inspect-robots 0.3.1__tar.gz

inspect_robots-0.3.1/.gitignore

@@ -0,0 +1,221 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer,
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# uv lockfile (this is a library; CI resolves from pyproject)
+uv.lock

inspect_robots-0.3.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 robocurve
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

inspect_robots-0.3.1/PKG-INFO

@@ -0,0 +1,209 @@
+Metadata-Version: 2.4
+Name: inspect-robots
+Version: 0.3.1
+Summary: The Inspect AI for robotics — an evaluation framework for VLA (vision-language-action) models across real robots and simulators.
+Project-URL: Homepage, https://github.com/robocurve/inspect-robots
+Project-URL: Documentation, https://inspectrobots.org/
+Project-URL: Repository, https://github.com/robocurve/inspect-robots
+Project-URL: Issues, https://github.com/robocurve/inspect-robots/issues
+Author: Inspect Robots contributors
+License-Expression: MIT
+License-File: LICENSE
+Keywords: benchmark,embodied-ai,evaluation,physical-ai,robotics,vision-language-action,vla
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: numpy>=1.24
+Provides-Extra: all
+Requires-Dist: rerun-sdk>=0.20; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: mypy>=1.11; extra == 'dev'
+Requires-Dist: numpy<2.5; extra == 'dev'
+Requires-Dist: pre-commit>=3.5; extra == 'dev'
+Requires-Dist: pytest-cov>=5.0; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff>=0.6; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: mkdocs-llmstxt>=0.2; extra == 'docs'
+Requires-Dist: mkdocs-material>=9.5; extra == 'docs'
+Requires-Dist: mkdocs>=1.6; extra == 'docs'
+Requires-Dist: mkdocstrings[python]>=0.26; extra == 'docs'
+Provides-Extra: rerun
+Requires-Dist: rerun-sdk>=0.20; extra == 'rerun'
+Provides-Extra: viz
+Requires-Dist: rerun-sdk>=0.20; extra == 'viz'
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+# 🤖 Inspect Robots
+
+### The [Inspect AI](https://inspect.aisi.org.uk/) for robotics
+
+**An open-source evaluation framework for physical AI and VLA (vision-language-action) models.**
+
+Define a robotics benchmark once, then run *any* policy against *any* compatible
+embodiment — a real robot or a simulator — with reproducible logs and first-class
+[Rerun](https://github.com/rerun-io/rerun) visualization.
+
+[![CI](https://github.com/robocurve/inspect-robots/actions/workflows/ci.yml/badge.svg)](https://github.com/robocurve/inspect-robots/actions/workflows/ci.yml)
+[![Docs](https://github.com/robocurve/inspect-robots/actions/workflows/docs.yml/badge.svg)](https://inspectrobots.org/)
+[![Python](https://img.shields.io/badge/python-3.10%E2%80%933.13-blue)](https://github.com/robocurve/inspect-robots)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+[![Typed](https://img.shields.io/badge/typed-mypy%20strict-blue)](https://github.com/robocurve/inspect-robots)
+[![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen)](https://github.com/robocurve/inspect-robots/actions/workflows/ci.yml)
+
+[**Documentation**](https://inspectrobots.org/) ·
+[Quickstart](https://inspectrobots.org/guide/quickstart.html) ·
+[Concepts](https://inspectrobots.org/guide/concepts.html) ·
+[For LLMs](https://inspectrobots.org/llms.txt)
+
+</div>
+
+---
+
+## One framework, two swappable inputs
+
+LLM evaluations have a single swappable input: the model. **Robotics evaluations
+have two** — and Inspect Robots makes both first-class and orthogonal:
+
+| | |
+|---|---|
+| 🧠 **`Policy`** — the VLA | The "brain". Maps an observation + instruction to an **action chunk** (a horizon of actions executed open-loop, as π0 / ACT / diffusion policies do). |
+| 🦾 **`Embodiment`** — the robot or sim | The "body + world". Produces observations, executes actions, owns the action/observation spaces and control rate. Real-robot-first; sims are a stricter special case. |
+
+A **`Task`** — a dataset of `Scene`s (initial conditions, instructions, success
+targets) plus scorers — is defined *independently* of both. Before any rollout,
+Inspect Robots checks the `(policy, embodiment)` pair is **compatible** (action/observation
+spaces, semantics, control rate, scene realizability) and fails fast if not.
+
+## Install
+
+```bash
+pip install inspect-robots            # core (numpy only)
+pip install "inspect-robots[rerun]"   # + Rerun visualization
+```
+
+## Quickstart
+
+With a default policy/embodiment configured once in
+`~/.config/inspect-robots/config.ini`, just tell the robot what to do:
+
+```bash
