AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Observability/
codex-usage-tracker
codex-usage-tracker logo

codex-usage-tracker

Active·★ 196·MIT·Updated 2026-10-14
★ Hidden Gem

Codex Usage Tracker is a local-first tool that provides a dashboard, CLI, and companion plugin for analyzing OpenAI Codex token usage and costs. It reads local log files, indexes usage data into SQLite, and helps developers understand where their credits are being spent.

#Codex Usage Tracking#Token Management#Analytics Dashboard#LLM Observability
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
#Local-first
#Python CLI
#SQLite Database
#Plugin Integration
$ Install
$ python -m pip install --user pipx && python -m pipx ensurepath && pipx install codex-usage-tracking && codex-usage-tracker setup
↗ Visit site★ GitHub
01

Features

01Local-first dashboard with live refresh and various views (Overview, Calls, Threads, Diagnostics).
02Indexes aggregate usage counters and local content evidence into an SQLite database.
03Provides CLI for summaries, queries, CSV export, and support bundles.
04Companion Codex plugin and skills for conversational usage analysis and waste discovery.
05Supports localized UI text for the dashboard, including Simplified Chinese.
02

Compatibility

Python
Runtime
Verified via docs
Ubuntu
OS
Verified via docs
macOS
OS
Verified via docs
Windows
OS
Verified via docs
Docker
Container
Verified via docs
03

Quick start

1
$ python -m pip install --user pipx
2
$ python -m pipx ensurepath
3
$ pipx install codex-usage-tracking
4
$ codex-usage-tracker setup
04

Use cases

↳Track and analyze OpenAI Codex token usage and estimated costs locally without uploading logs.
↳Identify threads, models, or subagents that consume the most tokens and contribute to unexpected costs.
↳Optimize usage by identifying high-context, low-cache calls and understanding context bloat in long chats.
↳Use the companion Codex skill to converse with usage data, ask questions, and get recommendations for reducing token waste.
05

Alternatives

⚡Top VS:
VSpreflight★65→VSgeo-score★32→VSyavio★31→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
bar-observatory
★24
→
preflight logo
preflight★ 65
Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.
VSCompare→
geo-score logo
geo-score★ 32
Can AI engines cite your site, and do they? Free 0–100 readiness score on an open GEO rubric, plus ask and weekly citation tracking via OpenAI, Perplexity, Gemini, Anthropic and OpenRouter with your own keys. Zero dependencies; CLI, GitHub Action and MCP server.
VSCompare→
yavio logo
yavio★ 31
The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
VSCompare→
bar-observatory logo
bar-observatory★ 24
Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.
VSCompare→
finopsmcp logo
finopsmcp★ 19
FinOps MCP server for Claude and Cursor. Ask nable about your AWS, Azure, GCP, Kubernetes, and SaaS/AI spend, get savings priced on your real rates, and fixes as PRs you approve. Open source, local-first.
VSCompare→
llmkit logo
llmkit★ 15
Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.
VSCompare→
engrim logo
engrim★ 299
The Universal Cross-Model Episodic Memory Standard. Local-first, project-scoped SQLite engine for Google Antigravity, Claude Code, Cursor, Codex CLI, and OpenCode. Zero cloud lock-in.
VSCompare→
MemWhale logo
MemWhale★ 148
Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.
VSCompare→
See all alternatives →
douglasmonsky /
codex-usage-tracker
↗

Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.

196MIT
Last commit1w ago
StatusActive
CategoryObservability
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit