We believe the intelligence singularity is already here, just in pieces. Every new model, provider, and harness arrives with its own keys, its own billing, and its own setup, and your code knows about none of it. Holding it together lands on whoever is trying to get work done.

Conifer is the inference gateway: many models, many providers, and many machines on one side, one OpenAI- or Anthropic-compatible endpoint on the other. Routing decides where each request runs: the cheapest path, the fastest response, or never leaving your machine.