@axichuhai: There is an open-source project on GitHub that aggregates the free quotas of 12 major large model platforms into a single unified entry point. You just drop in your scattered API keys, and you can easily scoop up hundreds of millions of tokens. The usage is also very simple: 1. Clone it locally and open the admin panel. 2. Fill in your keys one by one. 3. Go to Playg…

There’s an open-source project on GitHub that unifies free-tier quotas from 12 major LLM platforms into a single entry point.

Just plug in your scattered API keys, and you can harvest billions of tokens for free.

Usage is simple:

1. Clone it locally, open the admin panel
2. Fill in your keys one by one
3. Send a test message in the Playground – it will show which model replied and the latency in ms

Once configured, copy the unified URL and API key, set priority for each model.

When a task arrives, it automatically polls models in order – if one hits rate limits, it jumps to the next until the job is done.

阿西_出海 (@axichuhai):
Found another open-source project that breaks information asymmetry – 58k stars on GitHub, frequently topping the trending page.

It aggregates hot topics from major mainstream media, summarizes them, and pushes them directly to your phone – supports DingTalk, Feishu, email, etc.

Supports translation, so overseas trending topics are covered too.

Just tell it what you want in natural language, no need to browse multiple platforms yourself.