worldevals 0.3.0__tar.gz

worldevals-0.3.0/.github/workflows/ci.yml

@@ -0,0 +1,59 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+  workflow_dispatch:
+
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  quality:
+    name: lint · type
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+          cache-dependency-glob: |
+            **/pyproject.toml
+            **/uv.lock
+      - name: Create venv
+        run: uv venv --python 3.11
+      - name: Install from uv.lock (dev + docs extras; docs so mypy sees scripts/ imports)
+        run: uv sync --locked --extra dev --extra docs
+      - name: Ruff (lint)
+        run: uv run ruff check .
+      - name: Ruff (format check)
+        run: uv run ruff format --check .
+      - name: Mypy (strict)
+        run: uv run mypy
+
+  test:
+    name: test (${{ matrix.os }}, py${{ matrix.python-version }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        python-version: ["3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+          cache-dependency-glob: |
+            **/pyproject.toml
+            **/uv.lock
+      - name: Create venv (py${{ matrix.python-version }})
+        run: uv venv --python ${{ matrix.python-version }}
+      - name: Install from uv.lock (dev extras)
+        run: uv sync --locked --extra dev
+      - name: Pytest (100% coverage gate)
+        run: uv run pytest --cov --cov-report=term-missing

worldevals-0.3.0/.github/workflows/docs.yml

@@ -0,0 +1,71 @@
+name: Docs
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: false
+
+jobs:
+  build:
+    name: build docs
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+          cache-dependency-glob: |
+            **/pyproject.toml
+            **/uv.lock
+      - name: Create venv
+        run: uv venv --python 3.12
+      - name: Install from uv.lock (docs extras)
+        run: uv sync --locked --extra docs
+      - name: Build site (strict)
+        run: uv run mkdocs build --strict
+      - name: Upload Pages artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: site
+
+  deploy:
+    name: deploy to GitHub Pages
+    if: github.ref == 'refs/heads/main'
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url || steps.retry1.outputs.page_url || steps.retry2.outputs.page_url }}
+    steps:
+      # The Pages API intermittently rejects deployments with a transient
+      # "Deployment failed, try again later" — retry twice with backoff.
+      - name: Deploy
+        id: deployment
+        continue-on-error: true
+        uses: actions/deploy-pages@v4
+      - name: Wait before retry
+        if: steps.deployment.outcome == 'failure'
+        run: sleep 30
+      - name: Deploy (retry 1)
+        id: retry1
+        if: steps.deployment.outcome == 'failure'
+        continue-on-error: true
+        uses: actions/deploy-pages@v4
+      - name: Wait before second retry
+        if: steps.deployment.outcome == 'failure' && steps.retry1.outcome == 'failure'
+        run: sleep 60
+      - name: Deploy (retry 2)
+        id: retry2
+        if: steps.deployment.outcome == 'failure' && steps.retry1.outcome == 'failure'
+        uses: actions/deploy-pages@v4

worldevals-0.3.0/.github/workflows/release.yml

@@ -0,0 +1,23 @@
+name: Release
+
+# Publishes to PyPI via trusted publishing (OIDC) — no API tokens.
+# Authenticates against the PyPI trusted-publisher entry for this repo
+# (workflow: release.yml, environment: pypi).
+on:
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write  # OIDC token for PyPI trusted publishing
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+      - name: Build sdist + wheel
+        run: uv build
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

worldevals-0.3.0/.gitignore

@@ -0,0 +1,219 @@
+# 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
+

worldevals-0.3.0/.pre-commit-config.yaml

@@ -0,0 +1,58 @@
+# Pre-commit hooks for WorldEvals. Install once per clone:
+#
+#     uv run pre-commit install        # sets up both pre-commit and pre-push hooks
+#
+# On commit: file hygiene + ruff (lint & format) + mypy (strict).
+# On push:   pytest with the 100% coverage gate.
+#
+# Run everything manually with:  uv run pre-commit run --all-files
+#
+# The ruff / mypy / pytest hooks are "local" so they use the exact versions
+# pinned in this project's dev environment (matching CI) rather than a separate
+# pinned copy.
+default_install_hook_types: [pre-commit, pre-push]
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+        args: [--unsafe] # mkdocs.yml uses !!python/name: tags
+      - id: check-toml
+      - id: check-merge-conflict
+      - id: check-added-large-files
+
+  # Local hooks run through `uv run` so they use this project's dev environment
+  # (matching CI) regardless of whether a virtualenv is activated. Requires uv.
+  - repo: local
+    hooks:
+      - id: ruff-check
+        name: ruff (lint, autofix)
+        entry: uv run ruff check --fix
+        language: system
+        types_or: [python, pyi]
+        require_serial: true
+
+      - id: ruff-format
+        name: ruff (format)
+        entry: uv run ruff format
+        language: system
+        types_or: [python, pyi]
+        require_serial: true
+
+      - id: mypy
+        name: mypy (strict)
+        entry: uv run mypy
+        language: system
+        types: [python]
+        pass_filenames: false
+
+      - id: pytest-coverage
+        name: pytest (100% coverage gate)
+        entry: uv run pytest --cov --cov-report=term-missing
+        language: system
+        always_run: true # run on every push, even when no .py files changed
+        pass_filenames: false
+        stages: [pre-push]