+inspect-robots "place the spoon on the plate"                # zero-config ad-hoc eval
+inspect-robots "place the spoon on the plate" --sim          # same, on your configured sim
+```
+
+The full command line resolves any registered task/policy/embodiment
+(builtins + installed plugins):
+
+```bash
+inspect-robots list                                          # registered components
+inspect-robots run --task cubepick-reach --policy scripted --embodiment cubepick
+inspect-robots inspect logs/cubepick-reach_*.json            # results table
+```
+
+And everything is a Python API. No hardware or simulator needed — the
+dependency-free `CubePick` mock world exercises the whole stack:
+
+```python
+from inspect_robots import eval
+from inspect_robots.mock import CubePickEmbodiment, ScriptedPolicy
+from inspect_robots.scene import Scene
+from inspect_robots.scorer import success_at_end
+from inspect_robots.task import Task
+
+task = Task(
+    name="cubepick-reach",
+    scenes=[Scene(id=f"layout-{i}", instruction="reach the cube", init_seed=i) for i in range(5)],
+    scorer=success_at_end(),
+    max_steps=80,
+)
+
+# The two swappable inputs: a policy (VLA) and an embodiment (robot/sim).
+(log,) = eval(task, ScriptedPolicy(), CubePickEmbodiment())
+print(log.status, log.results.metrics)   # success {'success_at_end': 1.0}
+```
+
+## Why Inspect Robots
+
+- 🌍 **Real-world first.** Interfaces assume real-robot reality — human-in-the-loop
+  reset, no privileged success oracle, wall-clock control rate. Simulators just
+  offer more (seeding, privileged success, rendering) via opt-in capabilities.
+- 🔁 **Reproducible.** Every run yields an immutable, schema-versioned `EvalLog`
+  with the resolved config, git revision, and package versions — re-readable across
+  releases, and re-scorable offline.
+- 🪶 **Light core.** Depends only on NumPy. Rerun and simulator/VLA backends are
+  optional extras and separately installable plugins.
+- 🛑 **Safe unattended.** An explicit error taxonomy separates "record and continue"
+  from "halt and require a human", so a faulted robot never auto-advances overnight.
+- 🎞️ **Rerun visualization.** Stream camera images, 3D poses, joint/action
+  time-series, and success markers to a `.rrd` recording.
+- 🧩 **Pluggable.** Ship `inspect-robots-maniskill` or `inspect-robots-openvla` as separate
+  packages — entry points make them appear in `inspect-robots list` automatically.
+- ⚙️ **VLA-native.** Action chunking, open-loop execution, and ACT/ALOHA temporal
+  ensembling are built in, with action *semantics* (control mode, rotation
+  representation, gripper, frame) that make compatibility and ensembling correct.
+
+## How it maps to Inspect AI
+
+If you know [Inspect AI](https://inspect.aisi.org.uk/), you already know Inspect Robots.
+
+| Inspect AI | Inspect Robots |
+|---|---|
+| `Model` | `Policy` (VLA) **+** `Embodiment` *(two inputs)* |
+| `Task = dataset + solver + scorer` | `Task = scenes + controller + scorer` |
+| `Sample` | `Scene` |
+| `Solver` chain | `Controller` middleware (chunking, ensembling, smoothing) |
+| `eval()` → `EvalLog` | `eval()` → `EvalLog` |
+| `@task` / `@solver` / `@scorer` + registry | `@task` / `@policy` / `@embodiment` / `@scorer` + entry points |
+
+This repository is the **framework** (the "Inspect AI for robotics"). Concrete
+benchmarks (the "Inspect Evals for robotics") and backend adapters live in
+separate plugin packages.
+
+## Documentation
+
+Full guides and an auto-generated API reference live at
+**[inspectrobots.org](https://inspectrobots.org/)**.
+LLM-friendly versions: [`llms.txt`](https://inspectrobots.org/llms.txt)
+and [`llms-full.txt`](https://inspectrobots.org/llms-full.txt).
+
+## Development
+
+```bash
+uv venv && uv pip install -e ".[dev]"
+uv run pre-commit install          # ruff + mypy on commit, 100% coverage on push
+uv run pytest --cov                 # 100% coverage required
+uv run ruff check . && uv run mypy
+```
+
+Pre-commit hooks and a blocking CI coverage gate keep `main` green. See
+[`CONTRIBUTING.md`](CONTRIBUTING.md) and the design docs in [`plans/`](plans/).
+
+## Citation
+
+If you use Inspect Robots in your research, please cite it:
+
+```bibtex
+@software{inspect-robots,
+  author  = {Robocurve},
+  title   = {Inspect Robots: The open-source evaluation framework for physical AI},
+  year    = {2026},
+  url     = {https://github.com/robocurve/inspect-robots},
+  version = {0.3.0},
+  license = {MIT}
+}
+```
+
+## License
+
+[MIT](LICENSE)

