tuning and running pretrained models.
Intermediate - Structured Outputs
Instructor
A Python library leveraging Pydantic to guarantee structured JSON outputs from LLM API providers.
Beginner - Software & SDKs
Instructor JS SDK
A premier production framework in software & sdks providing typescript type-safe output extraction.
Intermediate - Software & SDKs
Instructor Pydantic
A premier production framework in software & sdks providing type-safe structured output extraction library.
Intermediate - Software & SDKs
Jan Desktop AI
A premier production framework in software & sdks providing local private open-source ai application.
Intermediate - Framework
JAX (2)
A numerical computing library combining automatic differentiation with just-in-time compilation for accelerators.
Advanced - Model Serving & Inference
Jsonformer Decoder
A premier production framework in model serving & inference providing schema-constrained token generation engine.
Intermediate - Speech Engine
Kokoro Engine
An ultra-compact neural speech engine generating natural voices locally.
Beginner - Vector Databases
LanceDB
An open-source embedded vector database utilizing the column-based Lance file format.
Beginner - RAG & Vector Search
LanceDB Python
A premier production framework in rag & vector search providing pyarrow native vector storage sdk.
Intermediate - RAG & Vector Search
LanceDB Vector Store
A premier production framework in rag & vector search providing embedded serverless columnar vector database.
Intermediate - Framework
LangChain (2)
A framework for composing language model applications from chains, tools, retrievers and agents.
Intermediate - Visual Agent Builders
Langflow
A visual UI for building multi-agent AI systems with instant execution sandbox.
Beginner - AI Observability
Langfuse
Open-source LLM engineering platform for tracing, analytics, prompt management, and evaluation.
Beginner - Developer Tools
LangFuse Telemetry
A premier production framework in developer tools providing open-source llm analytics and tracing.
Intermediate - Agent Architecture
LangGraph
A library for building stateful, multi-actor agent workflows with cyclic loops and human-in-the-loop control.
Intermediate - Agent Orchestration
LangGraph Enterprise
A premier production framework in agent orchestration providing production state graph orchestration framework.
Intermediate - AI Observability
LangSmith
LangChain's platform for debugging, testing, evaluating, and monitoring LLM applications.
Intermediate - Developer Tools
LangSmith Platform
A premier production framework in developer tools providing langchain llm observability and tracing.
Intermediate - Local AI Interfaces
LibreChat
An open-source AI chat platform supporting multiple model providers and web search.
Beginner - AI Infrastructure
LiteLLM Gateway
A premier production framework in ai infrastructure providing universal api proxy and load balancer for 100+ llms.
Intermediate - AI Infrastructure
LiteLLM Proxy Router
A premier production framework in ai infrastructure providing load-balanced universal api gateway.
Intermediate - AI Safety & Governance
Llama Guard 3
A premier production framework in ai safety & governance providing meta input and output moderation classifier.
Intermediate - Model Serving & Inference
llama-cpp-python
A premier production framework in model serving & inference providing python bindings for llama.cpp engine.
Intermediate - Local runtime
llama.cpp (2)
A C++ inference engine that runs quantised language models efficiently on CPUs and consumer GPUs.
Advanced - Framework
LlamaIndex (2)
A data framework focused on connecting private data to language models through indexing and retrieval.
Intermediate - RAG & Vector Search
LlamaIndex Workflows
A premier production framework in rag & vector search providing event-driven async rag architecture.
Intermediate - Local LLM Tools
LM Studio
A desktop application allowing users to discover, download, and run local GGUF models with a local API server.
Beginner - Software & SDKs
LM Studio Runtime
A premier production framework in software & sdks providing desktop app for running local llms.
Intermediate - Software & SDKs
LMQL Query Language
A premier production framework in software & sdks providing language model query language for logic.
Intermediate - Workflow Automation
Make.com AI Modules
Visual automation builder incorporating OpenAI, Claude, and custom API nodes.
Beginner - Data Extraction
Marker PDF
Deep learning pipeline converting PDF documents into clean, structured Markdown text.
Intermediate - RAG & Vector Search
Marqo Search Platform
A premier production framework in rag & vector search providing multimodal vector search engine.
Intermediate - Distributed Training
Megatron-LM
NVIDIA's framework for training large-scale Transformer models using tensor, pipeline, and sequence parallelism.
Advanced - Model Architecture
Megatron-LM Parallelism
A premier production framework in model architecture providing nvidia distributed model parallel framework.
Intermediate - Vector Databases
Milvus
A cloud-native, open-source vector database built for massive enterprise embedding search.
