Vibe Coding Discovercontext-engineering
View on GitHubContext Engineering: Build Consistent, Accurate, Predictable AI Systems
Companion repo for a book on context engineering: runnable Python/JS/Java/Jupyter examples covering RAG, agent memory, tools and MCP servers, multi-agent orchestration, prompting patterns, evals, and governance. A hands-on reference for building reliable LLM systems.
Use Cases
Build RAG pipelines (basic, agentic, vectorless)Add long-term and session memory to agentsImplement function calling and tool useCreate MCP serversOrchestrate multi-agent workflowsApply prompt patterns (few-shot, CoT, ReAct, chaining)Evaluate and observe LLM appsRedact PII and validate outputsDetect bias and add human-in-the-loop reviewRoute models via an AI gatewayCompress and manage contextFine-tune models
Built With
- Language
- Python
- Frameworks
- LangChain · LangGraph · LlamaIndex · Haystack · CrewAI · DeepAgents · DSPy · Qdrant · Ragas · DeepEval · Promptfoo · Langfuse · LangSmith · LiteLLM · Mem0 · Cognee
Tags
context-engineering · llm · ai-agents · mcp · rag · memory-management · multi-agent · prompting · agent-skills · evals · observability · orchestration · book-companion · examples · generative-ai · tutorial