Skip to content
← all systems

Vantage

Local-first analytics for Claude Code: token, cost, and agent-delegation insight from your own session logs.

thousands of sessions · zero data leaves the machine

role
Architect and sole engineer
stack
Next.js · TypeScript · Tailwind v4 · virtualized lists
status
oss

Vantage is local-first analytics for Claude Code. It reads the .jsonl session transcripts Claude Code already writes to ~/.claude/projects - no instrumentation, no telemetry - and turns thousands of them into token, cost, and agent-delegation insight: totals, a year heatmap, model mix, per-project and per-branch rollups, a searchable session explorer, and a cost view with a burn-rate meter. Every byte is computed on the machine that owns the data; nothing leaves it, and you can verify that by reading the code.

// 01 - PROBLEM

Heavy Claude Code users accumulate thousands of .jsonl session transcripts and no way to answer: where did the tokens go, what did each session cost, which projects and tools dominate? Existing tools ship your usage data to third parties.

// 02 - APPROACH

  • Reads the session logs Claude Code already writes to ~/.claude/projects - no instrumentation, no telemetry.
  • Insights dashboard: token totals, year heatmap, model mix, per-project and per-branch rollups, tool frequency.
  • Session explorer: server-side search, sort, filter over a virtualized list; per-session agent timeline and delegation tree.
  • Cost view: per-model estimates, 5-hour billing-window tracker, burn-rate meter.

// 03 - ARCHITECTURE

▸ parse-once ingest · bounded memory

  1. ~/.claude logs

    Session transcripts Claude Code already writes

  2. Parse once

    Each file parsed a single time into a compact contribution

  3. mtime cache

    Cache by modified-time; raw events dropped after rollup

  4. Rollups

    Per-project, per-branch, and per-tool aggregates

  5. Dashboard

    Insights, session explorer, and cost view

Parse once, cache by mtime
Each file parses a single time into a compact per-session contribution; full message events are dropped after rollup. Memory stays bounded across thousands of sessions.
Local-first, always
Everything computes on the machine that owns the data. Privacy mode anonymizes names for screenshots and demos.

// 04 - PRODUCTION-GRADE

  • Stays fast at thousands-of-sessions scale (windowed virtualization, server-side filtering)
  • Editable per-model pricing so estimates track reality
  • Keyboard-accessible controls, loading skeletons, empty states
  • Nothing leaves the machine - verifiable by reading the code

// 05 - SCREENS

Vantage insights dashboard with token totals, year heatmap, model mix, and rollups
Insights: token totals, year heatmap, model mix, and per-project rollups.
Vantage session explorer with search, filter, and a per-session agent timeline
Session explorer: server-side search and filter over a virtualized list.

// 06 - ARTIFACTS