Amesa Inference
A lightweight inference package for running Amesa agents using ONNX models without Ray or PyTorch dependencies.
Overview
composabl_inference provides a standalone inference engine for running trained Amesa agents. It uses ONNX Runtime for model inference, making it suitable for deployment scenarios where you want to avoid heavy dependencies like Ray and PyTorch.
Features
- ONNX-based inference: Uses ONNX Runtime for efficient model inference
- No Ray or PyTorch dependencies: Lightweight package suitable for production deployment
- Network management: Supports both local and remote objects (agents, perceptors, controllers)
- Compatible API: Similar interface to
Trainer.package()for easy migration
Installation
pip install amesa-inference
Usage
Basic Inference
from composabl_inference import InferenceEngine
from composabl_core import Agent
# Create inference engine (only license needed for license validation)
engine = InferenceEngine(license="your-license-key")
# Load agent
agent = Agent.load("path/to/agent")
await engine.load_agent(agent)
# Package agent for inference (similar to Trainer.package())
await engine.package()
# Run inference
observation = {...} # Your observation from the simulator
action = engine.execute(observation)
With Remote Objects
The inference engine supports remote agents, perceptors, and controllers, just like the Trainer:
from composabl_inference import InferenceEngine
# Optional: provide custom config for NetworkMgr (e.g., for remote targets)
config = {
"target": {
"local": {
"address": "localhost:1337",
},
},
}
engine = InferenceEngine(license="your-license-key", config=config)
await engine.load_agent("path/to/agent")
await engine.package()
# The agent processor will automatically handle remote objects
action = engine.execute(observation)
Cleanup
# Clean up resources
await engine.close()
Architecture
Components
- InferenceEngine: Main entry point for inference operations
- NetworkMgr: Manages network connections (non-Ray version)
- ONNXInferenceEngine: Handles ONNX model loading and inference
- ONNXAgentProcessor: Processes agents using ONNX models instead of PyTorch
Differences from Trainer
- Uses ONNX Runtime instead of PyTorch for model inference
- NetworkMgr is not a Ray actor (runs in the same process)
- No Ray initialization required
- Lighter weight, suitable for production deployment
Requirements
- Python >= 3.10
- composabl-core
- composabl-api
- onnxruntime
- numpy
License
Proprietary and confidential - Copyright (C) Amesa, Inc
Metadata
Release files for amesa-inference 0.41.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
Total release size: 14.3 MB
Release files / amesa_inference-0.41.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | amesa_inference-0.41.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 2.8 MB |
| Tags | CPython 3.11 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
6043d1f9b9a8fe953da12159bb2213a2add29349b4e1995b253a4eae48dca42f
|
|
BLAKE2b-256 checksum How to use checksums |
e5b2adafb5e116a59fdcd770298b2d56dc8a8223fffcca5d1a21c039d18880c3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
| Download URL | amesa_inference-0.41.9-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl |
|---|---|
| Size | 2.8 MB |
| Tags | CPython 3.11 Linux glibc 2.17+ ARM64 |
|
SHA-256 checksum How to use checksums |
c98eade485d65c1a73b74b2631da79a42189d70d3b20125ab946cc9adf7252bb
|
|
BLAKE2b-256 checksum How to use checksums |
569a527861ac8ce1efb0bad686bb6d38a5d03d0199cb25b1646f3f606ee1f561
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp311-cp311-macosx_11_0_arm64.whl
| Download URL | amesa_inference-0.41.9-cp311-cp311-macosx_11_0_arm64.whl |
|---|---|
| Size | 433.6 kB |
| Tags | CPython 3.11 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
