{"id":44349947,"url":"https://github.com/timothywarner-org/context-engineering","last_synced_at":"2026-02-11T14:36:42.344Z","repository":{"id":303662012,"uuid":"1016228519","full_name":"timothywarner-org/context-engineering","owner":"timothywarner-org","description":"🧠 Stop building AI that forgets. Master MCP (Model Context Protocol) with production-ready semantic memory, hybrid RAG, and the WARNERCO Schematica teaching app. FastMCP + LangGraph + Vector/Graph stores. Your AI assistant's long-term memory starts here.","archived":false,"fork":false,"pushed_at":"2026-01-27T22:31:13.000Z","size":74631,"stargazers_count":12,"open_issues_count":1,"forks_count":8,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-28T10:59:48.584Z","etag":null,"topics":["ai-agents","ai-memory","anthropic","azure-ai-search","chromadb","claude","context-engineering","fastapi","fastmcp","hybrid-rag","knowledge-graph","langgraph","llm","mcp","mcp-tools","model-context-protocol","python","rag","semantic-memory","vector-database"],"latest_commit_sha":null,"homepage":"https://techtrainertim.com","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/timothywarner-org.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":["your_github_username"],"patreon":["your_patreon_username"],"open_collective":["your_open_collective_username"],"ko_fi":["your_ko_fi_username"],"tidelift":["package_name"],"community_bridge":["your_community_bridge_project_name"],"liberapay":["your_liberapay_username"],"issuehunt":["your_issuehunt_username"],"otechie":["your_otechie_username"],"custom":["https://www.example.com/donate"]}},"created_at":"2025-07-08T17:23:01.000Z","updated_at":"2026-01-28T02:05:50.000Z","dependencies_parsed_at":"2025-07-08T19:49:02.876Z","dependency_job_id":"9fe34aa0-cba0-45ea-9fc2-74cb00585d10","html_url":"https://github.com/timothywarner-org/context-engineering","commit_stats":null,"previous_names":["timothywarner-org/context-engineering"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/timothywarner-org/context-engineering","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timothywarner-org%2Fcontext-engineering","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timothywarner-org%2Fcontext-engineering/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timothywarner-org%2Fcontext-engineering/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timothywarner-org%2Fcontext-engineering/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/timothywarner-org","download_url":"https://codeload.github.com/timothywarner-org/context-engineering/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timothywarner-org%2Fcontext-engineering/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29335276,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-11T14:34:07.188Z","status":"ssl_error","status_checked_at":"2026-02-11T14:34:06.809Z","response_time":97,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","ai-memory","anthropic","azure-ai-search","chromadb","claude","context-engineering","fastapi","fastmcp","hybrid-rag","knowledge-graph","langgraph","llm","mcp","mcp-tools","model-context-protocol","python","rag","semantic-memory","vector-database"],"created_at":"2026-02-11T14:36:41.476Z","updated_at":"2026-02-11T14:36:42.325Z","avatar_url":"https://github.com/timothywarner-org.png","language":"Python","readme":"# Context Engineering with MCP: Build AI Systems That Actually Remember\n\n\u003cimg src=\"images/cover.png\" alt=\"Context Engineering with MCP Course Cover\" width=\"700\"/\u003e\n\nWelcome to the training hub for mastering **Context Engineering with Model Context Protocol (MCP)**. This course teaches you to implement production-ready semantic memory systems for AI assistants using Python, FastAPI, FastMCP, and LangGraph.\n\n---\n\n## Quick Start\n\n### Prerequisites\n\n- Python 3.11+ (3.12+ recommended for WARNERCO Schematica)\n- Node.js 20+ (for Lab 01 and MCP Inspector)\n- [uv](https://docs.astral.sh/uv/) package manager (recommended for Python)\n- Claude Desktop or Claude Code\n\n### Option 1: Hello MCP Lab (Beginner Entry Point)\n\n```bash\ngit clone https://github.com/timothywarner-org/context-engineering.git\ncd context-engineering/labs/lab-01-hello-mcp/starter\nnpm install \u0026\u0026 npm start\n\n# Test with MCP Inspector (in another terminal)\nnpx @modelcontextprotocol/inspector node src/index.js\n```\n\n### Option 2: WARNERCO Schematica (Flagship Teaching App)\n\n```bash\ncd src/warnerco/backend\nuv sync\nuv run uvicorn app.main:app --reload    # HTTP server at http://localhost:8000\nuv run warnerco-mcp                      # MCP stdio server for Claude Desktop\n```\n\n---\n\n## Course Structure (4 x 50 Minutes)\n\n| Segment | Topic                  | Focus                                                           |\n| ------- | ---------------------- | --------------------------------------------------------------- |\n| **1**   | All About Context      | Token economics, context loss types, why RAG isn't enough       |\n| **2**   | All About MCP          | FastMCP, FastAPI, tools, resources, prompts, elicitations       |\n| **3**   | Semantic Memory Stores | JSON, ChromaDB, Azure AI Search, Graph Memory, Scratchpad       |\n| **4**   | MCP in Production      | Claude Desktop, Claude Code, VS Code, GitHub Copilot, LangGraph |\n\n---\n\n## WARNERCO Schematica Architecture\n\nThe flagship teaching application demonstrates production MCP patterns with a 7-node hybrid RAG pipeline:\n\n```\n+---------------------------------------------------------------+\n|                     FastAPI + FastMCP                         |\n+---------------------------------------------------------------+\n|  LangGraph Flow (7-node Hybrid RAG)                           |\n|  parse_intent -\u003e query_graph -\u003e inject_scratchpad -\u003e retrieve |\n|  -\u003e compress -\u003e reason -\u003e respond                             |\n+---------------------------------------------------------------+\n|  Hybrid Memory Layer                                          |\n|  +-------------------+  +-------------------+  +-------------+ |\n|  | Vector Store      |  | Graph Store       |  | Scratchpad  | |\n|  | JSON -\u003e Chroma -\u003e |  | SQLite + NetworkX |  | In-memory   | |\n|  | Azure AI Search   |  | (Knowledge Graph) |  | (Session)   | |\n|  +-------------------+  +-------------------+  +-------------+ |\n+---------------------------------------------------------------+\n```\n\n### Memory Store Comparison\n\n| Feature              | JSON         | ChromaDB      | Azure AI Search    | Graph       | Scratchpad     |\n| -------------------- | ------------ | ------------- | ------------------ | ----------- | -------------- |\n| Semantic Search      | No           | Yes           | Yes                | No          | No             |\n| Relationship Queries | No           | No            | No                 | Yes         | No             |\n| Session Memory       | No           | No            | No                 | No          | Yes            |\n| Best For             | Prototyping  | Local dev     | Production         | Connections | Working memory |\n\n---\n\n## Repository Structure\n\n```\ncontext-engineering/\n├── src/warnerco/backend/      # WARNERCO Schematica (FastAPI + FastMCP + LangGraph)\n├── labs/lab-01-hello-mcp/     # Hands-on beginner lab\n├── docs/                      # Student materials, tutorials, diagrams\n├── instructor/                # Instructor-only materials\n├── config/                    # Sample MCP client configurations\n├── .vscode/                   # VS Code workspace configuration\n├── .claude/                   # Claude Code agents and skills\n└── CLAUDE.md                  # Development instructions (SOURCE OF TRUTH)\n```\n\n**For development details, see [CLAUDE.md](CLAUDE.md)** - the source of truth for:\n- Complete MCP tool reference\n- API endpoint documentation\n- Environment variable configuration\n- LangGraph pipeline details\n- Graph and Scratchpad Memory features\n\n---\n\n## MCP Client Configuration\n\n### Claude Desktop\n\n**Windows**: `%APPDATA%\\Claude\\claude_desktop_config.json`\n**Mac**: `~/Library/Application Support/Claude/claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"warnerco\": {\n      \"command\": \"uv\",\n      \"args\": [\"run\", \"warnerco-mcp\"],\n      \"cwd\": \"C:/github/context-engineering/src/warnerco/backend\"\n    }\n  }\n}\n```\n\n### VS Code\n\nSee `.vscode/mcp.json` in the repository for local and Azure APIM configurations.\n\n---\n\n## Testing with MCP Inspector\n\n```bash\nnpx @modelcontextprotocol/inspector uv run warnerco-mcp\n# Opens http://localhost:5173\n```\n\n---\n\n## Resources\n\n- **[MCP Specification](https://spec.modelcontextprotocol.io/)** - Official protocol documentation\n- **[FastMCP Documentation](https://github.com/jlowin/fastmcp)** - Python MCP framework\n- **[CLAUDE.md](CLAUDE.md)** - Development instructions for this repository\n\n---\n\n## Your Instructor\n\n### Tim Warner\n\n**Microsoft MVP** - Azure AI and Cloud/Datacenter Management\n**Microsoft Certified Trainer** (25+ years)\n\n- Website: [techtrainertim.com](https://techtrainertim.com)\n- GitHub: [@timothywarner](https://github.com/timothywarner)\n- LinkedIn: [linkedin.com/in/timothywarner](https://www.linkedin.com/in/timothywarner/)\n\n---\n\n## License\n\nMIT License - 2026 Timothy Warner\n\n---\n\n**Now go build AI systems that actually remember!**\n","funding_links":["https://github.com/sponsors/your_github_username","https://patreon.com/[\"your_patreon_username\"]","https://opencollective.com/[\"your_open_collective_username\"]","https://ko-fi.com/[\"your_ko_fi_username\"]","https://tidelift.com/funding/github/[\"package_name\"]","https://funding.communitybridge.org/projects/[\"your_community_bridge_project_name\"]","https://liberapay.com/[\"your_liberapay_username\"]","https://issuehunt.io/r/[\"your_issuehunt_username\"]","https://otechie.com/[\"your_otechie_username\"]","https://www.example.com/donate"],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimothywarner-org%2Fcontext-engineering","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftimothywarner-org%2Fcontext-engineering","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimothywarner-org%2Fcontext-engineering/lists"}