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:Microsoft Autogen Studio Team Deployment
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:Microsoft Playwright AI agent driven testing
- Workflow:Zai org CogVideo SAT Finetuning
- Workflow:Liu00222 Open Prompt Injection DataSentinel Detection
- Workflow:Promptfoo Promptfoo Red Team Security Scan
- Workflow:Interpretml Interpret Model Explanation And Visualization
- Workflow:Hiyouga LLaMA Factory DPO Preference Alignment
- Workflow:Facebookresearch Audiocraft MusicGen Training Pipeline
- Workflow:Apache Beam Local Pipeline Execution
Principles
- Principle:Langfuse Langfuse Export Storage Upload
- Principle:Cleanlab Cleanlab Segmentation Label Issue Filtering
- Principle:Langgenius Dify Annotation System
- Principle:Microsoft Onnxruntime Training Artifact Generation
- Principle:Langgenius Dify React Context Pattern
- Principle:NVIDIA NeMo Aligner Knowledge Distillation Training
- Principle:Promptfoo Promptfoo Dynamic Module Loading
- Principle:Speechbrain Speechbrain Beam Search Decoding
- Principle:Datahub project Datahub Protobuf Compilation
- Principle:OpenHands OpenHands Session Closure
Implementations
- Implementation:Triton inference server Server Perf Analyzer Verification
- Implementation:BerriAI Litellm Secret Manager Main
- Implementation:Microsoft Playwright ElementHandleDispatcher
- Implementation:Tensorflow Tfjs Backend Operations
- Implementation:Open compass VLMEvalKit GLMVisionWrapper
- Implementation:Puppeteer Puppeteer Website Package Lock
- Implementation:ArroyoSystems Arroyo Api Server
- Implementation:DevExpress Testcafe ReExecutablePromise
- Implementation:Apache Paimon DLFAuthProvider
- Implementation:FMInference FlexLLMGen DeepSpeed Compression Layers
Heuristics
- Heuristic:Helicone Helicone Tiered Pricing Threshold Matching
- Heuristic:Interpretml Interpret EBM Hyperparameter Tuning Guide
- Heuristic:Bentoml BentoML Platform Serving Caveats
- Heuristic:Datahub project Datahub Gradle Task Only
- Heuristic:Danijar Dreamerv3 Symlog TwoHot Prediction
- Heuristic:Iterative Dvc Shell Execution Pitfalls
- Heuristic:Cohere ai Cohere python ToolCallV2 Auto UUID Override
- Heuristic:Apache Druid Capability Detection Strategy
- Heuristic:Arize ai Phoenix Queue Clear Race Condition
- Heuristic:Kubeflow Kubeflow Issue Routing To Sub Repos
Environments
- Environment:Shiyu coder Kronos Comet ML Logging
- Environment:Microsoft Semantic kernel OpenAI API Environment
- Environment:Eric mitchell Direct preference optimization PyTorch CUDA
- Environment:Ucbepic Docetl LLM API Keys
- Environment:Tensorflow Tfjs Node Native Runtime
- Environment:PeterL1n BackgroundMattingV2 PyTorch CUDA
- Environment:Sktime Pytorch forecasting Optuna Tuning Dependencies
- Environment:Romsto Speculative Decoding CUDA PyTorch
- Environment:Open compass VLMEvalKit GPU CUDA Environment
- Environment:Sgl project Sglang Web