Skip to main content

Agent Trajectory visualization and analysis platform

Project description

VibeLens

VibeLens

See what your AI coding agents are actually doing.
Replay. Analyze. Evolve.

PyPI Python License Live Demo

Live Demo · Quick Start · Supported Agents · PyPI · Changelog


VibeLens Comic — Understand your agent. Teach it. Master it.

Let your agent know you better!


Your AI coding agents run hundreds of tool calls, burn thousands of tokens, and you have no idea what happened. VibeLens changes that.

# macOS / Linux. Paste into Terminal.
curl -LsSf https://raw.githubusercontent.com/CHATS-lab/VibeLens/main/install.sh | sh

No Python, no pip, nothing to set up first. The script installs uv (a single binary), fetches VibeLens, and opens it in your browser.

Just want a look? Try the live demo. Nothing to install.

One install. Reads local logs. Works with Claude Code, Codex CLI, Gemini CLI, and OpenClaw out of the box.

Features

Feature Description
Session visualization Step-by-step timeline with tool calls, thinking, and sub-agents
Dashboard analytics Usage heatmaps, cost breakdowns, and per-project stats
Productivity tips (needs LLM key or Agent) Detects recurring frustration patterns and suggests concrete fixes
Personalization (needs LLM key or Agent) Retrieve, customize, and evolve reusable skills from your real sessions
Session sharing Share sessions via one-click links
Multi-agent support Claude Code, Codex CLI, Gemini CLI, OpenClaw with auto-detection

Supported Agents

Agent Format Data Location
Claude Code JSONL ~/.claude/projects/
Codex CLI JSONL ~/.codex/sessions/
Gemini CLI JSON ~/.gemini/tmp/
OpenClaw JSONL ~/.openclaw/agents/

VibeLens auto-detects the agent format. Just point it at your session directory and it works.

Screenshots

Session Visualization & Dashboard Analytics

Session Visualization

Session Visualization
Step-by-step timeline with messages, tool calls, thinking blocks, and sub-agent spawns.

Dashboard Analytics

Dashboard Analytics
Usage heatmaps, cost breakdowns by model, and per-project drill-downs.

Productivity Tips & Personalization

Productivity Tips

Productivity Tips
Detect friction patterns and get concrete suggestions to improve your workflow.

Skill Recommendation

Skill Recommendation
Match workflow patterns to pre-built skills from the catalog.

Skill Customization

Skill Customization
Generate new SKILL.md files tailored to your session patterns.

Skill Evolution

Skill Evolution
Evolve installed skills with targeted edits based on your real sessions.

Quick Start

One-liner (recommended)

Zero prerequisites: no Python, no pip. The commands below install uv first, then run VibeLens.

# macOS / Linux. Paste into Terminal.
curl -LsSf https://raw.githubusercontent.com/CHATS-lab/VibeLens/main/install.sh | sh
# Windows. Paste into PowerShell.
irm https://raw.githubusercontent.com/CHATS-lab/VibeLens/main/install.ps1 | iex

VibeLens starts on http://localhost:12001 and your browser opens automatically. Change it with --port (for example, vibelens serve --port 8080).

Pick your path

Your situation Command
Nothing installed (recommended) one-liner above
Already have Python 3.10+ pip install vibelens && vibelens serve
Prefer the npm workflow (Python also required) npx @chats-lab/vibelens serve
Want to hack on VibeLens developer setup

What happens on first run

  1. Your browser opens to http://localhost:12001.
  2. If you have Claude Code, Codex CLI, Gemini CLI, or OpenClaw sessions, VibeLens auto-detects them from ~/.claude/, ~/.codex/, ~/.gemini/, or ~/.openclaw/.
  3. Otherwise, bundled example sessions (recipe-book) show up so you can look around.
  4. Productivity Tips and Personalization need a language-model API key. Optional; configure later in Settings.

pip (if you already have Python 3.10+)

pip install vibelens
vibelens serve

Check your version first with python3 --version. Need Python? See docs/INSTALL.md.

uv (run without a permanent install)

uvx vibelens serve

This fetches VibeLens into uv's cache and runs it without a global install. The one-liner above calls this under the hood.

npm (if you already have Python and prefer the npm workflow)

VibeLens is a Python app with an npm wrapper for convenience. The wrapper still requires Python 3.10+ and an installed vibelens package. Use this when you already have both and want npx/npm ergonomics.

npx @chats-lab/vibelens serve

Or install globally: npm install -g @chats-lab/vibelens.

Developer setup

git clone https://github.com/CHATS-lab/VibeLens.git
cd VibeLens
uv sync --extra dev
uv run vibelens serve

Configuration

YAML configuration with environment variable overrides (VIBELENS_*). See config/vibelens.example.yaml for all options.

# Use a config file
vibelens serve --config config/self-use.yaml

# Override host/port
vibelens serve --host 0.0.0.0 --port 8080

Troubleshooting

Top issues. For the full list, see docs/INSTALL.md.

Data Donation

VibeLens supports donating your agent session data to advance research on coding agent behavior. Donated sessions are collected by CHATS-Lab (Conversation, Human-AI Technology, and Safety Lab) at Northeastern University.

To donate, upload your data, select the sessions you want to share, and click the Donate Data button.

Contributing

Contributions are welcome! Please ensure code passes ruff check and pytest before submitting.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vibelens-1.0.1.tar.gz (22.6 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vibelens-1.0.1-py3-none-any.whl (12.1 MB view details)

Uploaded Python 3

File details

Details for the file vibelens-1.0.1.tar.gz.

File metadata

  • Download URL: vibelens-1.0.1.tar.gz
  • Upload date:
  • Size: 22.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for vibelens-1.0.1.tar.gz
Algorithm Hash digest
SHA256 d3096b60d4af2109765deb8ffd75df70864b70798909640561a677b68d391caf
MD5 c9f769fa6cf47364825f8d6ed310ec7b
BLAKE2b-256 4a0e2bd5b644855f2cff105b27f42622f02bdb98b508d27075bd5f36dc4478dc

See more details on using hashes here.

Provenance

The following attestation bundles were made for vibelens-1.0.1.tar.gz:

Publisher: publish.yml on CHATS-lab/VibeLens

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vibelens-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: vibelens-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 12.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for vibelens-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 af486a4b1e63e4d1c3bca650f1574cc59e7b9226dded5fc3f1b4d796d7868add
MD5 3ea2e794684d2a751c9e5ff3e88c9296
BLAKE2b-256 dfd9313b1f2e22dd250446cd01657ac885b2af3b52561f11edd6e2be3717edd2

See more details on using hashes here.

Provenance

The following attestation bundles were made for vibelens-1.0.1-py3-none-any.whl:

Publisher: publish.yml on CHATS-lab/VibeLens

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page