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:Langgenius Dify Knowledge Base Management
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:Online ml River Time Series Forecasting
- Workflow:DistrictDataLabs Yellowbrick Cluster Analysis
- Workflow:Hpcaitech ColossalAI DPO Alignment
- Workflow:Openai Openai agents python Guardrails Secured Agent
- Workflow:Mlc ai Web llm Chrome Extension Integration
- Workflow:Truera Trulens LangGraph Agent Evaluation
- Workflow:Dotnet Machinelearning Binary Classification Pipeline
- Workflow:Risingwavelabs Risingwave Iceberg Lakehouse Ingestion
Principles
- Principle:Romsto Speculative Decoding Interactive CLI
- Principle:Diagram of thought Diagram of thought Task Requirements Definition
- Principle:Guardrails ai Guardrails BuildInfrastructure
- Principle:Triton inference server Server Model Weight Download
- Principle:Scikit learn Scikit learn Density Estimation
- Principle:Haosulab ManiSkill Tensor RNG Reward Primitives
- Principle:Isaac sim IsaacGymEnvs Population Based Training
- Principle:Google deepmind Mujoco Control Noise Generation
- Principle:Intel Ipex llm RAG Chain Assembly
- Principle:Webdriverio Webdriverio CommandLifecycle
Implementations
- Implementation:Apache Airflow Provider Yaml Schema
- Implementation:Sgl project Sglang Scalar Type
- Implementation:Evidentlyai Evidently Legacy Text Part Feature
- Implementation:Bigscience workshop Petals AutoTokenizer From Pretrained
- Implementation:PrefectHQ Prefect Pydantic AI Agent Setup
- Implementation:Langfuse Langfuse CompileChatMessages
- Implementation:Microsoft Onnxruntime TrainingOptimizer
- Implementation:Openai Evals Classify Function
- Implementation:Ggml org Llama cpp Convert Llama GGML To GGUF
- Implementation:Guardrails ai Guardrails SQLiteTraceHandler
Heuristics
- Heuristic:Recommenders team Recommenders Test Timing Budgets
- Heuristic:CARLA simulator Carla Sensor Queue Synchronization Pattern
- Heuristic:PrefectHQ Prefect SQLite Performance Tuning
- Heuristic:OpenHands OpenHands Clustered Race Condition Prevention
- Heuristic:Langchain ai Langgraph Checkpointer Selection Guide
- Heuristic:Onnx Onnx Protobuf 2GB Limit Workaround
- Heuristic:Allenai Open instruct Disable Dropout In RL
- Heuristic:Openai Openai python Fine Tuning Data Preparation Tips
- Heuristic:Sktime Pytorch forecasting Gradient Clipping Value
- Heuristic:Facebookresearch Audiocraft Generation Parameter Defaults
Environments
- Environment:FlowiseAI Flowise Database Environment
- Environment:Vibrantlabsai Ragas Optional NLP Metrics Environment
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Duckdb Duckdb Code Generation Tools
- Environment:Snorkel team Snorkel PySpark
- Environment:Evidentlyai Evidently Python Core Environment
- Environment:Intel Ipex llm CPU Finetuning Environment
- Environment:Marker Inc Korea AutoRAG Vector Database Backends
- Environment:CarperAI Trlx NeMo Megatron
- Environment:Huggingface Trl DeepSpeed Environment