aimux (Python)
Unified LLM service layer for Python — one API for 325 AI providers (OpenAI, Anthropic, Google, Bedrock, Vertex, DeepSeek, …), powered by a Rust core.
Install
pip install arcships-aimux
Pre-built wheels for Linux, macOS, and Windows (Python ≥ 3.8). No Rust toolchain needed.
Quick start
from aimux import generate_text, openai
model = openai("sk-...", "gpt-4o")
result = generate_text(model, "Explain Rust ownership in one sentence.")
print(result["text"])
Features
- Unified interface — switch providers by changing one constructor
- Streaming — token-by-token output with cancellation
- Full modality coverage — text, embeddings, images, speech, transcription, video, reranking, files
- Fast — Rust core, zero GC pauses; benchmarked faster than the official OpenAI SDK in docs/PERF-RESULTS.md
Documentation
License
MIT
Metadata
Release files for arcships-aimux 0.5.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| arcships_aimux-0.5.0-cp38-abi3-win_amd64.whl | CPython 3.8 | abi3 | Windows x86-64 | Details for arcships_aimux-0.5.0-cp38-abi3-win_amd64.whl |
| arcships_aimux-0.5.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl | CPython 3.8 | abi3 | Linux glibc 2.17+ x86-64 | Details for arcships_aimux-0.5.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
| arcships_aimux-0.5.0-cp38-abi3-macosx_11_0_arm64.whl | CPython 3.8 | abi3 | macOS 11.0+ ARM64 | Details for arcships_aimux-0.5.0-cp38-abi3-macosx_11_0_arm64.whl |
Total release size: 20.3 MB
Release files / arcships_aimux-0.5.0-cp38-abi3-win_amd64.whl
| Download URL | arcships_aimux-0.5.0-cp38-abi3-win_amd64.whl |
|---|---|
| Size | 7.0 MB |
| Tags | CPython 3.8 Windows x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
8d0a610a43d63a63b008f394e7d1fd3b5ed6eb491f25ddca3f77d0126355bfab
|
|
BLAKE2b-256 checksum How to use checksums |
1f6c14f90cf3ef4df883967da6a43f1a92d1d4e60026fe2188e79d145f2f295a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
maturin/1.15.0
|
Release files / arcships_aimux-0.5.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | arcships_aimux-0.5.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 7.0 MB |
| Tags | CPython 3.8 Linux glibc 2.17+ x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
8d308336a24a5881fd634adf93347fe81dc4e2c0a6f801f462c9fe28c747cab2
|
|
BLAKE2b-256 checksum How to use checksums |
b84a0122d8ce44c5397a16f61dc8a3e3564ddc483ee78dd2d8f1631cfeb64094
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
maturin/1.15.0
|
Release files / arcships_aimux-0.5.0-cp38-abi3-macosx_11_0_arm64.whl
| Download URL | arcships_aimux-0.5.0-cp38-abi3-macosx_11_0_arm64.whl |
|---|---|
| Size | 6.3 MB |
| Tags | CPython 3.8 abi3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
df27b1e8dc39ec558a23d73f26178406b0b938148f3083d6757af666b0811c26
|
|
BLAKE2b-256 checksum How to use checksums |
01861efa22752c8ac44bb9f47b32251c380f91def073ff6a65a7ae6bbc2eb11f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
maturin/1.15.0
|
Security for arcships-aimux 0.5.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.