Back to AIWatcher
Open source · early access

AIWatcher Local.

See what your local AI coding tools are doing before the invoice, the incident, or the runaway session surprises you. AIWatcher Local is the open-source individual tier: a private, zero-code-change view of Claude Code, Codex CLI, and Cursor activity on your machine. No account.

127.0.0.1:8765

AIWatcher Local

Last 7 days
TodayPromptProjectsSessionsInsights
Latest AI work
Your most recent local session and its outcome.
~/code/api-gateway
claude-code · $8.08 API-equivalent
Useful
One thing worth changing
The highest-signal local recommendation for your next run.

~/code/ml-pipeline crossed 250 model calls in one session — add an explicit stop condition before running it again.

Useful outcomes
4
Value per useful change: $3.76
Preflight decisions
11
Last 7 days
Sessions observed
9
This machine only
API-equivalent value
$15.72
Excludes subscription allocation
Projects driving AI usage
~/code/api-gateway
$8.39
~/code/data-sync
$4.93
~/code/web-app
$1.72
~/code/meeting-notes
$0.67
Models and tools
claude-sonnet-4-6
$15.72
gpt-5.5
$0.00
Recent sessions
ToolProjectTokensAPI valueOutcome
claude-code~/code/api-gateway551.9k$8.08Useful
codex-cli~/code/ml-pipeline179.1M$0.00Rework
claude-code~/code/data-sync330.9k$4.93Useful
claude-code~/code/web-app127.4k$1.72Useful
claude-code~/code/meeting-notes59.6k$0.65
claude-code~/code/api-gateway20.9k$0.31Useful
Local weekly report
Your AI coding week
9 local sessions$15.72 API-equivalent value358.2M tokens observed1165 tool calls observed
Enterprise handoff

Enterprise adds team history, policy controls, HITL approvals, evidence packs, and integrations.

Team visibilityBudget guardrailsAudit evidenceSSO/RBAC
Read-onlyNo LLM callsNo telemetryNo cloud upload
The local dashboard, served from your own machine at 127.0.0.1:8765.

What AIWatcher Local shows you

One developer, one machine, one read-only view. It answers the questions you actually ask when the bill looks off or a session ran longer than you meant it to:

Active tools

Which local AI coding tools are active right now.

Project usage

Which projects are driving usage, down to the git project root, not a parent folder.

Model spend

Which models are generating the most API-equivalent value.

Priced vs. limited

Which usage is API-priced versus subscription or plan-limited.

Worth a look

Which recent sessions are worth inspecting, with click-through detail.

Session detail

What happened inside a session, without showing prompt or source text.

Costliest ask

Which prompt or turn inside a session actually drove the cost, and which one is worth tightening next time.

Stop the runaway before it happens

Most tools tell you what an AI session cost after it’s over. AIWatcher Local can step in before a risky prompt runs at all.

Every prompt gets a local risk score — broad, destructive, vague, or expensive work is flagged before execution. AIWatcher then produces an intent-preserving execution brief: the same request, scoped down to what’s actually needed.

Automatic coverage

Install a native hook for Claude Code or Codex CLI once, and every prompt is preflighted automatically — no workflow change.

Your call, every time

For anything medium or high risk, a local decision screen (nothing leaves your machine) gives you four options: use the brief, edit it first, run the original anyway, or cancel. Low-risk prompts pass straight through.

Works even where hooks can’t reach: Claude Desktop, web chat, and editor sidebars don’t expose hook points yet. The dashboard’s Prompt Companion gives you the same preflight check as a copy-paste widget.

Turn it on:

console
$ aiwatcher install-claude-hook --write --scope user --gate
$ aiwatcher install-codex-hook --write --scope user --gate

A CLI and a local dashboard

aiwatcher today

The fast terminal version. A daily summary of measured AI work, broken down by tool, model, and project.

aiwatcher ui

A local dashboard at 127.0.0.1:8765. Served from the standard library, no external assets. Project rows and sessions are clickable.