Advanced - RAG & Vector Search
Milvus 2.4 Engine
A premier production framework in rag & vector search providing distributed cloud-native vector database.
Intermediate - RAG & Vector Search
Milvus Attu UI
A premier production framework in rag & vector search providing graphical dashboard for milvus vector clusters.
Intermediate - Model Serving & Inference
MLC LLM Engine
A premier production framework in model serving & inference providing universal on-device mobile ai runtime.
Intermediate - MLOps
MLflow
An open-source platform for managing the end-to-end machine learning lifecycle.
Intermediate - Frameworks
MLX
Apple's array framework designed specifically for efficient machine learning on Apple Silicon GPUs.
Intermediate - AI Infrastructure
Modal GPU Compute
A premier production framework in ai infrastructure providing serverless python gpu cloud platform.
Intermediate - Developer Tools
Modal GPU Sandbox
A premier production framework in developer tools providing isolated python code execution microvm.
Intermediate - Cloud Compute
Modal Labs (3)
A serverless cloud platform running Python, GPU containers, and AI batch jobs in seconds.
Intermediate - Platform
Model hub
A repository where model weights, datasets and demos are published, versioned and documented.
Beginner - Workflow Automation
n8n AI Integration
Fair-code workflow automation platform integrating LLMs, vectors, and tool nodes.
Beginner - AI Safety & Governance
NeMo Guardrails
A premier production framework in ai safety & governance providing nvidia programmable safety framework for llms.
Intermediate - MLOps
Neptune.ai
Experiment tracker for foundation model training and hyperparameter logging.
Intermediate - Platform
No-code AI builders
Visual tools that let non-programmers assemble AI workflows, chatbots and applications.
Beginner - Tooling
Notebooks
Interactive documents mixing code, output and narrative, the standard environment for data and model experimentation.
Beginner - AI Infrastructure
OctoAI Inference
A premier production framework in ai infrastructure providing optimized model serving cloud engine.
Intermediate - Local runtime
Ollama (2)
A tool for downloading and running open-weight models locally with a single command.
Beginner - Standard
ONNX
An open format for representing trained models so they can be moved between frameworks and runtimes.
Advanced - Interoperability
ONNX Format
Open Neural Network Exchange format for transferring models between frameworks.
Beginner - Model Optimization
ONNX Runtime
A cross-platform high-performance engine for accelerating machine learning inference.
Intermediate - Model Serving & Inference
ONNX Runtime GenAI
A premier production framework in model serving & inference providing microsoft high-performance cross-platform engine.
Intermediate - Local AI Interfaces
Open WebUI
Extensible, self-hosted AI interface for local LLMs via Ollama.
Beginner - Standard
OpenAI-compatible API
The chat completions request format that most providers and local runtimes now implement, making models broadly interchangeable.
Beginner - Developer Tools
OpenInference Standard
A premier production framework in developer tools providing opentelemetry specification for genai.
Intermediate - Model Optimization
OpenVINO
Intel's open-source toolkit optimizing deep learning models for deployment on Intel hardware.
Intermediate - Model Optimization
Optimum
Hugging Face extension optimizing models for ONNX Runtime and hardware accelerators.
Intermediate - Structured Sampling
Outlines
A library providing fast, guaranteed structured text generation using neural logit masking.
Intermediate - OCR Engines
PaddleOCR
Baidu's practical multilingual OCR toolkit supporting document table and text recognition.
Intermediate - Fine-Tuning Libraries
PEFT (3)
Hugging Face's Parameter-Efficient Fine-Tuning library supporting LoRA, Prefix Tuning, and P-Tuning.
Intermediate - Database extension
pgvector
A PostgreSQL extension that adds vector storage and similarity search to a standard relational database.
Intermediate - Vector Databases
Pinecone (2)
A fully managed serverless vector database providing low-latency similarity search.
Beginner - RAG & Vector Search
Pinecone Serverless
A premier production framework in rag & vector search providing decoupled compute-storage vector database.
Intermediate - Audio Libraries
Piper TTS
A fast, local neural text-to-speech engine optimized for Raspberry Pi and low-power devices.
Beginner - AI Gateway
Portkey
Control panel for production AI apps offering fallback routing, retries, and latency monitoring.
Intermediate - AI Infrastructure
Portkey AI Gateway
A premier production framework in ai infrastructure providing enterprise ai gateway and fallback router.
Intermediate - AI Safety & Governance
Presidio Protection
A premier production framework in ai safety & governance providing microsoft pii redaction and sanitization engine.
Intermediate - Optimisation
Prompt caching
Reusing the processed representation of a repeated prompt prefix so it is not recomputed on every request.
