Main Page
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Best practices and expert-level knowledge for Machine Learning and Data Engineering, covering 1000+ frameworks and libraries from training to deployment.
Browse implementation patterns, configuration guides, debugging heuristics, and battle-tested defaults for frameworks like vLLM, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more. Every page is structured so both humans and AI agents can find what they need fast.
Connect your AI coding agent. Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously:
- SuperML plugin — converts your AI coding agent into an expert ML engineer with agentic memory
- Leeroopedia MCP — search over best-practices and skills of ML/AI
- Kapso — experimentation platform for autonomous AI/ML software building
Browse by Category
| Category | Description | Browse |
|---|---|---|
| Workflows | Step-by-step processes and procedures | Browse All |
| Principles | Core ideas and foundational knowledge | Browse All |
| Implementations | Code-level details and modules | Browse All |
| Heuristics | Best practices and guidelines | Browse All |
| Environments | Setup and configuration guides | Browse All |
Explore Pages
Workflows
- Workflow:Openai Openai agents python Basic Agent Execution
- Workflow:Protectai Llm guard PII Anonymization Deanonymization
- Workflow:Deepseek ai Janus Multimodal Understanding
- Workflow:Mage ai Mage ai API Source Extraction
- Workflow:Arize ai Phoenix Trace Ingestion Pipeline
- Workflow:Apache Beam Twister2 Batch Execution
- Workflow:Apache Kafka Release Candidate Staging
- Workflow:AUTOMATIC1111 Stable diffusion webui Checkpoint merging
- Workflow:Sdv dev SDV Single table synthesis
- Workflow:Duckdb Duckdb Building From Source
Principles
- Principle:Wandb Weave Model Definition
- Principle:DistrictDataLabs Yellowbrick Discrimination Threshold Analysis
- Principle:Ollama Ollama LLM Memory Architecture
- Principle:NVIDIA TransformerEngine Baseline Transformer Layer
- Principle:Eventual Inc Daft Error Hierarchy
- Principle:Turboderp org Exllamav2 LoRA Adapter Loading
- Principle:ARISE Initiative Robosuite Omniverse Rendering
- Principle:Deepset ai Haystack Document Data Model
- Principle:Apache Paimon Table Writing
- Principle:Apache Paimon Ingestion Verification
Implementations
- Implementation:FlowiseAI Flowise SpeechToText
- Implementation:Cohere ai Cohere python Image Model
- Implementation:Langgenius Dify Env File Setup
- Implementation:Spotify Luigi Marker Table Check
- Implementation:Evidentlyai Evidently Legacy LLM Judge Feature
- Implementation:DevExpress Testcafe TestingUnit
- Implementation:Apache Airflow MetricsRegistry
- Implementation:Mlc ai Mlc llm Serve Data Py
- Implementation:BerriAI Litellm Braintrust Logger
- Implementation:Onnx Onnx Helper Make Node
Heuristics
- Heuristic:Tensorflow Tfjs Backend Selection Strategy
- Heuristic:Spotify Luigi Dynamic Requirements Generator
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Elevenlabs Elevenlabs python TTS Model Selection
- Heuristic:Kornia Kornia CPU GPU Branching Tip
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
- Heuristic:Lance format Lance Vector Index Tuning
- Heuristic:Datahub project Datahub Emitter Selection Strategy
- Heuristic:ArroyoSystems Arroyo Parallelism Configuration
- Heuristic:Ggml org Llama cpp Batch Size BLAS Minimum
Environments
- Environment:Bigscience workshop Petals Python Hivemind
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:DevExpress Testcafe Chrome Browser
- Environment:Deepspeedai DeepSpeed CPU Environment
- Environment:Apache Shardingsphere ZooKeeper Cluster Coordination
- Environment:Facebookresearch Habitat lab Python 3 9 Core Dependencies
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:Volcengine Verl Megatron Core Environment
- Environment:Langchain ai Langchain Anthropic API Credentials
- Environment:OpenHands OpenHands Integration Credentials