Skip to main content

Quality metrics for Claude Code sessions — score, track, and improve.

Project description

Qualito

Quality metrics for AI-assisted development. Know if your Claude Code sessions are worth the cost.

PyPI Python License

What it does

Qualito scores every Claude Code session on multiple quality dimensions (error rate, tool diversity, cache utilization, completion with work) and rolls them into a single Score (0-100). It tracks cost, detects incidents (error spikes, cost anomalies, quality drops), and surfaces actionable recommendations.

  • Read existing Claude Code sessions — no behavior change needed
  • Score each session across multiple dimensions (0-100)
  • Track costs, detect incidents, monitor quality trends
  • Set SLOs and get alerts when quality drops
  • Compare runs before/after a change (observational experiments)

Quick Start

See docs/getting-started.md for the full walkthrough.

Short version:

  1. Sign up at https://app.qualito.ai/login
  2. Copy the setup command shown on the onboarding page (includes a one-time token)
  3. Paste into your terminal:
    uvx qualito@latest setup st_setup_<your_token>
    
  4. Refresh the dashboard → your sessions are live

Cloud Dashboard

Free tier: 3 workspaces synced. Pro ($29/mo, coming soon): unlimited workspaces + LLM-generated root-cause + report summaries.

CLI Commands

Command What it does
qualito setup First-time setup: import sessions, configure MCP, optional cloud sync
qualito status See your local and cloud sync state
qualito import Import Claude Code sessions for measurement (--force to re-process)
qualito costs Analyze spending by workspace, model, and time
qualito privacy View or change per-workspace sync privacy settings
qualito audit list List flagged runs needing review
qualito sync Push local sessions to the cloud dashboard
qualito login Authenticate with the Qualito cloud
qualito logout Remove cloud credentials

View your data

Qualito is CLI-first. Your data lives locally and is accessed through commands:

qualito status       # local + cloud breakdown with per-workspace tokens + cost
qualito costs        # detailed spend analysis
qualito privacy      # per-workspace sync privacy settings
qualito audit list   # flagged runs needing review

For a web UI with charts and history, sync to the cloud and view at https://app.qualito.ai.

Privacy

Qualito is local-first. Your session data lives on your machine, and you control what syncs to the cloud on a per-workspace basis.

  • Default: metadata only (counts, durations, types, scores)
  • Opt in per workspace to sync full content for a richer dashboard
  • Every sync scanned for secrets (AWS keys, API tokens, passwords, etc.)
  • Server enforces your stated settings — defense in depth

See docs/privacy.md for the full field-by-field breakdown.

MCP Server

Use Qualito inline in your editor via MCP:

{
  "mcpServers": {
    "qualito": {
      "command": "uvx",
      "args": ["qualito-mcp"]
    }
  }
}

Tools available: qualito_setup, qualito_score, qualito_cost, qualito_patterns, qualito_warnings, qualito_templates, qualito_incidents, qualito_slo.

Local Development

git clone https://github.com/mp-web3/qualito.git
cd qualito
uv sync --extra dev --extra server

# Run tests
uv run pytest

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

qualito-0.1.12.tar.gz (86.5 kB view details)

Uploaded Source

Built Distribution

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

qualito-0.1.12-py3-none-any.whl (92.4 kB view details)

Uploaded Python 3

File details

Details for the file qualito-0.1.12.tar.gz.

File metadata

  • Download URL: qualito-0.1.12.tar.gz
  • Upload date:
  • Size: 86.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.5 {"installer":{"name":"uv","version":"0.10.5","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for qualito-0.1.12.tar.gz
Algorithm Hash digest
SHA256 14c2d5d2ddc467b9788bb68738bcacb4c44d3fd621a2510f1c8fd79d1f0da718
MD5 265581fca00468d14e25af8cfbe940ab
BLAKE2b-256 281e47093266775a95f6599d2bb34e5c3147014f59da85c995f2b56e3f28bcfa

See more details on using hashes here.

File details

Details for the file qualito-0.1.12-py3-none-any.whl.

File metadata

  • Download URL: qualito-0.1.12-py3-none-any.whl
  • Upload date:
  • Size: 92.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.5 {"installer":{"name":"uv","version":"0.10.5","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for qualito-0.1.12-py3-none-any.whl
Algorithm Hash digest
SHA256 676fe320c056422da51f6edf19593f7b3c8bf788abb210b1858ba9d230a3d773
MD5 aae77513a8fff2e4969789cffb76bb2b
BLAKE2b-256 dbd2f6c25f34566ec0f23bd39b8facf15d3e699fde4e4d891fc74e1a8832c51a

See more details on using hashes here.

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