Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:OpenGVLab InternVL LoRA Finetuning
- Workflow:CrewAIInc CrewAI Sequential Crew Execution
- Workflow:Axolotl ai cloud Axolotl Multimodal Vision Finetuning
- Workflow:Apache Druid Visual Data Exploration
- Workflow:Fede1024 Rust rdkafka Produce Consume Roundtrip
- Workflow:Scikit learn Scikit learn Data Preprocessing Pipeline
- Workflow:Zai org CogVideo Video Captioning
- Workflow:OpenHands OpenHands Conversation Lifecycle Management
- Workflow:Cohere ai Cohere python Semantic Search With Rerank
- Workflow:Mistralai Client python Azure Chat Completion
Principles
- Principle:Princeton nlp SimPO Dataset Loading and Mixing
- Principle:Apache Druid Streaming Source Configuration
- Principle:LMCache LMCache Disaggregated Proxy Routing
- Principle:MarketSquare Robotframework browser Page Navigation and Interaction
- Principle:Recommenders team Recommenders Ranking Rating Evaluation
- Principle:TobikoData Sqlmesh Virtual Layer Update
- Principle:Alibaba ROLL Policy Gradient Optimization
- Principle:Google deepmind Mujoco Visualization Initialization
- Principle:OWASP Www project top 10 for large language model applications Risk Scoring and Prioritization
- Principle:Ggml org Ggml Model Training
Implementations
- Implementation:NVIDIA TransformerEngine PyTorch Ext Swizzle
- Implementation:Haosulab ManiSkill UnitreeG1
- Implementation:Guardrails ai Guardrails Hub Install
- Implementation:Microsoft Playwright FrameSelectors
- Implementation:Haotian liu LLaVA Load Pretrained Model
- Implementation:Mage ai Mage ai Google Sheets Transform
- Implementation:Apache Airflow RBAC Security Config
- Implementation:Openai Openai python Response Computer Tool Call Param
- Implementation:Puppeteer Puppeteer Errors
- Implementation:ArroyoSystems Arroyo Controller Server
Heuristics
- Heuristic:Risingwavelabs Risingwave Stream Chunk Sizing
- Heuristic:Fede1024 Rust rdkafka Producer Flush Before Drop
- Heuristic:Tensorflow Tfjs WASM Cross Origin Isolation
- Heuristic:OpenHands OpenHands Redis Distributed Locking
- Heuristic:Langfuse Langfuse Eval Loop Prevention
- Heuristic:Microsoft Agent framework Typed Agent Options Pattern
- Heuristic:Roboflow Rf detr Small Dataset Oversampling
- Heuristic:Datahub project Datahub Emitter Selection Strategy
- Heuristic:Openai Openai python Retry Backoff Strategy
- Heuristic:Mlflow Mlflow Async Logging Best Practices
Environments
- Environment:EvolvingLMMs Lab Lmms eval Python Runtime Environment
- Environment:Liu00222 Open Prompt Injection CUDA Environment
- Environment:Bentoml BentoML BentoCloud Credentials
- Environment:Astronomer Astronomer cosmos Cosmos Airflow Configuration
- Environment:Dagster io Dagster DAGSTER HOME Configuration
- Environment:FMInference FlexLLMGen HuggingFace Access
- Environment:Openai Openai python Realtime WebSocket
- Environment:Cleanlab Cleanlab Python Core Environment
- Environment:Farama Foundation Gymnasium Box2D Physics Backend
- Environment:ContextualAI HALOs CUDA 12 1 Training Environment