Web UI

tj serve starts TokenJam Lens, a local dashboard at http://127.0.0.1:7391/.

tj serve

The web UI is a single Vite-built bundle served by the local REST API. No external dependencies, no cloud calls — it reads the same local store the CLI does.

How costs are framed

TokenJam never tells you that you “saved” money. It only ever shows what is estimated recoverable, and it adapts the unit to how you pay:

• Subscription plans (the “Max 5x plan” badge by the page title) — you see your token share and a × plan value multiplier (how many times your flat plan fee your usage is worth at on-demand rates). You never see a raw dollar figure, because there isn’t one to show.
• API keys — you see dollars, since every token has a real per-unit price.
• Per-item cost is always tokens. Traces, agents, and the cost table report token counts; the dollar/multiplier translation only happens at the headline level.

Every recoverable-waste figure carries an Estimated tag. Nothing is presented as realized savings until you act on it.

Dashboard

The Dashboard is the default landing view. It merges what used to be the separate “Overview” page into a single triage surface, so the first thing you see is where your tokens are going and what is recoverable.

It has three stacked sections:

• Recoverable Waste (Estimated) — one tile per analyzer: Downsize, Cache, Script, Reuse, Trim. Each tile shows its current finding (“No candidates”, ”✓ 100% cache efficacy”, “Not ready”) and drills through in place — click a tile to expand the underlying detail without leaving the Dashboard.
• Health at a glance — unread alerts, agents drifting (vs. their learned baseline), budgets at risk, and recent session activity, each as a single-number card.
• Explore — an embedded pivot explorer: pick a metric × dimension × chart (e.g. Spend by Model as Bars), flip the Stack, and read the headline KPIs (× plan value, tokens, sessions, events) with period-over-period deltas and a run-rate line. One-click Presets (Spend by model, Cost leaderboard, Tokens over time, Tool usage) and Export CSV are built in. The time-window selector (Last 7d / 30d / 90d) scopes the whole page.

The same pivot answers very different questions without leaving the page:

Cost leaderboard — Spend × Model as a ranked leaderboard.

Tool usage — Events × Tool category, ranked.

Status

Per-agent overview. Toggle between Cards and List (List is the default); each agent shows cost today (tokens), tokens in/out, tool calls, elapsed/active time, and any active alerts. Click an agent for its detail, or jump straight to its cost or traces. Recent alerts are listed inline below.

Traces

A session-level list of recent traces with token cost, duration, and span count. Open one for the cost-annotated waterfall: every span is laid out by magnitude (toggle By tokens / By duration) with a per-span cost/token column, and hovering a span reveals the call detail — provider, model, input/output tokens, and cache read/write.

Cost

Spend over time (in tokens) with a linear run-rate marker, paired with the Caching card — cache hit-rate, cached reads in the window, and per-day cached-token volume. Cached input bills at roughly a tenth of the normal input rate, so high cache reads spare your token budget. A per-day table breaks input, output, cache-read, cache-write, and total cost down by agent or model.

Analytics

The same pivot explorer as the Dashboard’s Explore band, given the full screen — metric × dimension × chart, stacking, presets, and CSV export — for when you want to dig past triage into ad-hoc analysis.

Alerts

Full alert history with a severity filter and inline detail expansion. Retry loops, drift, and budget breaches all surface here.

Drift

Behavioral drift report with Z-score analysis: it compares the latest session against a learned baseline and flags where behavior has moved outside normal range.

Optimize

The recoverable-waste analyzers in full — the same Downsize / Cache / Script / Trim / Reuse findings summarized on the Dashboard, expanded with the per-finding evidence behind each estimate. Mirrors tj optimize on the CLI.

Budget

View and edit daily and per-session ceilings per agent. Clearing a field (or entering 0) removes the limit, and changes are written to your config file immediately. Recent budget alerts are listed inline so you can see which scopes have breached.

Auto-polling

The UI auto-refreshes every few seconds while a session is active. Disable it from the settings menu if you’d rather refresh manually.

Sharing

By default tj serve binds to 127.0.0.1 (loopback only). To reach the dashboard from another machine on your network:

tj serve --host 0.0.0.0

Authentication can be enabled in Configuration. The ingest secret is separate from UI auth.

No signup, no cloud. Runs entirely on your machine.