Serves local language models from a native Zig binary on Apple Silicon and NVIDIA GPUs with OpenAI- and Anthropic-compatible APIs, for developers running models on their own hardware.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Verified Model Downloads
Use TensorFold to download qualified checkpoints into the Hugging Face cache: ‹what you need›
- Context Compaction
Use TensorFold to compact overflowing conversations into a memory note: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: tensorfold.dev
Call the API
Auth None needed
Its page: tensorfold.dev
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLI
- Auth
- None
- Skills
- 3
Skills
OpenAI and Anthropic Compatible Serving
Serves chat completions, completions, Responses, and Anthropic Messages endpoints from a local /v1 API.
Verified Model Downloads
Downloads qualified checkpoints into the Hugging Face cache with resumable, checksum-verified transfers.
Context Compaction
Compacts overflowing conversations into a memory note while keeping the system prompt and recent turns verbatim.