Embodied AI Architect
A design environment for creating and evaluating autonomous agents, with hardware/software codesign space exploration and optimization.
Features
- Model Analysis: Analyze PyTorch model structure and compute requirements
- Hardware Profiling: Recommendations for edge/cloud deployment
- Multi-Hardware Benchmarking: Local CPU, remote SSH, Kubernetes backends
- Interactive Chat: Claude-powered architect for design decisions
- Codebase Analysis: Scan and assess application codebases for hardware deployment
- SoC Optimization: LangGraph-based RTL optimization loop (experimental)
Installation
pip install embodied-ai-architect
With optional dependencies:
# Remote SSH benchmarking
pip install embodied-ai-architect[remote]
# Kubernetes benchmarking
pip install embodied-ai-architect[kubernetes]
# Interactive chat (requires ANTHROPIC_API_KEY)
pip install embodied-ai-architect[chat]
# All optional dependencies
pip install embodied-ai-architect[all]
Usage
# Show available commands
branes --help
# Analyze a PyTorch model
branes analyze model.pt
# Run full workflow
branes workflow run model.pt
# Benchmark on local CPU
branes benchmark model.pt --backend local
# Scan and assess a codebase for hardware deployment
branes codebase scan /path/to/project
branes codebase assess /path/to/project --hardware jetson_orin
# Interactive chat session
export ANTHROPIC_API_KEY=your-key-here
branes chat
Environment Variables
| Variable | Description |
|---|---|
ANTHROPIC_API_KEY |
Required for Claude-powered features (chat, codebase analysis) |
Documentation
For full documentation, development setup, and contributing guidelines, visit the GitHub repository.
Related Projects
- embodied-schemas: Shared Pydantic schemas and hardware catalog
- graphs: Analysis tools and roofline models
License
MIT License
1 maintainer
Metadata
1 maintainer
Release files for embodied-ai-architect 1.17.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| embodied_ai_architect-1.17.0.tar.gz | 1.0 MB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| embodied_ai_architect-1.17.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.4 MB
Release files / embodied_ai_architect-1.17.0.tar.gz
| Download URL | embodied_ai_architect-1.17.0.tar.gz |
|---|---|
| Size | 1.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cdd366331ed8f2d384eec66ec1a5c402ee13b9273613a212bc3d797b1dee8c93
|
|
BLAKE2b-256 checksum How to use checksums |
bd2a8d52f2206171cf664075b740ddcdcd76cc54e46af7c7c3aaf832287b914a
|
| 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 Sep 18, 2026.
Transparency logRelease files / embodied_ai_architect-1.17.0-py3-none-any.whl
| Download URL | embodied_ai_architect-1.17.0-py3-none-any.whl |
|---|---|
| Size | 1.4 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
cacd57d98030c9323ae6fc24a207705c2001e912157157886f43c2e25e78cd2e
|
|
BLAKE2b-256 checksum How to use checksums |
7ef96de8df2dfbf27a5e973e84c68bf9815876ca86295beee5177e179e35ba65
|
| 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 Sep 18, 2026.
Transparency logSecurity for embodied-ai-architect 1.17.0
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for embodied_ai_architect-1.17.0.tar.gz
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 Sep 18, 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.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