0c56e2f834f2d9f712978560793fd9b3c0e1993c37b4f48a31db6cfc4e9edc1d
|
|
BLAKE2b-256 checksum How to use checksums |
42c32f6493c2acacf42a46a915e24ac71dd8dd73153d3fe0253633e8dd67708d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp311-cp311-macosx_10_9_x86_64.whl
| Download URL | amesa_inference-0.41.9-cp311-cp311-macosx_10_9_x86_64.whl |
|---|---|
| Size | 436.4 kB |
| Tags | CPython 3.11 macOS 10.9+ x86-64 |
|
SHA-256 checksum How to use checksums |
3060679ade21d57ea5539250eadc8ed59b628311567b3a35080aa8060270ddcd
|
|
BLAKE2b-256 checksum How to use checksums |
83c8b98cc32d4b31a1b238d8cf85a74bb1a8b89f03e999248c45b1389b312782
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp311-cp311-macosx_10_9_universal2.whl
| Download URL | amesa_inference-0.41.9-cp311-cp311-macosx_10_9_universal2.whl |
|---|---|
| Size | 868.5 kB |
| Tags | CPython 3.11 macOS 10.9+ universal2 (ARM64, x86-64) |
|
SHA-256 checksum How to use checksums |
df1853769efb49f4f582cc0310da81b6d84838092f3a1d62d9c521d79f4ff6ac
|
|
BLAKE2b-256 checksum How to use checksums |
260d14ed53cd2afb87fcf893d16bac1fde357e6fcc5d726a476514ff1ccddd88
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | amesa_inference-0.41.9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 2.6 MB |
| Tags | CPython 3.10 Linux glibc 2.17+ x86-64 |
|
SHA-256 checksum How to use checksums |
57cef10083e9a5644d5e7c786cd886e4d89a9580cf9ae1192bd521e7375d6dce
|
|
BLAKE2b-256 checksum How to use checksums |
e8d7fd3c47b17e388be8b0ae96ee89508868ce5f4f24aa227669949183a128c2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
| Download URL | amesa_inference-0.41.9-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl |
|---|---|
| Size | 2.6 MB |
| Tags | CPython 3.10 Linux glibc 2.17+ ARM64 |
|
SHA-256 checksum How to use checksums |
b0efff62d3720984e4c9788776862ece87875bea95c4cd10954baaad8f975a0d
|
|
BLAKE2b-256 checksum How to use checksums |
0da5f0ef7fb874098e55335b411a0464000d5cbefe3f1c6478e2b5239293e390
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp310-cp310-macosx_11_0_arm64.whl
| Download URL | amesa_inference-0.41.9-cp310-cp310-macosx_11_0_arm64.whl |
|---|---|
| Size | 438.0 kB |
| Tags | CPython 3.10 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
ef8dd205585936c1a5f0d65d86a24c6113ec865f7e7a467729db0c0f2e5e3611
|
|
BLAKE2b-256 checksum How to use checksums |
e519aa30ad3f83b77b807e95a2b401f4dc23779039e5a4bfdeca7a68c6352a8e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp310-cp310-macosx_10_9_x86_64.whl
| Download URL | amesa_inference-0.41.9-cp310-cp310-macosx_10_9_x86_64.whl |
|---|---|
| Size | 441.3 kB |
| Tags | CPython 3.10 macOS 10.9+ x86-64 |
|
SHA-256 checksum How to use checksums |
413cdfbe082d15a2187b157ca3f962085d023b0f031debad2d97d1fc4e1b86f6
|
|
BLAKE2b-256 checksum How to use checksums |
9a3843f4899518c4cdfcc7541b0838b96ebe2ea1efd71b60a492e11361635b0f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / amesa_inference-0.41.9-cp310-cp310-macosx_10_9_universal2.whl
| Download URL | amesa_inference-0.41.9-cp310-cp310-macosx_10_9_universal2.whl |
|---|---|
| Size | 877.8 kB |
| Tags | CPython 3.10 macOS 10.9+ universal2 (ARM64, x86-64) |
|
SHA-256 checksum How to use checksums |
c8b61bf70c80fbd756c033d392e92e4a106d6872a0ddb7f68b9d01f2b7e0f5f1
|
|
BLAKE2b-256 checksum How to use checksums |
f5fca0eef597a02c42cfb6233e9d1d8fc78db894dcfe2a85f53bf56d48df3b29
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logSecurity for amesa-inference 0.41.9
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.
Full provenance
All 10 files in this release have been uploaded with provenance metadata.
Attestation for amesa_inference-0.41.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logA 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.