Intermediate - AI Safety & Governance
PromptFoo Testing
A premier production framework in ai safety & governance providing security and quality cli testing for prompts.
Intermediate - Developer Tools
Promptlayer Platform
A premier production framework in developer tools providing prompt management and analytics tool.
Intermediate - AI Safety & Governance
PyRIT Framework
A premier production framework in ai safety & governance providing microsoft python risk identification tool for ai.
Intermediate - Framework
PyTorch
The dominant open-source deep learning framework, used for most AI research and a large share of production training.
Intermediate - Frameworks
PyTorch 2.5
The premier open-source machine learning library powered by dynamic computation graphs and TorchCompile.
Intermediate - Vector Databases
Qdrant (2)
An open-source vector search engine and database written in Rust with payload filtering capabilities.
Intermediate - RAG & Vector Search
Qdrant Hybrid Search Engine
A premier production framework in rag & vector search providing sparse-dense vector search framework.
Intermediate - Architecture stack
RAG stack
The combination of ingestion, chunking, embedding, indexing, retrieval, reranking and generation that a production RAG system needs.
Intermediate - Distributed Compute
Ray
An open-source unified framework for scaling AI and Python applications across compute clusters.
Advanced - AI Cloud API
Replicate (2)
A cloud platform enabling developers to run open-source machine learning models via simple API calls.
Beginner - AI Infrastructure
Replicate Cloud
A premier production framework in ai infrastructure providing serverless api cloud for open ai models.
Intermediate - Software & SDKs
Rig Rust Agent Framework
A premier production framework in software & sdks providing rust high-performance agent sdk.
Intermediate - GPU Orchestration
Run:ai
A Kubernetes-based GPU orchestration platform maximizing cluster utilization for enterprise AI.
Advanced - Cloud GPU Infrastructure
RunPod
A cloud GPU provider renting on-demand NVIDIA A100, H100, and RTX GPUs for AI workloads.
Beginner - AI Infrastructure
RunPod GPU Cloud
A premier production framework in ai infrastructure providing on-demand gpu infrastructure for ai.
Intermediate - File Formats
Safetensors
A simple, secure format for storing tensors safely compared to Python pickle files.
Beginner - Hardware & Accelerators
SambaNova SN40
A premier production framework in hardware & accelerators providing reconfigurable dataflow unit ai accelerator.
Intermediate - RAG & Vector Search
ScaNN Vector Engine
A premier production framework in rag & vector search providing google anisotropic vector quantization library.
Intermediate - Enterprise AI SDK
Semantic Kernel
Microsoft's open-source enterprise SDK for integrating LLM plugins into C#, Python, and Java applications.
Intermediate - Software & SDKs
Semantic Kernel SDK
A premier production framework in software & sdks providing microsoft enterprise ai integration sdk.
Intermediate - Model Serving & Inference
SGLang Engine
A premier production framework in model serving & inference providing radixattention high-performance llm serving.
Intermediate - AI Safety & Governance
ShieldGemma Guard
A premier production framework in ai safety & governance providing google moderation model suite for safety.
Intermediate - Optimisation
Speculative decoding
Using a small fast model to draft several tokens that a larger model verifies in one pass, accelerating generation.
Advanced - UI Prototyping
Streamlit
Python framework for building data science and AI web dashboards quickly.
Beginner - Cloud Databases
Supabase Vector
PostgreSQL vector database suite with built-in embeddings and Edge Functions integration.
Beginner - OCR Engines
Surya OCR
Multilingual OCR and layout analysis model supporting line-level text detection across languages.
Intermediate - Tooling
Synthetic data generation
Software that produces artificial datasets for training, testing and privacy-preserving analysis.
Advanced - Framework
TensorFlow
Google's deep learning framework, strongest today in production serving, mobile and browser deployment.
Intermediate - Inference Engines
TensorRT-LLM
NVIDIA's library for compiling and optimizing LLM inference on Tensor Core GPUs.
Advanced - Model Serving & Inference
TensorRT-LLM Engine
A premier production framework in model serving & inference providing nvidia high-performance inference compiler.
Intermediate - OCR Engines
Tesseract OCR
Classic open-source optical character recognition engine for text extraction.
Beginner - Inference Engines
Text Generation Inference (TGI)
Hugging Face's production-ready serving solution for deploying LLMs with tensor parallelism and spec decoding.
Intermediate - Cloud Compute
Together AI (2)
A cloud platform providing fast API inference and cluster training for open foundation models.
