ThinkWatch-Lite
by ThinkWatchProject (organization)
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 request. (description from the project’s GitHub page)
Repository facts
- Stars
- 837
- Forks
- 14
- Open issues and pull requests
- 1
- Primary language
- TypeScript
- License
- MIT License (MIT)
- Owner
- ThinkWatchProject · Organization
- Created
- Sep 12, 2026
- Last push
- Oct 18, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 8,141: apache/casbin-gateway
See what every AI coding agent on your machine is doing, and whether the API behind it is the one you paid for. Claude Code, Codex, Cursor, Gemini CLI and more: one endpoint for 4…
643 starsGoApache-2.0Last push Oct 11, 2026
Rank 8,464: gglucass/headroom-desktop
Menu Bar App on MacOS and Windows that cuts Claude Code and Codex token costs by ~50%
606 starsRustMITLast push Oct 18, 2026
Rank 920: maximhq/bifrost
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing…
8,912 starsGoApache-2.0Last push Oct 18, 2026
Rank 8,126: mozilla-ai/otari
Open-source, OpenAI-compatible LLM gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
646 starsPythonApache-2.0Last push Oct 18, 2026
Rank 4,191: theopenco/llmgateway
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
1,690 starsTypeScriptOther licenseLast push Oct 18, 2026
Rank 469: lidge-jun/opencodex
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
17,563 starsTypeScriptMITLast push Oct 18, 2026