{"id":37066960,"url":"https://github.com/airmcp-com/mcp-standards","last_synced_at":"2026-01-14T07:51:36.558Z","repository":{"id":318749173,"uuid":"1075861180","full_name":"airmcp-com/mcp-standards","owner":"airmcp-com","description":"Self-learning AI standards system - learns from corrections and auto-updates CLAUDE.md","archived":true,"fork":false,"pushed_at":"2025-11-30T18:16:42.000Z","size":6842,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-12-03T01:26:48.781Z","etag":null,"topics":["ai-assistant","ai-coding-assistant","anthropic","automation","claude","code-quality","coding-standards","configuration-management","cursor-ai","developer-productivity","developer-tools","knowledge-base","local-first","machine-learning","mcp","mcp-server","pattern-learning","python","self-learning","sqlite"],"latest_commit_sha":null,"homepage":"","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/airmcp-com.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/CONTRIBUTING.md","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}},"created_at":"2025-10-14T05:01:56.000Z","updated_at":"2025-11-30T18:21:32.000Z","dependencies_parsed_at":"2025-10-15T01:35:55.785Z","dependency_job_id":"d25c7e35-ca38-4f84-9307-6a36c563b22f","html_url":"https://github.com/airmcp-com/mcp-standards","commit_stats":null,"previous_names":["airmcp-com/mcp-standards"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/airmcp-com/mcp-standards","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airmcp-com%2Fmcp-standards","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airmcp-com%2Fmcp-standards/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airmcp-com%2Fmcp-standards/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airmcp-com%2Fmcp-standards/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/airmcp-com","download_url":"https://codeload.github.com/airmcp-com/mcp-standards/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/airmcp-com%2Fmcp-standards/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28413512,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T05:26:33.345Z","status":"ssl_error","status_checked_at":"2026-01-14T05:21:57.251Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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-assistant","ai-coding-assistant","anthropic","automation","claude","code-quality","coding-standards","configuration-management","cursor-ai","developer-productivity","developer-tools","knowledge-base","local-first","machine-learning","mcp","mcp-server","pattern-learning","python","self-learning","sqlite"],"created_at":"2026-01-14T07:51:36.053Z","updated_at":"2026-01-14T07:51:36.542Z","avatar_url":"https://github.com/airmcp-com.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MCP Standards - Personal Memory for Claude\n\n\u003e **⚠️ ARCHIVED PROJECT**: This repository is archived and provided for reference only. The project was experimental and served as a proof-of-concept for automatic preference learning with AgentDB vector memory. See [ARCHIVE.md](ARCHIVE.md) for complete details.\n\n**Make Claude remember YOUR preferences automatically. Zero config, zero manual steps.**\n\n[![MIT License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![Archived](https://img.shields.io/badge/status-archived-inactive.svg)](ARCHIVE.md)\n\n---\n\n## 🎯 What This Does\n\nStop repeating yourself to Claude. This MCP server learns your preferences automatically:\n\n```\nYou: \"Install pytest\"\nClaude: pip install pytest\n\nYou: \"Actually, use uv not pip\"\nClaude: ✓ Remembered\n\nNext session:\nYou: \"Install requests\"\nClaude: uv pip install requests  [automatic]\n```\n\n**One correction. Forever remembered.