Beginner - AI Infrastructure
Together AI Cloud
A premier production framework in ai infrastructure providing fast cloud inference and fine-tuning api.
Intermediate - Model Serving
TorchServe
A flexible open-source tool for serving PyTorch models in production.
Intermediate - AI Infrastructure
TorchTitan Trainer
A premier production framework in ai infrastructure providing pytorch distributed native pre-training engine.
Intermediate - PyTorch Ecosystem
torchtune
PyTorch's native library for modular LLM fine-tuning.
Intermediate - Fine-Tuning & Optimization
Torchtune Library
A premier production framework in fine-tuning & optimization providing pytorch native llm fine-tuning library.
Intermediate - Hardware
TPU (2)
Google's custom accelerators designed specifically for neural network training and inference.
Advanced - Hardware & Accelerators
Transformers Engine
A premier production framework in hardware & accelerators providing nvidia hopper & ada fp8 speedup library.
Intermediate - Web AI
Transformers.js
Run Hugging Face Transformers directly inside web browsers using WebAssembly and WebGPU.
Beginner - GPU Programming
Triton
A Python-like programming language and compiler for writing custom high-throughput CUDA GPU kernels.
Advanced - Hardware & Accelerators
Triton Compiler
A premier production framework in hardware & accelerators providing open-source cuda kernel programming language.
Intermediate - Model Serving
Triton Inference Server
NVIDIA's enterprise serving software standardizing AI inference deployment across GPUs and CPUs.
Advanced - AI Observability
TruEra
AI quality management and observability platform evaluating RAG and LLM applications.
Intermediate - RAG & Vector Search
Turbopuffer Database
A premier production framework in rag & vector search providing serverless fast vector indexing cloud.
Intermediate - Software & SDKs
TypeChat Translator
A premier production framework in software & sdks providing microsoft typescript schema validation sdk.
Intermediate - Fine-Tuning Acceleration
Unsloth
An open-source framework accelerating LLM fine-tuning speeds by 2x-5x while reducing VRAM usage by 80%.
Intermediate - Fine-Tuning & Optimization
Unsloth Acceleration
A premier production framework in fine-tuning & optimization providing optimized cuda kernel fine-tuning tool.
Intermediate - Fine-Tuning & Optimization
Unsloth AI
An open-source library that speeds up LLM fine-tuning by up to 5x with 80% less memory using optimized custom CUDA kernels.
Intermediate - Data Processing
Unstructured.io
ETL tool for ingesting and processing unstructured documents (PDFs, PPTs) for RAG.
Beginner - RAG & Vector Search
USearch Vector Store
A premier production framework in rag & vector search providing compact c++ fast vector search library.
Intermediate - GPU Marketplace
Vast.ai
A peer-to-peer compute marketplace for renting low-cost GPU instances.
Beginner - Software & SDKs
Vercel AI SDK 4.0
A premier production framework in software & sdks providing typescript unified web ai streaming framework.
Intermediate - RAG & Vector Search
Vespa Search Engine
A premier production framework in rag & vector search providing yahoo open-source big-data vector engine.
Intermediate - Serving runtime
vLLM (2)
A high-throughput inference server for open-weight language models, built around efficient KV cache management.
Advanced - Model Serving & Inference
vLLM PagedAttention Engine
A premier production framework in model serving & inference providing memory-efficient llm serving framework.
Intermediate - Model Serving & Inference
vLLM PagedAttention v2
An upgraded high-throughput inference engine featuring enhanced multi-GPU KV cache allocation and low-latency chunked prefill.
Advanced - Model Serving & Inference
vLLM Serving Engine
A high-throughput LLM serving engine powered by PagedAttention for optimal KV-cache management.
Advanced - Vector Databases
Weaviate (2)
An open-source vector database with hybrid search, GraphQL, and native multi-modal support.
Intermediate - RAG & Vector Search
Weaviate Modules
A premier production framework in rag & vector search providing custom plugin architecture for weaviate.
Intermediate - RAG & Vector Search
Weaviate Vector DB
A premier production framework in rag & vector search providing graphql native vector search database.
Intermediate - Inference
WebGPU AI
Web standard bringing hardware-accelerated GPU compute to web browsers for client-side AI.
Intermediate - Runtime
WebGPU for AI
A browser API that exposes GPU compute, allowing models to run client-side without a server.
Advanced - MLOps & Experiment Tracking
Weights & Biases (W&B)
The developer platform for experiment tracking, dataset versioning, and evaluation.
Beginner - Workflow Automation
Zapier Central
AI bot platform connecting natural language instructions with 6,000+ app actions.
Beginner