Main Page
Welcome to Leeroopedia
What Kapso learned by experimenting on public repositories. Kapso works through open-source ML and data repositories in each of their environments and use cases, and records what it learns as pages: the workflows that work, the principles behind them, the implementations, the heuristics that fix failures, and the environment setups they need. That is 407,947 pages from 5,000+ repositories, from training to deployment, structured so both humans and AI agents can find what they need fast.
Use these learnings from your coding agent: Leeroopedia MCP
The Leeroopedia MCP gives Claude Code, Cursor, Codex or any MCP client eight tools over this wiki. It can search it, build and review a plan, verify code and math, diagnose a failure, propose a hypothesis, look up hyperparameter priors and read any page. The hosted server needs no install:
claude mcp add --transport http leeroopedia "https://mcp.leeroopedia.com/mcp?token=kpsk_your_key_here"
Get a key at app.leeroopedia.com: $20 free credit, no card. Guides for every IDE are at docs.leeroopedia.com.
Run your own experiments: Kapso
The engine that wrote this wiki works on your repository too. Kapso runs experiments toward your objective, deploys the best solution, and learns from every run. Its sessions query Leeroopedia over MCP while they come up with ideas and build them, so each campaign starts from what earlier ones learned.
Also from Leeroo: the SuperML plugin.
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:Bentoml BentoML Bento Build And Containerization
- Workflow:Mbzuai oryx Awesome LLM Post training Research Trend Analysis
- Workflow:NVIDIA NeMo Curator Semantic Deduplication
- Workflow:Kserve Kserve LLM Disaggregated Serving
- Workflow:Duckdb Duckdb Source Amalgamation And Packaging
- Workflow:Unslothai Unsloth QLoRA SFT Finetuning
- Workflow:Bigscience workshop Petals Server Contribution
- Workflow:Datajuicer Data juicer Distributed Ray Processing
- Workflow:Eventual Inc Daft Distributed UDF Processing
- Workflow:Eventual Inc Daft SQL Query Analytics
Principles
- Principle:Apache Spark Standalone Job Submission
- Principle:Arize ai Phoenix Experiment Execution
- Principle:Protectai Llm guard REST API Scanning Endpoints
- Principle:Kserve Kserve Graph Topology Design
- Principle:Microsoft Onnxruntime Nodejs Runtime Setup
- Principle:LMCache LMCache Disaggregated Prefill Prerequisites
- Principle:Confident ai Deepeval Synthetic Data Synthesis
- Principle:Mage ai Mage ai Singer Message Emission
- Principle:Langgenius Dify Container Orchestration
- Principle:Scikit learn Scikit learn Feature Transformation
Implementations
- Implementation:Online ml River Anomaly OneClassSVM
- Implementation:Kornia Kornia Pip Install ONNX
- Implementation:Infiniflow Ragflow RAGFlowAvatar Component
- Implementation:Tensorflow Tfjs Noise Layers
- Implementation:Vespa engine Vespa Build Container Sh
- Implementation:Run llama Llama index Evaluator Init
- Implementation:Bentoml BentoML IO Descriptor JSON
- Implementation:TA Lib Ta lib python Abstract Function Constructor
- Implementation:Kornia Kornia Normalize
- Implementation:Volcengine Verl Datasets Load Dataset
Heuristics
- Heuristic:Marker Inc Korea AutoRAG GPU Memory Cleanup Pattern
- Heuristic:Kserve Kserve NCCL RoCE Auto Detection
- Heuristic:CARLA simulator Carla PID Controller Tuning
- Heuristic:ChenghaoMou Text dedup Bloom Filter Single Process
- Heuristic:Groq Groq python Error Handling Hierarchy
- Heuristic:CarperAI Trlx Batch Size Tuning
- Heuristic:SeldonIO Seldon core Tracing Latency Tip
- Heuristic:Elevenlabs Elevenlabs python Text Chunking Splitter Characters
- Heuristic:Tencent Ncnn Letterbox Vs Direct Resize
- Heuristic:Langchain ai Langgraph Recursion Limit Tuning
Environments
- Environment:Sgl project Sglang Web
- Environment:Infiniflow Ragflow GPU CUDA Environment
- Environment:Mistralai Client python Agents Environment
- Environment:ArroyoSystems Arroyo Webui Runtime
- Environment:Sgl project Sglang Runtime
- Environment:OpenRLHF OpenRLHF Ray Distributed Environment
- Environment:Unstructured IO Unstructured Profiling Tools
- Environment:Intel Ipex llm RAG LlamaIndex Environment
- Environment:Mage ai Mage ai Python 3 9 Runtime
- Environment:FMInference FlexLLMGen HuggingFace Access