Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/vibe-log/vibe-log-cli

A CLI tool for logging and analyzing Claude Code and Cursor ai-driven coding session.
https://github.com/vibe-log/vibe-log-cli

ai-assisted-development ai-coding ai-coding-assistant analysis claude claude-code cursor dev-analytics developer-analytics developer-productivity logging productivity project-management prompt-engineering prompt-optimization session-analytics tui vibe-coding workflow-optimization

Last synced: 7 days ago
JSON representation

A CLI tool for logging and analyzing Claude Code and Cursor ai-driven coding session.

Awesome Lists containing this project

README 

          





 og-image





Open-source CLI for analyzing Claude Code and Codex sessions locally and generating productivity reports





by vibe-log.dev

npm version

License: MIT

Node.js Version



Tests

NPM Publish

Build Verification

Coverage



Security Policy

Transparent Build



PRs Welcome

X  Follow

Star this repo  

 



[Website](https://vibe-log.dev) â€ĸ [Report Bug](https://github.com/vibe-log/vibe-log-cli/issues) â€ĸ [Request Feature](https://github.com/vibe-log/vibe-log-cli/issues)




## What is Vibe-Log?



Vibe-log-cli is an open-source command-line tool that analyzes your Claude Code and Codex sessions to extract productivity insights and generate reports. All analyses can run completely locally on your machine using your local AI coding tool through ACP. It also includes a Claude Code statusline that helps you get more from your sessions.  



## Getting Started fast

Just run: 

```bash

npx vibe-log-cli@latest

```

 



## Main features 

### 1. 📋 Today's standup 

New: Be prepared in 2-3 minutes for your daily standup meeting! 

Screenshot 2025-10-02 163102



### 2. 📊 Claude Code and Codex Productivity Report Generation (Local) 

Generate comprehensive productivity reports from Claude Code and Codex sessions using your local AI coding setup. No data leaves your machine.

See example of locally generated report here: https://vibe-log.dev/example-daily-report

image



 



### 3. 🧠 Claude Code Co-pilot Statusline 

Strategic product advisor in Claude Code. Your prompts are analyzed locally (via CC) to provide actionable guidance that pushes you to ship faster. Feedback appears in your Claude Code status line with concrete next steps.

image



## Updates 



### What's New in v0.7.x

#### Today's Standup ✨

Get a personalized standup summary of your recent Claude Code and Codex activity right from your terminal. Runs 100% locally using your own AI coding setup.

The standup feature analyzes your recent sessions and generates a concise summary of:

* What you worked on

* Key accomplishments

* Next steps



#### Improved Onboarding Experience 🚀

Getting started with vibe-log is now smoother than ever:

Better first-run setup flow

Helpful prompts to guide you through configuration

Improved error messages when things go wrong



#### Improved Time Calculation ⏱ī¸

More accurate session duration tracking with better handling of:

Massive sessions: Sessions with 10,000+ messages no longer cause performance issues

Smart truncation: Large sessions are intelligently truncated while preserving time data

Consistent timestamps: Better parsing and validation of session timing information

Edge case handling: Fixed issues with sessions that had missing or invalid timestamps



## đŸ’Ŧ More about Claude Status Line - Strategic Co-pilot / Advisor (Local)



**🔒 Installation Safety**: Automatically backs up your existing status line configuration. Uninstalling instantly restores your original setup - zero risk to your Claude Code configuration.



### Why Use Status Line?



- **🚀 Ship Faster**: Get pushed to deliver

- **đŸŽ¯ Stay Focused**: Remembers your original mission and keeps you on track and forward ⏊ī¸Ž

- **⚡ Concrete Actions**: Specific next steps like:

- **📈 Strategic Thinking**: Considers edge cases, user experience, and scaling at the right time

- **📊 Token Usage Display**: Integrates with ccusage to show real-time token metrics

- **↩ī¸ Easy Restore**: Your original status line is backed up and can be restored anytime

