ThinkWatch-Lite — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ThinkWatchProject · Claude Skill · ★ 985

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is ThinkWatch-Lite safe to install? View the security audit →

About ThinkWatch-Lite

ThinkWatch Lite English | 中文 ThinkWatch Lite is a desktop app for macOS, Windows and Linux that runs an AI API gateway on the local machine. Claude Code, Codex and other clients of the OpenAI and Anthropic APIs send their requests through it, and the app records what each request cost, which upstream served it and which keys were redacted before it was sent. The gateway can also be deployed on a server; the app then connects to ThinkWatch Core on that server over an encrypted control channel. <img src="docs/screenshots/en/overview-light.png" alt="The overview for the last seven days: tokens, cost and requests against the seven days before, with

ai-gatewayanthropicclaude-codecodexcost-monitoringcost-trackingcross-platformlinuxllm-costllm-gateway

Quick Facts

Stars985
Forks12
LanguageTypeScript
CategoryClaude Skill
LicenseMIT
Quality Score70.9352916466306/100
Last Updated2026-10-03
Created2026-09-12
Platformsclaude-code, cli, codex, node
Est. Tokens~22k

ThinkWatch-Lite alternative? Top 6 similar tools

Looking for a ThinkWatch-Lite alternative? If you're comparing ThinkWatch-Lite with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • octopus by bestruirui · ⭐ 2.7k

    One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关

  • llmgateway by theopenco · ⭐ 1.7k

    Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

  • agent-sessions by jazzyalex · ⭐ 889

    Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across

  • dario by askalf · ⭐ 558

    Use your Claude and ChatGPT subscriptions in Cursor, Cline, Aider, Claude Code and the Agent SDK: one local en

  • ccproxy by starbaser · ⭐ 350

    Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligen

  • claude-notifications-go by 777genius · ⭐ 806

    🔔 Cross-platform smart notifications plugin for Claude Code. 6 types. Click-to-focus (many terminal). 1 line

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is ThinkWatch-Lite?

ThinkWatch-Lite is Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every r. It is categorized as a Claude Skill with 985 GitHub stars.

What programming language is ThinkWatch-Lite written in?

ThinkWatch-Lite is primarily written in TypeScript. It covers topics such as ai-gateway, anthropic, claude-code.

How do I install or use ThinkWatch-Lite?

You can find installation instructions and usage details in the ThinkWatch-Lite GitHub repository at github.com/ThinkWatchProject/ThinkWatch-Lite. The project has 985 stars and 12 forks, indicating an active community.

What license does ThinkWatch-Lite use?

ThinkWatch-Lite is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ThinkWatch-Lite?

The top alternatives to ThinkWatch-Lite on Agent Skills Hub include octopus, llmgateway, agent-sessions. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools