Metadata-Version: 2.5
Name: tracevox-ai
Version: 0.2.0
Summary: TraceVox Research CLI and compute runner — run agent experiments on your own compute; observe, replay, and reproduce the evidence.
Project-URL: Homepage, https://tracevox.ai
Project-URL: Documentation, https://tracevox.ai/research/docs
Project-URL: Public Research, https://tracevox.ai/research
Author: TraceVox Research
License-Expression: Apache-2.0
Keywords: adversarial-robustness,agents,reinforcement-learning,reproducibility,research
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Requires-Dist: requests>=2.28
Provides-Extra: all
Requires-Dist: gymnasium>=0.29; extra == 'all'
Requires-Dist: minigrid>=2.3; extra == 'all'
Requires-Dist: numpy>=1.24; extra == 'all'
Requires-Dist: pyyaml>=6.0; extra == 'all'
Requires-Dist: tensorboard>=2.14; extra == 'all'
Requires-Dist: torch>=2.0; extra == 'all'
Requires-Dist: tyro>=0.8; extra == 'all'
Provides-Extra: dev
Requires-Dist: build>=1.0; extra == 'dev'
Requires-Dist: pytest>=7.0; extra == 'dev'
Provides-Extra: minigrid
Requires-Dist: gymnasium>=0.29; extra == 'minigrid'
Requires-Dist: minigrid>=2.3; extra == 'minigrid'
Requires-Dist: numpy>=1.24; extra == 'minigrid'
Provides-Extra: rl
Requires-Dist: gymnasium>=0.29; extra == 'rl'
Requires-Dist: minigrid>=2.3; extra == 'rl'
Requires-Dist: numpy>=1.24; extra == 'rl'
Requires-Dist: tensorboard>=2.14; extra == 'rl'
Requires-Dist: torch>=2.0; extra == 'rl'
Requires-Dist: tyro>=0.8; extra == 'rl'
Provides-Extra: yaml
Requires-Dist: pyyaml>=6.0; extra == 'yaml'
Description-Content-Type: text/markdown

# tracevox-ai

TraceVox Research CLI and compute runner. TraceVox is a visual, reproducible
research environment for studying intelligent agents — reinforcement
learning, trustworthy AI, multimodal agents, adversarial robustness.
**Observable · Reproducible · Adversarial.**

The browser is the research control and visualization layer; **this package
is the compute layer**: it executes typed research jobs (train / evaluate /
sweep / export) on your own hardware — laptop, workstation, lab GPU server,
or cluster node — and streams evidence to a TraceVox control plane (hosted,
institution-hosted, or fully local/offline).

```bash
pip install tracevox-ai            # CLI + runner agent
pip install "tracevox-ai[rl]"      # + PyTorch/Gymnasium/MiniGrid for RL work

tracevox doctor                    # readable environment health report
tracevox connect --code <code>     # pair with a TraceVox control plane
tracevox runner start              # accept typed research jobs
```

Headless/HPC use needs no browser:

```bash
tracevox experiment run experiment.json
tracevox experiment export --experiment-id exp_…
tracevox experiment reproduce --experiment-id exp_…   # new lineage, original untouched
```

Security model: the runner connects **outbound-only** (no inbound ports),
pairing codes are one-time and short-lived, runner tokens are hashed at rest
and revocable, and jobs are **typed research requests** validated locally
against registered environments/algorithms — there is no arbitrary-command
job, so a TraceVox server can never execute arbitrary code on your machine.

Explore published research without installing anything:
https://tracevox.ai/research — machine-readable docs at
https://tracevox.ai/llms.txt.
