Software you
own outright.

Every drop replaces a subscription you are already paying for. Clone it, point it at a model you own, and keep it.

The drops

Software you can actually own.

View all

Configuration

Bring your own everything.

Every drop reads the same three variables. Drop 001 and drop 100 take identical config, so you set this up once and never think about it again.

  • You do not need a GPU. The default is a free hosted model — no download, no credit card, about a minute to get a key.
  • There is no keyless free model. Every hosted provider rejects unauthenticated requests — checked, not assumed. Free means free of charge, not free of signup.
  • Free tiers are smaller than they look. Measured: OpenRouter gives 50 requests a day on :free models. A 10-slide deck spends eleven.
Read the setup
.env
LLM_BASE_URL=https://openrouter.ai/api/v1
LLM_MODEL=google/gemma-4-26b-a4b-it:free
LLM_API_KEY=                    # free key, no card

Anything speaking the OpenAI chat-completions shape works — Ollama, LM Studio, llama.cpp, vLLM, OpenRouter, Groq, Together, Cerebras, Google AI Studio, OpenAI itself.

On the block

Subscriptions with a replacement coming.

  • Perplexity
  • Cursor
  • Wispr Flow
  • Rize
  • Opal
  • Napkin
  • Granola
  • Superhuman
  • Otter
  • every screentime app charging a subscription to turn off notifications
Nominate a target