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

  1. InferenceEngine: Main entry point for inference operations
  2. NetworkMgr: Manages network connections (non-Ray version)
  3. ONNXInferenceEngine: Handles ONNX model loading and inference
  4. 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

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.37.1)

Owner

PyPI data
Data sourced directly from PyPI's database.

Credits

Author: Hunter Park

Requires

Python <3.13, >=3.10

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

amesa_inference-0.35.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.7 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.17+ x86-64

amesa_inference-0.35.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (2.7 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.17+ ARM64

amesa_inference-0.35.0-cp311-cp311-macosx_11_0_arm64.whl (418.9 kB view details)

Uploaded CPython 3.11macOS 11.0+ ARM64

amesa_inference-0.35.0-cp311-cp311-macosx_10_9_x86_64.whl (418.9 kB view details)

Uploaded CPython 3.11macOS 10.9+ x86-64

amesa_inference-0.35.0-cp311-cp311-macosx_10_9_universal2.whl (835.7 kB view details)

Uploaded CPython 3.11macOS 10.9+ universal2 (ARM64, x86-64)

amesa_inference-0.35.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.5 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.17+ x86-64

amesa_inference-0.35.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (2.5 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.17+ ARM64

amesa_inference-0.35.0-cp310-cp310-macosx_11_0_arm64.whl (421.1 kB view details)

Uploaded CPython 3.10macOS 11.0+ ARM64

amesa_inference-0.35.0-cp310-cp310-macosx_10_9_x86_64.whl (421.6 kB view details)

Uploaded CPython 3.10macOS 10.9+ x86-64

amesa_inference-0.35.0-cp310-cp310-macosx_10_9_universal2.whl (840.7 kB view details)

Uploaded CPython 3.10macOS 10.9+ universal2 (ARM64, x86-64)

File details

Details for the file amesa_inference-0.35.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 b8e5f8bf3be9f3a2897d69d9efbed97f98ab2c91bc11634dd55a58838f51026a
MD5 4bb19a08416591883a00a6f125811e87
BLAKE2b-256 56aabc8c20eb06eee144357a3e194d93c15fcca57f250efcddc6effc9acd6423

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 59e79a34438edd0500b98cdd358bd022a6b294731f5e07414e3920400149d6a7
MD5 9b34aa3f4a33e647b32da97b13f5c475
BLAKE2b-256 486f615a05a0877f7e790bef6783b444cfec9b5406a08272f9a021f6350df5e8

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp311-cp311-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp311-cp311-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 08bd4c5894b43262bffa4c140c8923d0eee09f6cf71f587483cdeefeeb184ce0
MD5 174faf2ca3daca60ae651f451e9cf091
BLAKE2b-256 fc123bae61ad7a0be38ae3bb01cacd7e26ffc78952df5a142a9a2521056b46f2

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp311-cp311-macosx_11_0_arm64.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp311-cp311-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp311-cp311-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 daedd8799da390ec86e7caaa011799923fd9f9b297af9e0156fae51c0a7efb24
MD5 9c1faac48d01bab59bc826efb242a295
BLAKE2b-256 78e6f221e413d5c78a1580c3857705b3f9e92e404ac87608f1f6c44554a0591a

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp311-cp311-macosx_10_9_x86_64.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp311-cp311-macosx_10_9_universal2.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp311-cp311-macosx_10_9_universal2.whl
Algorithm Hash digest
SHA256 523350904a2fcf6a4480064c251270719a53945628e7356cf8f70b56fa4ad319
MD5 dfe266b0277b694e5770272b85a0885e
BLAKE2b-256 897517afe10a1ff59f900149ba0a0817e9a39eec1f1d33d0f0ce5ba2cc078e17

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp311-cp311-macosx_10_9_universal2.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 e34013db5d194addbff301aa46ef5c0a818ca282678ee35a95413cc6513eccc4
MD5 5d58a3879b64c3888d3af3ea5a6d1708
BLAKE2b-256 9e985bbbdcb97f2306b5adf0b227c939c5a1d626935281fe4c0510c8246c1f92

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 2b3c1a254dcd6ddeb30311c7b207ed7f2a1327e6c57a5859fa2ad21325bbed71
MD5 0e41ee42e1e23be3fca7babaeadcac41
BLAKE2b-256 4b14280fa14193403648d0025367f87c1b9e3f11c55037aa5213305f665d42f8

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp310-cp310-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp310-cp310-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 0edefc680cc40f2682b26a6c1e63e766691bd6acc06c3c089788cbd40ee8e102
MD5 3e342f82b1c04c5c0accbc0cd20749e7
BLAKE2b-256 863cabb81b00f1af8349d0886b43a5d43db32a834d141b450afd47f05e1cbf26

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp310-cp310-macosx_11_0_arm64.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp310-cp310-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp310-cp310-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 3e0316de314f5dd175135eb0a4e2f636fe502d54a83636119ff170eb395cb247
MD5 3613f3680ceac43a5162c41e157b7e2a
BLAKE2b-256 005baa0bb98f0627d1e76cbaf992a5c2fa013913cfe6c65b90683e4f23b1645d

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp310-cp310-macosx_10_9_x86_64.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file amesa_inference-0.35.0-cp310-cp310-macosx_10_9_universal2.whl.

File metadata

File hashes

Hashes for amesa_inference-0.35.0-cp310-cp310-macosx_10_9_universal2.whl
Algorithm Hash digest
SHA256 43889d3884bab86b4df61f26366d2e698fe73e19c71aa2f7c27531997f78afdb
MD5 e06e885ae6091d6af8169a6252c54e8f
BLAKE2b-256 14964df31a19a36d179b0a47eaf0dc2fd5ac5d81ce10b04abf2f0a495cde70ea

See more details on using hashes here.

Provenance

The following attestation bundles were made for amesa_inference-0.35.0-cp310-cp310-macosx_10_9_universal2.whl:

Publisher: build-and-publish-package.yaml on Composabl/sdk.composabl.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.37.1

10 files

0.37.0

10 files

0.36.1

10 files

0.36.0

10 files

0.35.2

10 files

0.35.1

10 files

This release

0.35.0 This release

10 files

0.34.1

10 files

0.34.0

10 files

0.33.2

10 files

0.33.1

10 files

0.33.0

10 files

0.31.0

10 files

0.30.0

10 files

0.29.1

10 files

0.29.0

10 files

0.28.0

10 files

0.27.0

10 files

0.26.0

10 files

0.25.0

10 files

0.24.0

10 files

0.22.0

10 files

0.21.0

10 files

0.20.0

10 files

0.19.7

10 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page