worldevals-0.3.0/CITATION.cff

@@ -0,0 +1,9 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+title: "WorldEvals: A curated catalog of physical-AI benchmarks"
+authors:
+  - name: "Robocurve"
+type: software
+license: MIT
+repository-code: "https://github.com/robocurve/worldevals"
+version: "0.3.0"

worldevals-0.3.0/CLAUDE.md

@@ -0,0 +1,60 @@
+# WorldEvals — agent guide
+
+WorldEvals is the **"Inspect Evals for robotics"**: a curated **catalog + CLI**
+indexing physical-AI benchmarks built on
+[Inspect Robots](https://github.com/robocurve/inspect-robots). Unlike Inspect Evals' monorepo,
+each benchmark here is **its own repo** (e.g.
+[KitchenBench](https://github.com/robocurve/kitchenbench)); WorldEvals is the
+lightweight index that ties them together.
+
+## The one big idea
+
+- `inspect-robots list` → what Inspect Robots tasks are **installed**.
+- `worldevals list` → what benchmarks **exist** and how to install them.
+
+WorldEvals does **not** depend on or import the benchmark repos (they're separate
+packages). It only keeps a static `catalog.py` of `Benchmark` entries; the
+`worldevals tasks` command bridges the two by annotating *installed* Inspect Robots
+tasks with the catalogued benchmark they belong to.
+
+## Layout
+
+```
+src/worldevals/
+  catalog.py   # Benchmark dataclass + CATALOG (the registry of benchmark repos) +
+               # accessors: catalog(), get(name), by_tag(tag), benchmark_for_task(key)
+  cli.py       # `worldevals list [--tag] | info <name> | tasks`
+  __init__.py  # public API (catalog, get, by_tag, benchmark_for_task, Benchmark)
+tests/         # 100% coverage; catalog-integrity + CLI tests
+plans/0001-worldevals-design.md   # design doc
+README.md      # collection landing page (benchmark table + contribution guide)
+```
+
+The package is small and self-documenting, so there's no separate `src/` guide.
+
+## Working here (important gotchas)
+
+- **Dependency on Inspect Robots is a git tag** (`[tool.uv.sources] inspect-robots = { git =
+  ..., tag = "v0.3.0" }`); it's used only by the `tasks` command (to read the
+  Inspect Robots registry). `tool.uv.sources` is **uv-only**: plain pip ignores it,
+  and `inspect-robots` isn't on PyPI, so every pip-facing install instruction is
+  **two-step** — `pip install "inspect-robots @
+  git+https://github.com/robocurve/inspect-robots@v0.3.0"` first, then the
+  package. Keep README, `catalog.py` install strings, `scripts/gen_catalog.py`,
+  and `docs/contributing.md` in that form.
+- **Conda is active in this shell** — `uv pip install -e .` lands in conda base,
+  not `.venv`. Activate first: `source .venv/bin/activate && export
+  VIRTUAL_ENV="$PWD/.venv"` (or use `uv run`).
+- Dev loop: `uv venv && uv pip install -e ".[dev]"`, `uv run pre-commit install`,
+  `uv run pytest --cov`.
+- **Gates (all required, blocking PR checks):** `ruff check .`,
+  `ruff format --check .`, `mypy` (strict), `pytest --cov` at **100% coverage**.
+
+## Adding a benchmark to the catalog
+
+Append a `Benchmark(...)` entry to `src/worldevals/catalog.py` with its name,
+title, description, repo URL, install command, the Inspect Robots task keys it
+registers, tags, and contributors. `tests/test_catalog_cli.py` validates every
+entry (unique name, well-formed `https://github.com/...` repo URL, ≥1 task key) —
+so a malformed entry fails CI. Keep `task_keys` in sync with the benchmark repo's
+actual registered task names.

worldevals-0.3.0/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.