inspect_robots-0.3.1/README.md

@@ -0,0 +1,165 @@
+<div align="center">
+
+# 🤖 Inspect Robots
+
+### The [Inspect AI](https://inspect.aisi.org.uk/) for robotics
+
+**An open-source evaluation framework for physical AI and VLA (vision-language-action) models.**
+
+Define a robotics benchmark once, then run *any* policy against *any* compatible
+embodiment — a real robot or a simulator — with reproducible logs and first-class
+[Rerun](https://github.com/rerun-io/rerun) visualization.
+
+[![CI](https://github.com/robocurve/inspect-robots/actions/workflows/ci.yml/badge.svg)](https://github.com/robocurve/inspect-robots/actions/workflows/ci.yml)
+[![Docs](https://github.com/robocurve/inspect-robots/actions/workflows/docs.yml/badge.svg)](https://inspectrobots.org/)
+[![Python](https://img.shields.io/badge/python-3.10%E2%80%933.13-blue)](https://github.com/robocurve/inspect-robots)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+[![Typed](https://img.shields.io/badge/typed-mypy%20strict-blue)](https://github.com/robocurve/inspect-robots)
+[![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen)](https://github.com/robocurve/inspect-robots/actions/workflows/ci.yml)
+
+[**Documentation**](https://inspectrobots.org/) ·
+[Quickstart](https://inspectrobots.org/guide/quickstart.html) ·
+[Concepts](https://inspectrobots.org/guide/concepts.html) ·
+[For LLMs](https://inspectrobots.org/llms.txt)
+
+</div>
+
+---
+
+## One framework, two swappable inputs
+
+LLM evaluations have a single swappable input: the model. **Robotics evaluations
+have two** — and Inspect Robots makes both first-class and orthogonal:
+
+| | |
+|---|---|
+| 🧠 **`Policy`** — the VLA | The "brain". Maps an observation + instruction to an **action chunk** (a horizon of actions executed open-loop, as π0 / ACT / diffusion policies do). |
+| 🦾 **`Embodiment`** — the robot or sim | The "body + world". Produces observations, executes actions, owns the action/observation spaces and control rate. Real-robot-first; sims are a stricter special case. |
+
+A **`Task`** — a dataset of `Scene`s (initial conditions, instructions, success
+targets) plus scorers — is defined *independently* of both. Before any rollout,
+Inspect Robots checks the `(policy, embodiment)` pair is **compatible** (action/observation
+spaces, semantics, control rate, scene realizability) and fails fast if not.
+
+## Install
+
+```bash
+pip install inspect-robots            # core (numpy only)
+pip install "inspect-robots[rerun]"   # + Rerun visualization
+```
+
+## Quickstart
+
+With a default policy/embodiment configured once in
+`~/.config/inspect-robots/config.ini`, just tell the robot what to do:
+
+```bash
+inspect-robots "place the spoon on the plate"                # zero-config ad-hoc eval
+inspect-robots "place the spoon on the plate" --sim          # same, on your configured sim
+```
+
+The full command line resolves any registered task/policy/embodiment
+(builtins + installed plugins):
+
+```bash
+inspect-robots list                                          # registered components
+inspect-robots run --task cubepick-reach --policy scripted --embodiment cubepick
+inspect-robots inspect logs/cubepick-reach_*.json            # results table
+```
+
+And everything is a Python API. No hardware or simulator needed — the
+dependency-free `CubePick` mock world exercises the whole stack:
+
+```python
+from inspect_robots import eval
+from inspect_robots.mock import CubePickEmbodiment, ScriptedPolicy
+from inspect_robots.scene import Scene
+from inspect_robots.scorer import success_at_end
+from inspect_robots.task import Task