**\n\n---\n\n## ⚡ Quick Start (5 Minutes)\n\n### 1. Install\n\n```bash\ngit clone https://github.com/airmcp-com/mcp-standards.git\ncd mcp-standards\n\n# Install dependencies\nnpm install\n\n# Setup AgentDB\nnpm run setup\n```\n\n### 2. Configure Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-standards\": {\n      \"command\": \"uv\",\n      \"args\": [\n        \"run\",\n        \"--directory\",\n        \"/ABSOLUTE/PATH/TO/mcp-standards\",\n        \"python\",\n        \"-m\",\n        \"mcp_standards.server_simple\"\n      ]\n    }\n  }\n}\n```\n\n**⚠️ Replace `/ABSOLUTE/PATH/TO/` with your actual path!**\n\n### 3. Restart Claude Desktop\n\nQuit and relaunch Claude Desktop.\n\n### 4. Test It!\n\n```\nYou: \"Remember: use uv not pip\"\nClaude: ✓ Remembered: 'use uv not pip' (python)\n\nYou: \"What do you remember?\"\nClaude: I remember you prefer:\n- Use uv not pip for Python projects\n```\n\n**That's it! You're done.** 🎉\n\n---\n\n## 🧠 How It Works\n\n### Automatic Learning\n\nJust correct Claude naturally - it learns automatically:\n\n```\nSession 1:\nYou: \"Use uv not pip\"\n→ Auto-detected and stored in AgentDB\n\nSession 2+:\nYou: \"Install anything\"\n→ Claude uses uv automatically\n```\n\n### What Gets Remembered\n\n✅ **Tool preferences**: \"use uv not pip\", \"prefer yarn over npm\"\n✅ **Workflow patterns**: \"run tests before commit\"\n✅ **Code style**: \"use TypeScript for new files\"\n✅ **Project conventions**: \"follow PEP 8\"\n\n### Categories (Auto-Detected)\n\n- `python` - Python/pip/uv preferences\n- `javascript` - npm/yarn/pnpm preferences\n- `git` - Git workflow preferences\n- `docker` - Docker/container preferences\n- `testing` - Test framework preferences\n- `general` - Everything else\n\n---\n\n## 📊 Features\n\n| Feature | Status |\n|---------|--------|\n| **Auto-detection** | ✅ Detects \"use X not Y\" automatically |\n| **Semantic search** | ✅ \u003c1ms with AgentDB (150x faster than SQLite) |\n| **Cross-session** | ✅ Preferences persist forever |\n| **Zero config** | ✅ Works out of the box |\n| **100% local** | ✅ No cloud, all private |\n| **Simple** | ✅ 5-minute setup |\n\n---\n\n## 📖 Documentation\n\n- **[Quick Start Guide](docs/QUICKSTART_SIMPLE.md)** - Detailed setup instructions\n- **[Validation Checklist](docs/VALIDATION_CHECKLIST.md)** - Testing \u0026 troubleshooting\n- **[Implementation Plan](docs/SIMPLE_V2_PLAN.md)** - Technical details\n- **[Skills Guide](.claude/skills/remember-preferences.md)** - How to use in Claude\n\n---\n\n## 🛠️ MCP Tools Available\n\n### Personal Memory (Simple Version)\n\n```javascript\n// Store preference\nremember({\n    content: \"use uv not pip\",\n    category: \"python\"\n})\n\n// Search preferences\nrecall({\n    query: \"package manager\",\n    top_k: 5\n})\n\n// List all categories\nlist_categories()\n\n// Get statistics\nmemory_stats()\n```\n\n### Config Standards (Bonus)\n\n```javascript\n// Generate minimal CLAUDE.md from project config files\ngenerate_ai_standards({\n    project_path: \".\",\n    formats: [\"claude\"]\n})\n```\n\n---\n\n## 🚀 Architecture\n\n### Simple \u0026 Fast\n\n```\nUser corrects Claude\n   ↓\nAuto-detection hook triggers\n   ↓\nStores in AgentDB (semantic vector memory)\n   ↓\nNext session: Claude queries AgentDB automatically\n   ↓\nUses remembered preference\n```\n\n### Technologies\n\n- **AgentDB** - Ultra-fast vector memory (\u003c1ms search)\n- **Python** - MCP server (async)\n- **SQLite** - Fallback storage\n- **MCP Protocol** - Claude Desktop integration\n- **100% Local** - No cloud dependencies\n\n---\n\n## 📁 Project Structure\n\n```\nmcp-standards/\n├── src/mcp_standards/\n│   ├── agentdb_client.py        # AgentDB wrapper\n│   ├── hooks/auto_memory.py     # Auto-detection\n│   └── server_simple.py         # Simple MCP server\n├── tests/\n│   └── test_simple_setup.py     # Validation tests\n├── docs/\n│   ├── QUICKSTART_SIMPLE.md     # Setup guide\n│   ├── VALIDATION_CHECKLIST.md  # Testing guide\n│   └── SIMPLE_V2_PLAN.md        # Technical details\n├── scripts/\n│   └── setup-agentdb.js         # Setup script\n├── .claude/skills/\n│   └── remember-preferences.md  # Claude skill\n└── README.md                     # This file\n```\n\n**Clean. Simple. Works.