ThinkWatchProject/ThinkWatch-Lite
Cross-platform local gateway that sits between AI coding clients and upstream LLM providers, routing requests and tracking usage.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
ThinkWatch Lite is a Tauri-based desktop application that acts as a local proxy between AI coding clients such as Claude Code and Codex and their upstream LLM providers. It allows users to switch upstreams and models without reconfiguring clients, redacts API keys before requests leave the machine, and blocks dangerous tool calls injected by relays. Every request is logged with token counts, cost, and routing information, providing observability and cost monitoring across macOS, Windows, and Linux.
Frequently asked
- What is ThinkWatchProject/ThinkWatch-Lite?
- Cross-platform local gateway that sits between AI coding clients and upstream LLM providers, routing requests and tracking usage.
- Is ThinkWatch-Lite open source?
- Yes — ThinkWatchProject/ThinkWatch-Lite is open source, released under the MIT license.
- What language is ThinkWatch-Lite written in?
- ThinkWatchProject/ThinkWatch-Lite is primarily written in TypeScript.
- How popular is ThinkWatch-Lite?
- ThinkWatchProject/ThinkWatch-Lite has 748 stars on GitHub.
- Where can I find ThinkWatch-Lite?
- ThinkWatchProject/ThinkWatch-Lite is on GitHub at https://github.com/ThinkWatchProject/ThinkWatch-Lite.