## Architecture

### How Status Line Works

1. Intercepts prompts submitted in Claude Code

1. Analyzes via the local Claude Code latest prompt with relevant session context.

4. Provides strategic guidance and pushes you to ship

5. Displays actionable feedback in the Claude Code status line



In more details:

```mermaid

flowchart LR

    subgraph Input ["âœŗī¸ In Claude Code"]

        User([👤 You type a
prompt]) --> Submit[Press Enter to
submit prompt]

        Submit --> Hook[đŸĒ UserPromptSubmit
hook triggers]

    end



    subgraph Analysis ["🧠 Local Prompt Analysis via Claude Code SDK"]

        Hook --> CLI[Vibe-log CLI
receives prompt]

        CLI --> Check{Is new chat?}

        Check -->|No| Context[📝 Include previous
conversation]

        Check -->|Yes| Direct[💭 Analyze prompt
standalone]

        

        subgraph Personality ["🎭 Infuse Coach Personality"]

            Gordon[🧑‍đŸŗ Gordon
Tough love]

            Vibe[💜 Vibe-log
Encouraging]

            Custom[✨ Custom
Your style]

        end

        

        Context --> SDK[Claude SDK
analyzes prompt quality]

        Direct --> SDK

        Personality -.-> SDK

        SDK --> Score[📊 Generate score
& suggestion]

    end



    subgraph Display ["đŸ’Ŧ Status Line Feedback"]

        Score --> Save[💾 Save to
~/.vibe-log/analysis]

        Save --> Status[Status bar
reads result]

        Status --> Show[đŸŸĸ 85/100
✨ Gordon says:
Add more context chef!]

    end



    Show --> Improve([📈 Better prompts
Better results])

  ```



### Coach Personalities

- **Gordon** - Sharp, pushy, business-focused. Creates urgency: "Ship by FRIDAY or you're fired!"

- **Vibe-Log** - Supportive but pushy senior dev. Helps you ship: "MVP checklist: Auth works ✓ | Ship it!"

- **Custom** - User-defined personality with strategic focus



### Example Output

 



### Setup

1. Run `npx vibe-log-cli`

2. Select "Configure prompt coach status line"

3. Choose coach personality

4. (Optional) Enable ccusage token metrics display

5. Prompts will be analyzed locally in Claude Code



**Note**: Installation automatically backs up your current status line (if any). When you uninstall vibe-log, your original configuration is instantly restored.



## Local Report Generation Works



Generate comprehensive productivity reports from Claude Code and Codex sessions. No data leaves your machine.

- Select timeframe

- Select projects

  

```mermaid

flowchart TD

    Start([📝 Claude Code and Codex Sessions]) --> Select[vibe-log-cli select time frame and projects]

    Select --> Extract[Extracts & prepares session data]

    Extract --> Launch[Launches local ACP analysis]

    Launch --> Parallel{Session analysis}

    Parallel --> Gather[Gathers results &
Generates report]

    Gather --> Output[📊 HTML Report in current folder]    

    style Start fill:#e1f5fe

    style Output fill:#d4edda

```

## Example of Local Report Output

screencapture-file-C-vibelog-vibe-log-cli-vibe-log-report-2025-09-05-2-html-2025-09-05-15_54_16



## ☁ī¸ Cloud Sync (Optional)



Optionally sync your sanitized session data to the vibe-log dashboard for advanced analytics and tracking over time.



### Features

- **🎁 Free Forever**: Up to 1,000 session analyses per month

- **📈 Track Over Time**: Monitor your prompt quality and productivity trends

- **🔄 Auto-sync**: Configure hooks for automatic background sync

- **🔒 Privacy First**: All code removed before upload, only patterns synced

- **📊 Web Dashboard**: Learn and improve your AI coding sessions.



### How It Works



```mermaid

flowchart TD

    subgraph Local ["🏠 Your Machine"]

        Sessions[Claude Code and Codex Sessions] --> Select[Select sessions]

        Select --> Privacy[🔒 Privacy Layer
Removes code & secrets
Keeps only patterns]

    end

    

    subgraph Cloud ["☁ī¸ Vibe-Log Cloud"]

        Privacy --> Upload[Upload patterns]

        Upload --> Verify[Server verification]

        Verify --> Analysis[AI analysis]

        Analysis --> Dashboard[📊 Web Dashboard]

    end

    

    subgraph Features ["Dashboard Features"]

        Dashboard --> Track[📈 Track prompt improvement over time]

        Dashboard --> Metrics[⚡ Deeper productivity insights]  

        Dashboard --> Streaks[đŸ”Ĩ Peak times/Low times]

        Dashboard --> Prompt[đŸ’Ŧ User Prompt Analysis]

    end

    

    style Local fill:#e1f5fe

    style Cloud fill:#f3e5f5

    style Features fill:#d4edda

```

## Auto-Sync 

### What is Auto-Sync

Claude Code hooks and Codex hooks allow Vibe-Log to automatically sync local sessions in the background. Claude Code auto-sync is stable. Codex auto-sync is experimental and sync-only.



What are hooks?



  â€ĸ Small commands that run at specific moments in Claude Code or Codex

  

  â€ĸ They work silently in the background (you won't notice them)



  

Which Claude Code hooks do we use?



  📍 SessionStart - Syncs previous sessions when you start/resume work

     (Triggers: startup, resume, clear commands)

     

  đŸ“Ļ PreCompact - Syncs full session before context compression

     (Triggers: manual or automatic context cleanup)



     

Why we recommend both:



  ✓ SessionStart ensures nothing is lost between sessions

  

  ✓ PreCompact syncs everything before Claude compresses context



Which Codex hooks do we use?



  📍 SessionStart - Syncs recent Codex sessions when work starts



  🔚 Stop - Syncs after Codex finishes responding



  Codex hooks write Vibe-Log commands to Codex `hooks.json` and enable `[features].codex_hooks = true` in Codex `config.toml`. Vibe-Log does not install Codex prompt coach or statusline hooks.

    

### Setup Auto-sync

1. Run `npx vibe-log-cli`

2. Authenticate with your Github account

3. Enable auto-sync via CLI menu



## Supported Coding Engines 



Currently supported:

- ✅ Claude Code

- ✅ Codex (manual cloud sync, experimental auto-sync hooks, local standups, local reports)



Future:

- 🔜 Cursor

- 🔜 VS Code



🌍 Cross-Platform - Runs on macOS, Windows, Linux, and any environment with Node.js



## 🔒 Privacy & Security





Automated Releases

NPM Provenance

SHA256 Checksums

Open Source








**This package is built with complete transparency:**



- ✅ **Source Code**: Fully open source at [github.com/vibe-log/vibe-log-cli](https://github.com/vibe-log/vibe-log-cli)

- ✅ **Not Minified**: Published code is readable and verifiable

- ✅ **Source Maps**: Included for debugging and verification

- ✅ **Automated Builds**: All releases via GitHub Actions (no manual publishing)

- ✅ **npm Provenance**: Every package includes build attestation

- ✅ **Checksums**: SHA256 hashes for integrity verification



### Verify Our Package



```bash

# Download and inspect the package

npm pack vibe-log-cli@latest

tar -xzf vibe-log-cli-*.tgz

head -100 package/dist/index.js  # Verify it's readable



# Check checksums

cd package/dist && sha256sum -c checksums.sha256

```



### Privacy

- **Context-Preserving Sanitization**: Messages are sanitized to remove sensitive data while preserving context

- **What gets redacted/removed**:

  - Code blocks → `[CODE_BLOCK_1: javascript]`

  - API keys/tokens → `[CREDENTIAL_1]`

  - File paths → `[PATH_1]`

  - URLs → `[DATABASE_URL]`, `[API_URL]`

  - Emails → `[EMAIL_1]`

  - Environment variables → `[ENV_VAR_1]`

  - Also Removed: Images/Binary files 

- **What's preserved**: Conversation flow, questions, explanations

- **Transparent**: Preview sanitized data with the interactive prompt

- **Open source**: Review our sanitization at [src/lib/message-sanitizer-v2.ts](src/lib/message-sanitizer-v2.ts)



## Troubleshooting



### Authentication Issues

Try the following: 

- Log out from the CLI

- Clear cookies

- Re-authenticate via the CLI 



### No Sessions Found

- Make sure Claude Code or Codex is installed

- Check that you've used Claude Code or Codex recently

- For Codex cloud sync, use `send --source codex` or choose Codex from the manual sync menu



### Sessions Stuck in Analyzing

- Please open a Github issue.



### Debug Mode

```bash

# Enable debug logging

VIBELOG_DEBUG=1 npx vibe-log-cli send

```



## Contributing



We love your input! We want to make contributing to Vibe-Log CLI as easy and transparent as possible. Please see our [Contributing Guide](CONTRIBUTING.md) for details.



```bash

# Clone the repository

git clone https://github.com/vibe-log/vibe-log-cli.git

cd vibe-log-cli



# Install dependencies

npm install



# Run tests

npm test



# Build the project

npm run build

```



Check out our [open issues](https://github.com/vibe-log/vibe-log-cli/issues) for a list of proposed features and known issues.



## Community



- **GitHub**: Star us on [GitHub](https://github.com/vibe-log/vibe-log-cli)

- **Issues**: Report bugs and request features in [GitHub Issues](https://github.com/vibe-log/vibe-log-cli/issues)

- **Website**: Visit [vibe-log.dev](https://vibe-log.dev)



## Support



Need help? Here are some ways to get support:

- 🐛 Report bugs in [GitHub Issues](https://github.com/vibe-log/vibe-log-cli/issues)

- 📧 Email us at support@vibe-log.dev



## License



MIT Š Vibe-Log - see the [LICENSE](LICENSE) file for details.



## Acknowledgments



Built with love by the Vibe-Log team [@mickmicksh](https://github.com/mickmicksh), [@dannyshmueli](https://github.com/dannyshmueli)



Special thanks to [ccusage](https://www.npmjs.com/package/ccusage) for providing token usage metrics integration for Claude Code sessions.



## Star History



[![Star History Chart](https://api.star-history.com/svg?repos=vibe-log/vibe-log-cli&type=Date)](https://www.star-history.com/#vibe-log/vibe-log-cli&Date)