MAS Library Samples
Reusable sample artefacts (apps, datasets, tools, skills, overlays, infra manifests) for tutorials and labs. Use it when you need a ready-made MAS or manifest to run or reference; it holds no runnable experiments.
YAML samples live here, grouped by artefact type. Experiments belong only under labs/*.lab/: a lab is the experiment pack, this tree is a library. When to create each: docs/labs-and-libraries.md.
Quick start, from the repository root:
mas-ctl chat docs/tutorials/01-building-an-agent/agent.yaml \
-o library-samples/overlays/hitl-on-tool.yaml
What belongs here
| Kind | Examples |
|---|---|
| apps | apps/trip-planner/ (real use-case MAS: agents, local tools/skills), apps/qa-mas/ (small question-answering MAS) |
| datasets | datasets/trip-planner/benchmark.yaml — complete pack for the app, tutorials, and CI |
| tools | tools/calc.py, tools/*.tool.yaml (trip-planner domain tools: see tools/README.md) |
| skills | skills/answer-formatting/ (shared); app-specific skills live under the app tree |
| overlays | overlays/cot-moderator.yaml, overlays/hitl-on-tool.yaml, … |
| infra | infra/tool-providers.yaml, infra/llm-cache-{write,replay}.yaml, MCP / A2A deployment manifests |
| pipelines, experiments | pipelines/pipeline-test.yaml, experiments/moderator-design-patterns.yaml (small reference files, not paper experiments) |
| sample-workspace | sample-workspace/config.yaml — OSS dev/CI workspace default |
Generic pipelines, built-in steps, and shared artefacts belong in library-standard (or future lab-standard libraries), not here.
What does not belong here
experiment.yaml— only inlabs/<name>.lab/- Lab-specific pipeline definitions — colocate with the lab (
labs/.../pipeline-figure.yaml, inline in experiment) - One-off benchmark output paths or canvas exports
- Small plugin/feature examples — those sit in
library-standard/examples/<category>/(not underapps/)
Labs compose library artefacts by registered id — not path traversal. In an
experiment.yaml:
experiment:
application:
app: trip-planner # id from this library's library.yaml `apps:`
configs_dir: ./overlays
dataset:
name: trip-planner-benchmark
locator: samples # mas.runtime.manifest_libraries scheme
# limit: 5 # optional: first N items (smoke / CI)
Install library-samples (or uv pip install -e library-samples) so the
samples locator resolves via its entry point.
Labs may also declare libraries: [samples] under lab: in lab-config.yaml to
inject the library root at run time (see labs/design-space.lab/*/lab-config.yaml).
Referencing from tutorials
From the repository root, pass an overlay by path:
mas-ctl chat docs/tutorials/01-building-an-agent/agent.yaml \
-o library-samples/overlays/hitl-on-tool.yaml
Tool refs inside manifests use the library scheme instead of a path, for example
ref: samples:tools/calc.tool.yaml (see
Tutorial 14). Copy an overlay
into a tutorial's overlays/ folder for a self-contained bundle.
Metadata
Release files for mas-lab-library-samples 0.2.0
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 | Actions |
|---|---|---|---|---|
| mas_lab_library_samples-0.2.0.tar.gz | 44.6 kB | With provenance | Details for mas_lab_library_samples-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mas_lab_library_samples-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for mas_lab_library_samples-0.2.0-py3-none-any.whl |
Total release size: 120.4 kB
Release files / mas_lab_library_samples-0.2.0.tar.gz
| Download URL | mas_lab_library_samples-0.2.0.tar.gz |
|---|---|
| Size | 44.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
65ba0ec5c87eb297da3d847a1b586e9855c925c11597f507c1cfdb21b69d5d4a
|
|
BLAKE2b-256 checksum How to use checksums |
385201dd031824510cdf9c411d368ab95b3889b16c7147cd282e55d8b2df000a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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 Nov 5, 2026.
Transparency logRelease files / mas_lab_library_samples-0.2.0-py3-none-any.whl
| Download URL | mas_lab_library_samples-0.2.0-py3-none-any.whl |
|---|---|
| Size | 75.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6bdd2f51701cedbc8bd933079d115e988a673f3bab9c0adffbfeaa99ac60280e
|
|
BLAKE2b-256 checksum How to use checksums |
ae03caac38080a48b135bca39a72529942278e59cef6ce74e1ce748dac28d11a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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 Nov 5, 2026.
Transparency logSecurity for mas-lab-library-samples 0.2.0
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
Both files in this release have been uploaded with provenance metadata.
Attestation for mas_lab_library_samples-0.2.0.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 Nov 5, 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.