+
+task = Task(
+    name="cubepick-reach",
+    scenes=[Scene(id=f"layout-{i}", instruction="reach the cube", init_seed=i) for i in range(5)],
+    scorer=success_at_end(),
+    max_steps=80,
+)
+
+# The two swappable inputs: a policy (VLA) and an embodiment (robot/sim).
+(log,) = eval(task, ScriptedPolicy(), CubePickEmbodiment())
+print(log.status, log.results.metrics)   # success {'success_at_end': 1.0}
+```
+
+## Why Inspect Robots
+
+- 🌍 **Real-world first.** Interfaces assume real-robot reality — human-in-the-loop
+  reset, no privileged success oracle, wall-clock control rate. Simulators just
+  offer more (seeding, privileged success, rendering) via opt-in capabilities.
+- 🔁 **Reproducible.** Every run yields an immutable, schema-versioned `EvalLog`
+  with the resolved config, git revision, and package versions — re-readable across
+  releases, and re-scorable offline.
+- 🪶 **Light core.** Depends only on NumPy. Rerun and simulator/VLA backends are
+  optional extras and separately installable plugins.
+- 🛑 **Safe unattended.** An explicit error taxonomy separates "record and continue"
+  from "halt and require a human", so a faulted robot never auto-advances overnight.
+- 🎞️ **Rerun visualization.** Stream camera images, 3D poses, joint/action
+  time-series, and success markers to a `.rrd` recording.
+- 🧩 **Pluggable.** Ship `inspect-robots-maniskill` or `inspect-robots-openvla` as separate
+  packages — entry points make them appear in `inspect-robots list` automatically.
+- ⚙️ **VLA-native.** Action chunking, open-loop execution, and ACT/ALOHA temporal
+  ensembling are built in, with action *semantics* (control mode, rotation
+  representation, gripper, frame) that make compatibility and ensembling correct.
+
+## How it maps to Inspect AI
+
+If you know [Inspect AI](https://inspect.aisi.org.uk/), you already know Inspect Robots.
+
+| Inspect AI | Inspect Robots |
+|---|---|
+| `Model` | `Policy` (VLA) **+** `Embodiment` *(two inputs)* |
+| `Task = dataset + solver + scorer` | `Task = scenes + controller + scorer` |
+| `Sample` | `Scene` |
+| `Solver` chain | `Controller` middleware (chunking, ensembling, smoothing) |
+| `eval()` → `EvalLog` | `eval()` → `EvalLog` |
+| `@task` / `@solver` / `@scorer` + registry | `@task` / `@policy` / `@embodiment` / `@scorer` + entry points |
+
+This repository is the **framework** (the "Inspect AI for robotics"). Concrete
+benchmarks (the "Inspect Evals for robotics") and backend adapters live in
+separate plugin packages.
+
+## Documentation
+
+Full guides and an auto-generated API reference live at
+**[inspectrobots.org](https://inspectrobots.org/)**.
+LLM-friendly versions: [`llms.txt`](https://inspectrobots.org/llms.txt)
+and [`llms-full.txt`](https://inspectrobots.org/llms-full.txt).
+
+## Development
+
+```bash
+uv venv && uv pip install -e ".[dev]"
+uv run pre-commit install          # ruff + mypy on commit, 100% coverage on push
+uv run pytest --cov                 # 100% coverage required
+uv run ruff check . && uv run mypy
+```
+
+Pre-commit hooks and a blocking CI coverage gate keep `main` green. See
+[`CONTRIBUTING.md`](CONTRIBUTING.md) and the design docs in [`plans/`](plans/).
+
+## Citation
+
+If you use Inspect Robots in your research, please cite it:
+
+```bibtex
+@software{inspect-robots,
+  author  = {Robocurve},
+  title   = {Inspect Robots: The open-source evaluation framework for physical AI},
+  year    = {2026},
+  url     = {https://github.com/robocurve/inspect-robots},
+  version = {0.3.0},
+  license = {MIT}
+}
+```
+
+## License
+
+[MIT](LICENSE)