Conifer — run AI locally, route the rest

conifer
An ASCII luminance dither of a conifer, framed by a sun and moon. Hover with a pointer to ripple the characters along the row.

Works anywhere.

  • Claude Desktop
  • Codex Desktop
  • Antigravity
  • Terminal
  • cmux
  • VS Code
  • OpenCode
  • Pi
  • Zed
  • Cursor

Works with the cloud, self-hosted models, and your own hardware.

  1. Install the runtime

    curl -fsSL https://www.conifer.build/install-cli.sh | sh

  2. Bring your existing keys

    We support hundreds of vendors, and it’s free — we don’t charge a fee to bring your own key or run on your own hardware.

  3. Or run it on your own hardware

    Use any llama-compatible endpoint or our custom engine to deploy local models at no cost.

Dynamic query-based routing.

Visibility over your token costs.

  • A graphics card, drawn in ASCII.your hardwareweights resident on this machine
  • A rack of server nodes, drawn in ASCII.on prema box you own, in your building or on your LAN
  • A skeleton key, drawn in ASCII.your API keysOpenAI, Anthropic, OpenRouter
  • A towering cumulonimbus cloud, drawn in ASCII.the cloudmanaged, metered per token

one endpoint