claude-knowledge-catalyst
Advanced tools
AI-powered knowledge management with YAKE keyword extraction for Claude Code development
Claude Code ⇄ Obsidian Seamless Integration System
Automatically synchronize insights from Claude Code development processes with Obsidian vaults for structured knowledge management. Automated analysis reduces manual classification overhead.
.claude/ directory to Obsidian vault# Enhanced Metadata Example (Secondary Effect)
type: [prompt, code, concept, resource] # Content nature
tech: [python, react, fastapi, kubernetes, ...] # Technology stack
domain: [web-dev, ml, devops, mobile, ...] # Application domain
team: [backend, frontend, ml-research, devops] # Team ownership
status: [draft, tested, production, deprecated] # Lifecycle state
complexity: [beginner, intermediate, advanced] # Skill level
confidence: [low, medium, high] # Content reliability
obsidian-vault/
├── _system/ # Templates and configuration
├── _attachments/ # Media files
├── inbox/ # Unprocessed content
├── active/ # Work-in-progress content
├── archive/ # Completed/deprecated content
└── knowledge/ # Mature knowledge (main area)
curl -LsSf https://astral.sh/uv/install.sh | sh (Unix/macOS) or powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" (Windows)🚀 v0.10.1 Test Stabilization: Complete test-until-pass implementation with 396/396 passing tests and 48.09% test coverage ensures production stability.
Experience seamless integration:
# Install CKC
uv pip install claude-knowledge-catalyst
# Initialize in Claude Code project
cd your-claude-project
uv run ckc init
# Connect to Obsidian vault
uv run ckc add my-vault /path/to/obsidian/vault
# Sync .claude/ files with Obsidian
uv run ckc sync
What happens:
.claude/ content with Obsidian-optimized structure.claude/ directory and Obsidian vault# Install from PyPI using uv (recommended)
uv pip install claude-knowledge-catalyst
# Or using pip
pip install claude-knowledge-catalyst
# Or install from source for development
git clone https://github.com/drillan/claude-knowledge-catalyst.git
cd claude-knowledge-catalyst
uv sync --dev
# Navigate to Claude Code project
cd your-claude-project
# Initialize CKC (detects .claude/ directory)
uv run ckc init
# Connect to Obsidian vault
uv run ckc add main-vault /path/to/your/obsidian/vault
# Experience automatic analysis of .claude/ content
echo "# Git Useful Commands
## Branch Status Check
\`\`\`bash
git branch -vv
git status --porcelain
\`\`\`" > .claude/git_tips.md
# Verify automated analysis and Obsidian metadata generation
uv run ckc classify .claude/git_tips.md --show-evidence
# Enhance existing Obsidian vault for Claude Code integration
uv run ckc migrate --source /existing/obsidian --target /enhanced/vault
# Preview changes
uv run ckc migrate --source /existing/obsidian --target /enhanced/vault --dry-run
# Automatic content analysis
uv run ckc classify file.md --show-evidence
# Batch classification
uv run ckc batch-classify .claude/
# Missing metadata detection
uv run ckc scan-missing-metadata
# Zero-config initialization
uv run ckc init
# Vault connection
uv run ckc add vault-name /path/to/obsidian
# State-based synchronization
uv run ckc sync
uv run ckc sync --project "My Project"
# Real-time monitoring
uv run ckc watch
# System status
uv run ckc status
# File analysis with evidence
uv run ckc analyze .claude/my-prompt.md
# Cross-dimensional search
uv run ckc search --tech python --status production
uv run ckc search --team frontend --complexity advanced
# Project insights
uv run ckc project stats my-project
CKC uses a YAML configuration file with pure tag-centered settings:
version: "1.0"
project_name: "My AI Project"
auto_sync: true
# Tag-centered architecture
tag_system:
enabled: true
multi_dimensional: true
auto_classification: true
confidence_threshold: 0.75
# 7-dimensional tag schema
tags:
type_tags: ["prompt", "code", "concept", "resource"]
tech_tags: ["python", "javascript", "react", "fastapi"]
domain_tags: ["web-dev", "machine-learning", "devops"]
team_tags: ["backend", "frontend", "ml-research"]
status_tags: ["draft", "tested", "production", "deprecated"]
complexity_tags: ["beginner", "intermediate", "advanced"]
confidence_tags: ["low", "medium", "high"]
# Obsidian integration
sync_targets:
- name: "main-vault"
type: "obsidian"
path: "/Users/me/Documents/ObsidianVault"
enabled: true
enhance_metadata: true
# Automated features
automation:
auto_classification: true
evidence_tracking: true
natural_language_search: true
# State-based workflow
workflow:
inbox_pattern: "status:draft"
active_pattern: "status:tested"
knowledge_pattern: "status:production"
archive_pattern: "status:deprecated"
# Security settings
watch:
include_claude_md: false # Enable with caution
claude_md_sections_exclude:
- "# secrets"
- "# private"
- "# api-keys"
CKC implements a revolutionary pure tag-centered architecture:
├── prompts/ # "Is this a prompt or template?"
├── code/ # "Code snippet or tool?"
├── concepts/ # "Concept or best practice?"
└── misc/ # Catch-all confusion
Issues:
├── _system/ # System files and templates
├── inbox/ # Unprocessed items (workflow state)
├── active/ # Currently working (activity state)
├── archive/ # Deprecated/old (lifecycle state)
└── knowledge/ # Mature content (90% of files)
└── Dynamic discovery through enhanced multi-layer tags
Benefits:
Demo the cognitive transformation:
# Experience tag-centered migration
./demo/tag_centered_demo.sh
# Try automated classification
./demo/demo.sh
# Multi-team collaboration
./demo/multi_project_demo.sh
This project is licensed under the MIT License - see the LICENSE file for details.
We welcome contributions! Please see our Contributing Guide for details.
Welcome to the cognitive revolution! No more "which category?" decisions - experience pure, discoverable knowledge management.
Built with ❤️ by the Claude community
FAQs
AI-powered knowledge management with YAKE keyword extraction for Claude Code development
We found that claude-knowledge-catalyst demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Product
Socket now supports Scala and Kotlin, bringing AI-powered threat detection to JVM projects with easy manifest generation and fast, accurate scans.
Application Security
/Security News
Socket CEO Feross Aboukhadijeh and a16z partner Joel de la Garza discuss vibe coding, AI-driven software development, and how the rise of LLMs, despite their risks, still points toward a more secure and innovative future.
Research
/Security News
Threat actors hijacked Toptal’s GitHub org, publishing npm packages with malicious payloads that steal tokens and attempt to wipe victim systems.