CLUSTER AGENT-DASHBOARD-LOCAL · 19 ENTRIES · EARLIEST ENTRY 2026-09-04

AI coding agent usage dashboards

This cluster consists of local dashboard tools that parse AI coding agent session logs to display token usage, cache hit rates, cost estimates, and activity across models and tools. The dated history is too thin to read a shape from—it predates the index or its members are undated. Traction leaders include hermes-plugin-session-analyzer with 16 stars, HanaAgent-session-insight with 7 stars, and secaiq-watch with 5 stars.

Entry timeline

ENTRY TIMELINE

AUG 2026: 3SEP 2026: 10OCT 2026: 6
AUG 2026OCT 2026

Members by activity

Activity signals, not revenue.

Build origin · 2 hand-coded · 17 unlabelled

Operator · 13 hobby · 6 unlabelled

Two labels per entry, never collapsed into one: how it was built, and who stands behind it. Counted over the 19 listed below. Unlabelled means nothing has decided yet — not that the answer is small.

  1. 01HanaAgent-session-insight7★23 days—hand-codedDashboard for developers that visualizes AI session usage including token counts, cache hit rates, costs, and vendor balances.
  2. 02agent-lookout5★3 dayslivehobbyLocal dashboard that monitors AI agent sessions running on a machine and highlights which ones are waiting for user input.
  3. 03sessionscope1★14 dayslivehobbyLocal-first web app that lets users browse, search, and compare AI agent session transcripts with token and cost analytics.
  4. 04agent-monitor2★6 days—Local dashboard that shows what AI coding agents did during sessions, including costs, timelines, touched files, and searchable logs, without cloud upload.
  5. 05claude-code-capsule-panel1★3 days—hobbyLive usage dashboard that shows context-window usage, cache hits, rate-limit forecasts, costs, and activity for AI coding sessions.
  6. 06token-dashboard1★21 days—hobbyLocal dashboard that reads AI agent session logs to show token usage, cache hit rates, and cost estimates, updating automatically in a browser.
  7. 07agent-token-viewer1★18 days—hobbyLocal dashboard that scans AI coding agent session files and displays token usage, costs, and activity across tools and models.
  8. 08token-lens0★13 days—Local dashboard that displays real-time token usage and cost for AI coding agent sessions, reading on-disk logs without cloud or telemetry.
  9. 09token-meter0★7 dayslivehobbyLocal dashboard that tracks token usage, cache hit rates, and usage trends for multiple AI coding agents and reconciles official account usage against local logs.
  10. 10claude-dashboard0★22 days—hobbyLocal dashboard that visualizes running AI coding assistant sessions, showing sub-agent trees, scheduled jobs, and token cost estimates.
  11. 11agent-leverage0★11 dayslivehobbyDashboard that analyzes local coding-agent logs to show how many hours AI agents work per user hour and compares that ratio over time.
  12. 12agent-radar0★11 dayslivehobbyLocal web dashboard that shows all active AI coding sessions on a computer as live radar blips with status cards and progress visuals.
  13. 13codexmon0★1 moliveDeveloper dashboard that monitors AI coding assistant usage, showing live agent activity, token consumption, subagent lineage, and historical trends from local session logs.
  14. 14burnboard0★19 days—Web dashboard that monitors AI coding agent usage and token costs from local session logs.
  15. 15claude-usage0★23 days—hobbyUtility that tracks AI coding assistant usage limits, reset times, and burn rate from local logs in a dashboard.
  16. 16codex-fleet-monitor1★1 molivehobbyDashboard that monitors AI coding sessions, subagent activity, token usage, and quotas across shared hosts.
  17. 17codex-usage1★1 molivehobbyDesktop app that monitors usage of an AI coding tool by reading local session logs and displaying statistics.
  18. 18claude-cache-monitor0★1 mo—hand-codedhobbyReal-time dashboard that monitors an AI coding assistant's session logs to show cache status, costs, and context composition.
  19. 19cocopit1★2 mo—Web console that tracks usage and costs for AI coding agents, providing session browsing, quota management, and a built-in terminal.