
Security News
The Hidden Blast Radius of the Axios Compromise
The Axios compromise shows how time-dependent dependency resolution makes exposure harder to detect and contain.
@probelabs/memaris
Advanced tools
Stop re-teaching your AI. Turn past Claude Code sessions into persistent memory that follows you across projects.

Stop re-teaching your AI. Turn past sessions into persistent memory.
Memaris analyzes your Claude Code conversation history to extract patterns, preferences, and lessons learned. It turns every correction, rejected approach, and successful pattern into permanent memory that follows you across sessions.
The Problem: Every time you start a new Claude Code session, you're teaching the same preferences again. "Don't use sudo with npm." "Prefer async/await." "Always add error boundaries."
The Solution: Memaris reads your past sessions, identifies what worked and what didn't, then creates a personalized CLAUDE.md file with instructions tailored to your coding style.
# Navigate to your project
cd your-project
# Preview insights (no file changes)
npx -y @probelabs/memaris
# Apply insights to CLAUDE.md
npx -y @probelabs/memaris --update
That's it! No installation needed - just run and go. Memaris will analyze your Claude Code history and generate personalized instructions.
💡 Pro tip: The first command previews what insights will be added. Use
--updateto actually modify your CLAUDE.md file.
|
📝 Your Conversations Every correction, preference, and rejected approach in your Claude Code sessions |
🤖 AI Analysis Extracts patterns, identifies mistakes to avoid, and learns your coding style |
✨ Optimized CLAUDE.md Personalized instructions that make every future session start smarter |
npx -y @probelabs/memaris # Preview insights (default)
npx -y @probelabs/memaris --update # Apply insights to CLAUDE.md
npx -y @probelabs/memaris /path/to/project # Analyze specific project
| Option | Description | Example |
|---|---|---|
--update | Write changes to CLAUDE.md (default: preview only) | npx -y @probelabs/memaris --update |
--all | Analyze all conversation history in batches | npx -y @probelabs/memaris --all --update |
--batch-size <n> | Token batch size when using --all (default: 50000) | npx -y @probelabs/memaris --all --batch-size 25000 |
--depth <n> | Maximum messages to analyze (deprecated, use --tokens) | npx -y @probelabs/memaris --depth 100 |
--tokens <n> | Maximum tokens to analyze (default: 50000) | npx -y @probelabs/memaris --tokens 25000 |
--pattern-only | Use pattern-matching instead of AI analysis | npx -y @probelabs/memaris --pattern-only |
--exclude-patterns | Exclude sessions matching patterns | npx -y @probelabs/memaris --exclude-patterns "debug,test" |
--debug | Show debug information | npx -y @probelabs/memaris --debug |
# For large projects with lots of history
npx -y @probelabs/memaris --all --batch-size 30000 --update
# Quick analysis for recent work only
npx -y @probelabs/memaris --tokens 10000 --update
# Pattern-only analysis (faster, no API key needed)
npx -y @probelabs/memaris --pattern-only --update
# Discover all Claude Code projects
npx -y @probelabs/memaris scan
# Export analysis results
npx -y @probelabs/memaris export my-project json
npx -y @probelabs/memaris export my-project markdown
# Focus on specific insights
npx -y @probelabs/memaris insights --type preferences
~/.claude/projects/ANTHROPIC_API_KEY for AI-powered analysis
# Optional: Enable AI-powered analysis
export ANTHROPIC_API_KEY="your-api-key-here"
# Verify Claude Code history exists
ls ~/.claude/projects/
Note: Memaris works great with pattern-matching analysis (no API key required), but AI-powered analysis provides much richer insights.
# Clone the repository
git clone https://github.com/probelabs/memaris.git
cd memaris
# Install dependencies
bun install
# Run in development mode
bun run dev
# Build for production
bun run build
# Check if Claude Code history exists
ls ~/.claude/projects/
# If empty, use Claude Code first to create conversation history
# Use absolute path
npx -y @probelabs/memaris /full/path/to/your/project --debug
# Or use the scan command to see all detected projects
npx -y @probelabs/memaris scan
# Verify API key is set
echo $ANTHROPIC_API_KEY
# Use pattern-only analysis as fallback
npx -y @probelabs/memaris --pattern-only --update
# Reduce analysis scope
npx -y @probelabs/memaris --tokens 10000 --update
# Use smaller batch sizes
npx -y @probelabs/memaris --all --batch-size 25000 --update
Memaris is part of the Probe ecosystem—tools dedicated to improving human and AI collaboration in development.
MIT © Probe Labs
Contributions are welcome! Please feel free to submit a Pull Request.
Questions or feedback? Reach out at hello@probelabs.com
Memaris: From the ancient Greek μνήμη (mneme) meaning memory - helping AI remember and learn from every conversation.
FAQs
Stop re-teaching your AI. Turn past Claude Code sessions into persistent memory that follows you across projects.
We found that @probelabs/memaris 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.

Security News
The Axios compromise shows how time-dependent dependency resolution makes exposure harder to detect and contain.

Research
A supply chain attack on Axios introduced a malicious dependency, plain-crypto-js@4.2.1, published minutes earlier and absent from the project’s GitHub releases.

Research
Malicious versions of the Telnyx Python SDK on PyPI delivered credential-stealing malware via a multi-stage supply chain attack.