# chiphuyen/sniffly

Claude Code dashboard with usage stats, error analysis, and sharable feature

Repository: https://github.com/chiphuyen/sniffly
Canonical: https://ross.abutalabs.com/products/sniffly
Homepage: https://sniffly.dev
Language: Python
License: MIT
License Family: permissive
Topics: agent, ai, analytics, coding
Last push: 2025-08-08T18:38:03+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 35, release rhythm 35, longevity 29
- inputs: {"age_days": 414, "days_push": 390, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1263, forks 120 (observed 2026-08-28T04:04:10.483016+00:00)

## What it is
Sniffly is a Python-based analytics dashboard for Claude Code that parses local Claude Code logs to surface usage statistics, error breakdowns, and message history. It runs a local web server with a browser dashboard and supports generating shareable links to stats and instructions.

## Use cases
- analyze my Claude Code usage patterns
- see where Claude Code makes mistakes
- visualize token and tool usage stats from Claude Code logs
- share my Claude Code session stats with coworkers
- walk through my Claude Code prompt history
- dashboard for AI coding assistant logs

## When to choose
- you use Claude Code and want insight into your usage and its errors
- you want a self-hosted, local dashboard over your own logs
- you need shareable reports of your AI coding sessions

## When to avoid
- you don't use Claude Code or another tool whose logs it can parse
- you need team-wide aggregated analytics across many users
- you want real-time monitoring or alerting rather than retrospective analysis

## Facets
- artifact type: application
- maturity: active
- function: analytics, developer-tools, cli, data-visualization, logging
- domain: developer-tools, analytics
- platform: python, cli, cross-platform
- tags: claude-code, ai-coding-assistant, usage-stats, dashboard, log-analysis, sharable-reports, ai-agents, command-line, web-server

## Member repositories
- chiphuyen/sniffly (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:10.483016+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:04:07.500510+00:00, confidence not recorded.
  - readme: https://github.com/chiphuyen/sniffly (fetched 2026-08-28T04:04:10.483016+00:00, sha 6d0c1b08c8d3)
  - homepage: https://sniffly.dev (fetched 2026-08-29T12:16:28.976047+00:00, sha 22eee4d4e68c)
  - registry_pypi: https://pypi.org/pypi/sniffly/json (fetched 2026-08-29T12:16:28.985687+00:00, sha 861ed6e03ff0)
- Data as of 2026-08-30T08:39:29.467469+00:00.