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:Avhz RustQuant Stochastic Process Simulation
- Workflow:Neuml Txtai API Deployment
- Workflow:Openclaw Openclaw Agent Message Loop
- Workflow:Openai CLIP Linear probe evaluation
- Workflow:MarketSquare Robotframework browser Plugin Development
- Workflow:Fastai Fastbook Neural Network From Scratch
- Workflow:Ray project Ray Remote Task Execution
- Workflow:Risingwavelabs Risingwave Iceberg Lakehouse Ingestion
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:Triton inference server Server Quickstart Model Deployment
Principles
- Principle:Apache Paimon Target Table Preparation
- Principle:Guardrails ai Guardrails HubPackageManagement
- Principle:Openai Openai python Input Token Counting
- Principle:Heibaiying BigData Notes Spark Data Writing
- Principle:Google deepmind Dm control Props and Targets
- Principle:Confident ai Deepeval Faithfulness Evaluation
- Principle:Openai Whisper Model Loading
- Principle:Teamcapybara Capybara Form Submission
- Principle:Ggml org Llama cpp Model Serialization
- Principle:Facebookresearch Habitat lab Metric Visualization
Implementations
- Implementation:Interpretml Interpret LimeTabular
- Implementation:Sail sg LongSpec MathScale Answer Utils
- Implementation:BerriAI Litellm Service Logger
- Implementation:Huggingface Alignment handbook DPOTrainer APO Zero
- Implementation:Huggingface Datasets ParquetDatasetReader
- Implementation:Elevenlabs Elevenlabs python TextToSpeechClient Convert
- Implementation:FlowiseAI Flowise SaveProcessingLoader
- Implementation:CrewAIInc CrewAI Knowledge Storage Search
- Implementation:Haosulab ManiSkill ManiSkillTrajectoryDataset
- Implementation:NVIDIA DALI CUDAStreamPool
Heuristics
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Identity Loss Color Preservation
- Heuristic:Lm sys FastChat Tokenizer Offset Correction
- Heuristic:Turboderp org Exllamav2 Quantization Conversion Tips
- Heuristic:LMCache LMCache Memory Fragmentation Budget
- Heuristic:Zai org CogVideo DeepSpeed Checkpoint Conversion Tips
- Heuristic:Openai Evals Thread Tuning
- Heuristic:Openai Openai agents python Tool Choice Reset Prevents Loops
- Heuristic:SqueezeAILab ETS Softmax Temperature Tuning
- Heuristic:Openai CLIP L2 Normalization For Cosine Similarity
- Heuristic:Treeverse LakeFS S3 Multipart Size Constraint
Environments
- Environment:DataTalksClub Data engineering zoomcamp Kestra Orchestration Environment
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment
- Environment:Openclaw Openclaw Gateway Network Ports
- Environment:ClickHouse ClickHouse Linux Build Environment
- Environment:Datahub project Datahub Frontend Build
- Environment:Alibaba ROLL Python Runtime Environment
- Environment:Fede1024 Rust rdkafka Rust Librdkafka Build Environment
- Environment:Apache Flink Java Build Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Matplotlib
- Environment:Scikit learn contrib Imbalanced learn Python Scikit learn