{"full_name":"Maciek-roboblog/Claude-Code-Usage-Monitor","owner":"Maciek-roboblog","name":"Claude-Code-Usage-Monitor","shard":"1","url":"https://github.com/Maciek-roboblog/Claude-Code-Usage-Monitor","description":"Real-time Claude Code usage monitor with predictions and warnings","homepage":"","topics":["ai","claude","claude-code","limits","monitoring","terminal","usage-tracking","claude-usage","analytics"],"tag_pages":["ai","analytics","claude","claude-code","monitoring","terminal"],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/18363314?u=3482c061aff2019ec6b4e16fb49b98fcbc4effa8&v=4","created_at":"2025-06-19T00:00:05Z","pushed_at":"2026-07-05T04:52:21Z","metrics":{"stars":8801,"forks":461,"watchers":34,"issues":134,"prs":82,"releases":12,"issues_open":26,"issues_closed":108,"prs_open":14,"prs_closed":48,"prs_merged":20,"discussions":11},"growth":{"day":{"stars":0,"forks":1,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[8799,8800,8800,8801,8801,8801,8801],"forks":[462,462,461,461,461,460,461],"watchers":[null,34,34,34,34,34,34],"issues_open":[null,26,26,26,26,26,26],"prs_open":[null,13,13,13,13,13,14]},"boards":{},"same_owner":[],"issues":[{"number":158,"title":"[BUG] Incorrect Cost Usage calculation when continuing work in a resumed session","comments":11,"created_at":"2025-09-18T10:33:48Z"},{"number":31,"title":"brew support?","comments":11,"created_at":"2025-06-20T16:24:32Z"},{"number":212,"title":"monitor dosnt look accurate","comments":3,"created_at":"2026-05-01T16:33:20Z"},{"number":152,"title":"Feature Request: Cross-device usage synchronization","comments":3,"created_at":"2025-09-01T14:50:01Z"},{"number":235,"title":"Persist an audit trail for extra-usage transitions and provider-reported billing state","comments":1,"created_at":"2026-07-27T18:15:59Z"},{"number":231,"title":"On Windows, CCMonitor is tryingm to access WSL?","comments":1,"created_at":"2026-07-18T13:51:05Z"},{"number":206,"title":"Debian Packaging","comments":1,"created_at":"2026-04-14T07:23:36Z"},{"number":187,"title":"API based claude code cost monitoring like LiteLLM","comments":1,"created_at":"2026-02-13T16:39:51Z"}],"discussions":[{"number":225,"title":"SigRank — token-efficiency leaderboard that ranks operators, not just models","comments":0,"category":"Show and tell","created_at":"2026-07-03T16:54:47Z"},{"number":218,"title":"ccline: type natural language at your zsh prompt, get AI answers — for Claude Code users","comments":0,"category":"Show and tell","created_at":"2026-06-10T08:38:11Z"},{"number":213,"title":"Using Claude Code for investment analysis — options flow scanner + price alerts (open source)","comments":0,"category":"General","created_at":"2026-05-13T13:39:05Z"},{"number":205,"title":"ESP32/RasPi Support","comments":1,"category":"Ideas","created_at":"2026-04-13T09:07:53Z"},{"number":203,"title":"Translating the 88k gauge into \"Real-World Work\" capacity","comments":0,"category":"General","created_at":"2026-04-12T08:38:35Z"},{"number":194,"title":"Research request: what real value remains beyond /usage, /stats, and the native status line?","comments":7,"category":"Announcements","created_at":"2026-03-12T08:45:40Z"},{"number":191,"title":"Should I run it inside .ralph or from the parent level?","comments":0,"category":"Q&A","created_at":"2026-02-24T08:20:34Z"},{"number":168,"title":"Help calibrating actual usage and shown Usage?","comments":2,"category":"Q&A","created_at":"2025-10-14T16:55:11Z"}],"latest_release":{"name":"Release v4.0.0","tag":"v4.0.0","published_at":"2026-06-27T09:31:40Z","body":"### Bug Fixes\n- **Model distribution shows all families**: `ModelUsageBar` now renders every model family — Sonnet, Opus, Haiku, and an \"Other\" bucket for anything else — instead of only Sonnet/Opus. Haiku and other models no longer vanish from the usage bar or skew the displayed percentages. (#124, #164)\n- **Plan is now saved and restored**: the selected `--plan` is persisted in `last_used.json` and reloaded on the next run; an explicit `--plan` on the command line still takes priority. (#162)\n- **Saved theme no longer overwritten**: an explicitly chosen `light`/`dark`/`classic` theme is preserved across runs instead of being silently replaced by background auto-detection. (#102, #200)\n- **Clear message on unsupported Python**: running on Python older than 3.9 now prints a clear \"Python 3.9+ is required\" message (with a `uv` install hint) instead of failing cryptically; the version check is now actually wired into startup and uses the documented 3.9 minimum. (#172)\n- **Helpful \"no data\" diagnostic**: when no Claude data directory is found, the monitor now lists the exact paths it searched and how to fix it, instead of a single terse line / blank screen. (#110)\n- **CLAUDE_CONFIG_DIR is honored**: when set, usage data under `$CLAUDE_CONFIG_DIR/projects` is discovered (comma-separated directories supported) and checked before the standard locations; path discovery also deduplicates repeated directories. (#116)\n- **Up-to-date, version-specific model pricing**: token costs now use current Anthropic rates — Opus 4.5+ at $5/$25 (previously billed at the legacy $15/$75, a 3x overcharge), Haiku 4.5 at $1/$5, and Fable 5 at $10/$50 — while older models (Opus 3/4.0/4.1, Haiku 3/3.5) keep their original rates. (#182)\n- **`--reset-hour` is now actually applied**: the flag was accepted and persisted but never used in any calculation. It now sets the daily rollover boundary in the daily/monthly table views, so a usage day runs from `reset_hour` to `reset_hour` (e.g. `--reset-hour 4` counts 02:00 toward the previous day) instead of midnight to midnight. It deliberately does not shift the rolling 5-hour window, whose reset comes from the session/official data. (#95, #96, #106)\n- **Reset time prefers what Claude reported**: when a session block contains a rate-limit message with a reset time, that time is shown as the reset instead of the start-plus-5h estimate, so the displayed reset matches what Claude actually told you. Official statusline limits still take precedence when available. (#114, #106)\n- **Epoch reset timestamps parsed in UTC**: a numeric reset timestamp from a `limit reached|<epoch>` message was parsed as local wall time and then mislabeled as UTC, shifting the shown reset by the host's offset on non-UTC machines (e.g. two hours off in Central Europe). Epochs are now interpreted as the absolute UTC instant they are. (#106, #220)\n- **Windows and local timezone detection now use IANA zones**: Windows auto-detection now uses `tzlocal` and refuses to return raw `tzutil` labels such as `Eastern Standard Time` as if they were valid `pytz` zones; the accepted `--timezone local` alias now resolves before display code runs. Added regression coverage for Istanbul reset display so reset times do not drift by an extra hour. (#188, #98, #121, #220)\n- **Non-Anthropic models are no longer priced as Claude**: a model routed through Claude Code Router (e.g. a GPT or DeepSeek model) was silently billed at the Sonnet rate, inflating reported cost. Models that are not recognizably Anthropic now report as unpriced ($0) instead of a fabricated Claude cost; unknown but clearly-Claude models still use the family fallback. (#217, #199)\n- **Official limits hardened against stale and malformed captures**: a statusline capture older than the freshness window no longer drives the displayed reset, status, or `confidence: official` label (it falls back to the local estimate, flagged `stale`); an official percentage drives the exit code even with no local sess","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}