worldevals-0.3.0/PKG-INFO

@@ -0,0 +1,148 @@
+Metadata-Version: 2.4
+Name: worldevals
+Version: 0.3.0
+Summary: The Inspect Evals for robotics — a curated catalog of physical-AI benchmarks built on Inspect Robots.
+Project-URL: Homepage, https://github.com/robocurve/worldevals
+Project-URL: Documentation, https://worldevals.org/
+Project-URL: Framework, https://github.com/robocurve/inspect-robots
+Author: RoboCurve
+License-Expression: MIT
+License-File: LICENSE
+Keywords: benchmarks,catalog,evaluation,physical-ai,robotics,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: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: inspect-robots>=0.3
+Provides-Extra: dev
+Requires-Dist: mypy>=1.11; 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-gen-files<0.6.1,>=0.5; 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'
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+# 🌍 WorldEvals
+
+**The [Inspect Evals](https://inspect.aisi.org.uk/evals/) for robotics.**
+
+A curated catalog of physical-AI / VLA benchmarks built on
+[Inspect Robots](https://github.com/robocurve/inspect-robots).
+
+[![CI](https://github.com/robocurve/worldevals/actions/workflows/ci.yml/badge.svg)](https://github.com/robocurve/worldevals/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+[![Coverage](https://img.shields.io/badge/coverage-100%25-brightgreen)](https://github.com/robocurve/worldevals/actions/workflows/ci.yml)
+[![Built on Inspect Robots](https://img.shields.io/badge/built%20on-Inspect%20Robots-indigo)](https://github.com/robocurve/inspect-robots)
+
+**[📖 Browse the catalog → worldevals.org](https://worldevals.org/)**
+
+</div>
+
+[Inspect Robots](https://github.com/robocurve/inspect-robots) is the *framework* (the "Inspect
+AI for robotics"). **WorldEvals is the collection** — but unlike Inspect Evals'
+monorepo, each benchmark here lives in **its own repository** so it owns its
+release cadence, dependencies, hardware notes, and leaderboard. WorldEvals is the
+lightweight index that ties them together: what benchmarks exist, what tasks each
+provides, and how to install them.
+
+- `inspect-robots list` tells you what's **installed**.
+- `worldevals list` tells you what **exists** and how to get it.
+
+## Benchmarks
+
+| Benchmark | Tasks | Tags | Status |
+|---|--:|---|---|
+| [KitchenBench](https://github.com/robocurve/kitchenbench) — 10 bimanual kitchen-manipulation tasks | 10 | kitchen, bimanual, manipulation | alpha |
+
+## Install & use
+
+```bash
+# Inspect Robots isn't on PyPI yet, so install it from its git tag first:
+pip install "inspect-robots @ git+https://github.com/robocurve/inspect-robots@v0.3.0"
+pip install "worldevals @ git+https://github.com/robocurve/worldevals"
+
+worldevals list                 # all benchmarks
+worldevals list --tag bimanual  # filter by tag
+worldevals info kitchenbench    # repo, install command, task keys
+worldevals tasks                # Inspect Robots tasks installed locally, by benchmark
+```
+
+Then install a benchmark and run it through Inspect Robots:
+
+```bash
+pip install "inspect-robots @ git+https://github.com/robocurve/inspect-robots@v0.3.0"
+pip install "kitchenbench @ git+https://github.com/robocurve/kitchenbench"
+inspect-robots run --task kitchenbench/pour_pasta --policy kitchen_scripted --embodiment kitchen
+```
+
+## Backends (run on real robots)
+
+Benchmarks are embodiment-agnostic; **backend adapters** supply a concrete
+`Policy` + `Embodiment` so a benchmark runs on real hardware or a simulator.
+These are their own repos too (not catalog entries):
+
+| Adapter | Policy · Embodiment | Stack |
+|---|---|---|
+| [inspect-robots-yam](https://github.com/robocurve/inspect-robots-yam) | `molmoact2` · `yam_arms` | [MolmoAct2](https://github.com/allenai/molmoact2) on [I2RT YAM](https://i2rt.com/products/yam-6-dof-arm) bimanual arms |
+| [inspect-robots-so101](https://github.com/robocurve/inspect-robots-so101) | `lerobot` · `so_arm` | [LeRobot](https://github.com/huggingface/lerobot) policies (ACT, SmolVLA, π0, …) on [SO-ARM](https://github.com/TheRobotStudio/SO-ARM100) (SO-100 / SO-101) follower arms |
+
+```bash
+inspect-robots run --task kitchenbench/pour_pasta --policy molmoact2 --embodiment yam_arms
+```
+
+## Add your benchmark
+
+A benchmark is any repo that:
+
+1. depends on `inspect-robots`,
+2. defines one or more Inspect Robots `Task`s, and
+3. registers them via `[project.entry-points."inspect_robots.tasks"]` (and, if it ships
+   a sim/embodiment or policy, `inspect_robots.embodiments` / `inspect_robots.policies`).
+
+To list it here, add a `Benchmark(...)` entry to
+[`src/worldevals/catalog.py`](src/worldevals/catalog.py) and open a PR. A test
+validates every entry (unique name, well-formed repo URL, ≥1 task key). See
+[KitchenBench](https://github.com/robocurve/kitchenbench) as the reference
+implementation.
+
+## Development
+
+```bash
+uv venv && uv pip install -e ".[dev]"     # inspect_robots resolved from the v0.3.0 tag
+uv run pre-commit install
+uv run pytest --cov                        # 100% coverage required
+uv run ruff check . && uv run mypy
+```
+
+## Citation
+
+If you use WorldEvals in your research, please cite it:
+
+```bibtex
+@software{worldevals,
+  author  = {Robocurve},
+  title   = {WorldEvals: A curated catalog of physical-AI benchmarks},
+  year    = {2026},
+  url     = {https://github.com/robocurve/worldevals},
+  version = {0.3.0},
+  license = {MIT}
+}
+```
+
+## License
+
+[MIT](LICENSE)