Combs Engine — local-first AI inference CLI (Rust GPU core). Installs the prebuilt `combs` binary for your platform.
Project description
combs-engine (PyPI)
Installs the prebuilt combs CLI
binary for your platform (macOS arm64/x86_64, Linux x86_64, Windows x86_64).
pip install combs-engine
combs devices
combs run --model <path-or-gguf> --prompt "Hello" --chat
combs chew chat-ui my-app --yes # scaffold + install + launch a chat UI
combs serve --model <path> --port 8080
On first run the binary is fetched from the matching GitHub Release into
~/.cache/combs/bin (override with COMBS_HOME). CI-built platform wheels
bundle the binary directly, so no download is needed for those.
| Env var | Effect |
|---|---|
COMBS_BIN |
Use an existing combs binary |
COMBS_HOME |
Override the cache directory (default ~/.cache/combs) |
COMBS_RELEASE_REPO |
Override the GitHub repo releases are fetched from |
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file combs_engine-0.2.0.tar.gz.
File metadata
- Download URL: combs_engine-0.2.0.tar.gz
- Upload date:
- Size: 3.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.11.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e2848e9781a5b0f7e01f5fe358ac1f4e9743da0568de1f52d700f2a39cc1d9cf
|
|
| MD5 |
fb0572374b343ad323b37b10ca1cb3f3
|
|
| BLAKE2b-256 |
900846966be32fb53e3a1092f2dc0e32c3a720d557bc998f5b4f38ef88bafc80
|
File details
Details for the file combs_engine-0.2.0-py3-none-any.whl.
File metadata
- Download URL: combs_engine-0.2.0-py3-none-any.whl
- Upload date:
- Size: 4.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.11.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b520f41ae8d7765e64779b4593c28b1e7cd325991b597314de2a020095d4a47d
|
|
| MD5 |
727780ca0e5fc5f49053c9f3fcda6103
|
|
| BLAKE2b-256 |
3bbc8c1f592973bef418fcf2d5d16ac9eb7ffed02aa87295e413ad8730cc1b5d
|