**\n\n---\n\n## 🧪 Testing\n\nRun automated validation:\n\n```bash\npython3 tests/test_simple_setup.py\n```\n\n**Expected output**:\n```\n✓ PASS: Directory Structure\n✓ PASS: Required Files\n✓ PASS: Module Imports\n✓ PASS: AgentDB Client Init\n✓ PASS: Auto Memory Patterns\n\nResults: 5/5 tests passed\nStatus: Ready for dev testing 🚀\n```\n\n---\n\n## 🐛 Troubleshooting\n\n### Setup fails\n\n```bash\n# Check Node.js version\nnode --version  # Need v18+\n\n# Install AgentDB manually\nnpm install -g agentdb\nnpx agentdb --version\n```\n\n### Claude Desktop doesn't connect\n\n```bash\n# Check logs\ntail -f ~/Library/Logs/Claude/mcp*.log\n\n# Look for initialization messages\n# Should see: \"MCP Standards (Simple) initialized\"\n```\n\n### Preferences not remembered\n\nCheck that:\n1. Server is running (check Claude Desktop MCP status)\n2. Corrections use clear phrases (\"use X not Y\")\n3. AgentDB path exists: `~/.mcp-standards/agentdb`\n\n**More help**: See [Validation Checklist](docs/VALIDATION_CHECKLIST.md)\n\n---\n\n## 🎯 Performance\n\n| Metric | Value |\n|--------|-------|\n| **Setup time** | \u003c5 minutes |\n| **Server startup** | \u003c2 seconds |\n| **Search speed** | \u003c1ms (AgentDB HNSW) |\n| **Detection** | Real-time (async) |\n| **Storage** | \u003c10ms |\n| **Memory usage** | ~50MB (embedding model) |\n\n**150x faster than SQLite. Zero lag.**\n\n---\n\n## 🔒 Privacy\n\n- ✅ **100% local** - Everything stored in `~/.mcp-standards/`\n- ✅ **No cloud** - No external API calls\n- ✅ **No telemetry** - No data collection\n- ✅ **Your data** - You control everything\n\n---\n\n## 📝 What Changed (v2 Simple)\n\nWe removed all the complexity:\n\n| v1 (Old) | v2 Simple (New) |\n|----------|-----------------|\n| Manual MCP calls (4-5 steps) | ✅ Automatic (zero steps) |\n| SQLite keyword search (50ms+) | ✅ AgentDB vector search (\u003c1ms) |\n| No semantic matching | ✅ Semantic understanding |\n| Complex setup | ✅ 5-minute setup |\n| 6,000+ LOC | ✅ ~950 LOC |\n\n**Result**: 80% less code, 100x better UX\n\n---\n\n## 🤝 Contributing\n\nThis is a personal side project. If you want to contribute:\n\n1. Try it yourself first\n2. Open an issue describing what you want to add\n3. Wait for feedback before writing code\n\n**Please don't**: Submit large PRs without discussion first.\n\n---\n\n## 📜 License\n\nMIT License - See [LICENSE](LICENSE) file\n\n---\n\n## 🙏 Credits\n\nBuilt with inspiration from:\n\n- **[AgentDB](https://agentdb.ruv.io)** - Ultra-fast vector memory\n- **[Context Engineering Guide](https://github.com/coleam00/context-engineering-intro)** - Minimal CLAUDE.md principles\n- **Gunnar's approach** - Simple side projects that solve personal problems\n\n---\n\n## 💬 Questions?\n\n**Q: Why not just use v1?**\nA: v1 requires 4-5 manual MCP calls per correction. v2 is zero-touch.\n\n**Q: Do I need AgentDB?**\nA: Yes, but it's installed automatically via `npm run setup`.\n\n**Q: Is my data private?**\nA: 100% local. Everything stored in `~/.mcp-standards/`. No cloud.\n\n**Q: What if I want the old version?**\nA: Use `src/mcp_standards/server.py` instead of `server_simple.py`.\n\n---\n\n## 🚀 Next Steps\n\n```bash\n# Try it now\ngit clone https://github.com/airmcp-com/mcp-standards.git\ncd mcp-standards\nnpm run setup\n\n# See: docs/QUICKSTART_SIMPLE.md\n```\n\n**Stop repeating yourself. Start remembering automatically.** 🎯\n\n---\n\n## 📦 Archive Status\n\n**This project is archived.** See [ARCHIVE.md](docs/ARCHIVE.md) for:\n- Complete project status and achievements\n- Security audit results\n- Full documentation index\n- Lessons learned and technical insights\n- How to use this repository as reference\n\n---\n\n**Made with ❤️ by keeping it simple**\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fairmcp-com%2Fmcp-standards","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fairmcp-com%2Fmcp-standards","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fairmcp-com%2Fmcp-standards/lists"}