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:HKUDS AI Trader Multi Agent Comparison
- Workflow:Google research Deduplicate text datasets Single file deduplication
- Workflow:Scikit learn contrib Imbalanced learn Ensemble Imbalanced Classification
- Workflow:Arize ai Phoenix Prompt Management Pipeline
- Workflow:Guardrails ai Guardrails Server Deployment
- Workflow:Onnx Onnx External Data Handling
- Workflow:FMInference FlexLLMGen HELM Benchmark Evaluation
- Workflow:Mistralai Client python Streaming Chat Completion
- Workflow:Ucbepic Docetl YAML Pipeline Execution
- Workflow:NVIDIA DALI Custom Operator Development
Principles
- Principle:NVIDIA NeMo Curator Bucket to Edge Conversion
- Principle:Datahub project Datahub Entity Read Modify
- Principle:Scikit learn Scikit learn Probability Calibration
- Principle:CrewAIInc CrewAI Baseline Crew Configuration
- Principle:DataExpert io Data engineer handbook AB Test SDK Initialization
- Principle:SeleniumHQ Selenium Coding Convention Compliance
- Principle:Onnx Onnx Operator Node Construction
- Principle:Pyro ppl Pyro Biological Sequence Models
- Principle:PrefectHQ Prefect AI Agent Configuration
- Principle:Zai org CogVideo DDIM Pipeline Loading
Implementations
- Implementation:Princeton nlp Tree of thought llm Solve BFS
- Implementation:Facebookresearch Habitat lab HumanoidSeqPoseController
- Implementation:Haifengl Smile Streaming Prediction API
- Implementation:Online ml River Bandit Envs KArmedTestbed
- Implementation:Astronomer Astronomer cosmos Cluster Policy
- Implementation:CARLA simulator Carla BufferPool
- Implementation:CARLA simulator Carla Pugixml Interface
- Implementation:Microsoft BIPIA FewShotChatGPT35Defense Construct Example
- Implementation:Teamcapybara Capybara Minitest Expectations
- Implementation:Elevenlabs Elevenlabs python McpServerConfigOutput
Heuristics
- Heuristic:Danijar Dreamerv3 Replay Context Carry Init
- Heuristic:DevExpress Testcafe CDP Performance Monitoring
- Heuristic:Romsto Speculative Decoding Seed Fixing For Reproducibility
- Heuristic:Huggingface Datatrove Gopher Quality Thresholds
- Heuristic:Apache Airflow Scheduler Performance Tuning
- Heuristic:Google deepmind Dm control Physics Timestep Configuration
- Heuristic:InternLM Lmdeploy Max Batch Size Selection
- Heuristic:ArroyoSystems Arroyo Batch Size And Backpressure
- Heuristic:Protectai Llm guard Token Limit Early Guard
- Heuristic:Princeton nlp SimPO Left Truncation Strategy
Environments
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Mistralai Client python Agents Environment
- Environment:Datahub project Datahub Python Ingestion
- Environment:Openai Openai python Voice Helpers
- Environment:Mistralai Client python GCP Deployment Environment
- Environment:Fede1024 Rust rdkafka Rust Librdkafka Build Environment
- Environment:Apache Paimon Optional Extensions
- Environment:Haosulab ManiSkill Python SAPIEN Core
- Environment:AUTOMATIC1111 Stable diffusion webui Xformers Attention
- Environment:Sgl project Sglang ROCm