And here is a local session in the terminal. Scroll for the weekly report and per-project projects breakdown:

console
$ aiwatcher today

Today - Tuesday, June 23, 2026
3 sessions · 551.9k API-priced tokens · 239.0M plan/limited observed · $8.08 API-equivalent value
Projected month: ~$71.09 API-equivalent at current pace
Note: subscription plans may not bill this as incremental spend.

By tool
Tool              API value   Calls    Tokens  Sessions
-------------------------------------------------------
claude-code           $8.08     896    551.9k         1
codex-cli             $0.00       2    239.0M         2

By model
Model                 API value    Tokens   Calls
-------------------------------------------------
claude-sonnet-4-6         $8.08    551.9k     896
gpt-5.5                   $0.00    239.0M       2

Top project: ~/code/api-gateway (100% of today's API-equivalent value)
Note: Codex cost is subscription/plan-based, not estimated as API spend

This week: $15.72     This month: $54.50

$ aiwatcher report --days 7

AIWatcher Local report - last 7 days
Sessions: 9 · API-equivalent value: $15.72 · Tokens: 358.2M
Model calls: 1888 · Tool calls: 1165

Top project: ~/code/api-gateway ($8.39)
Top tool: claude-code (6 sessions)
Top model: claude-sonnet-4-6 (1.1M tokens)

Suggested next checks:
- Review top project sessions for runaway or abandoned work.
- Compare API-priced tokens with plan/limited tokens before reading invoice impact.
- Run `aiwatcher ui` for clickable local drill-down.

$ aiwatcher projects --days 7

AI usage by project - last 7 days
Cost is shown as API-equivalent value; subscription plans may differ.

  $8.39    2 sessions   576.0k tokens   ~/code/api-gateway
  $4.93    1 session    330.9k tokens   ~/code/data-sync
  $1.72    1 session    127.4k tokens   ~/code/web-app
  $0.67    2 sessions    62.5k tokens   ~/code/meeting-notes

The dashboard exposes a read-only JSON summary at /api/summary. The time-window selector updates the values, and project rows and recent sessions open into local drill-down. It is the first thing you would screenshot and show a teammate.

The privacy contract is the product

Local trust boundary

  • Local-only by default. Read-only.
  • No LLM API calls.
  • No phone-home telemetry.
  • No source-code or prompt-content storage in summaries.
  • No cloud upload unless you explicitly connect the paid tier.

If AIWatcher Local cannot explain what it reads and why, it should not read it.

What it reads

Claude Code

Reads ~/.claude/projects/**/*.jsonl, uses event-level working directory, and normalizes nested folders to the git project root when possible. The richest support today.

Codex CLI

Reads ~/.codex/state_5.sqlite in read-only mode when available. Support depends on local SQLite accessibility and schema shape.

Cursor

Detects local AI log activity where available. Cost and token detail is marked limited on purpose, because Cursor does not reliably expose it locally.

Cline

Detected when installed. Full session scanning isn't implemented yet — AIWatcher Local confirms Cline is present but doesn't extract session or cost detail from it today.

Windsurf

Detected when installed. Full session scanning isn't implemented yet — AIWatcher Local confirms Windsurf is present but doesn't extract session or cost detail from it today.

Breakdowns and local export

  • Project, tool, model, session, token, and API-equivalent value breakdowns.
  • A clear split between API-priced tokens and subscription or plan-limited tokens.
  • A local weekly report from the terminal.
  • Local JSON export for personal analysis, including privacy-safe event hashes.

Event exports include timestamps, models, token counts, API-equivalent value, project paths, event types, and content hashes. They do not include prompt text or source code.

Mark any session useful, rework, or abandoned with aiwatcher outcome — the record that closes the loop between what you did and what it was worth.

Local vs paid

AIWatcher Local answers

What are my local AI coding tools doing, where is usage growing, and what is the API-equivalent value before the invoice arrives?

The paid tier answers

What is our entire team's AI work doing, who is driving the biggest costs, and where are the risks before they become incidents?

AIWatcher Local is never gated behind signup. The paid tier builds on the same collector with team rollups, anomaly detection, cost attribution by team and customer, and integrations for the workflows engineering leaders already use.

Open source, install today.

AIWatcher Local ships as a separate package you run on your own machine. No account, no signup — just install it.