labagent: open-source hands-on Cloud & AI labs for technical training, workshops and hackathons
Currently works for AWS, Azure, Neo Cloud (Lambda, Nebius, Shadeform)
labagent builds a lab with one command and removes it with one more. Each lab is a pack: ordered, re-runnable steps. launch resumes after a failure. destroy removes only what the pack created.
Built for people who run labs for other people:
- Trainers and instructor-led training teams who set up the same hands-on lab for 5 to 50 learners every cohort
- Bootcamps, training academies and college courses that need GPU, Databricks, Azure or AWS virtual labs without buying a lab platform
- GPU and cloud providers who want developer adoption through workshops and hackathons running on their own capacity
Install
Mac
brew install pipx && pipx ensurepath
pipx install labagent
Windows
# Install prerequisites & labagent
winget install Python.Python.3.14
Invoke-WebRequest -Uri https://bootstrap.pypa.io/get-pip.py -OutFile get-pip.py
python get-pip.py
Linux
pip install labagent
Use
labagent packs # list labs (add --json for a machine-readable catalog)
labagent launch <pack> --name demo --param k=v # build or resume
labagent destroy <pack> --name demo # remove what launch created
Packs
| Pack | What it builds | Where |
|---|---|---|
azure-labs |
Copy Azure VMs, disks and network from one resource group to another with snapshots, or snapshot a dead VM or disk. Source is read-only. An Azure Lab Services alternative. Guide | Azure (needs az login) |
gpu-notebooks |
Rent a GPU VM (Shadeform) and give each GPU slice its own JupyterLab, with a URL and login per lab. Guide. See what to rent first: labagent compute offers --cloud shadeform --gpu H100 (compute) |
Shadeform (API key) |
db-agent |
db-agent text-to-SQL app on Databricks Apps, pinned commit. Which model, warehouse and schema it picks | Databricks Free Edition |
dbx-lakehouse |
Medallion lakehouse (bronze, silver, gold) from real open data, with masks, a row filter, notebooks and exercises. Guide | Databricks Free Edition, AWS, Azure |
dbx-workspace |
Premium Databricks workspace via Terraform. Plan only unless apply=yes. Guide |
AWS or Azure (costs money) |
rag-ide |
Private browser VS Code per learner with the RAG lab | Modal, EC2 or Docker |
Workshops, hackathons and instructor-led training
Put the whole event in one YAML file. Launch every learner's sandbox before the session, destroy them after, and pay only for the hours used:
labagent launch -f hackathon.yaml # one lab per learner
labagent destroy -f hackathon.yaml # removes everything the
Azure Lab Services is retiring (June 28, 2027)
export LABAGENT_ALLOWED_AZURE_SUBSCRIPTIONS=$(az account show --query id -o tsv)
labagent launch azure-labs --name move1 --param source_rg=legacy-rg --param target_rg=new-rg
labagent launch azure-labs --name old1 --param source_rg=legacy-rg --param target_rg=archive-rg --param snapshot_only=true
labagent destroy azure-labs --name move1 --param target_rg=new-rg
Teaching with labagent?
labagent is free and open source. If you run cohorts and would rather not run the environments yourself, BeCloudReady runs managed hands-on labs for a fixed price per cohort, and builds custom packs for your course.
- Trainers and training companies: we're taking a few design partners for early 2027 cohorts, at cloud cost. Details on /labs.
- GPU and cloud providers: want a pack, hackathon or workshop driving developer adoption on your capacity? Open an issue or reach out through becloudready.com/labs.
- Upcoming: free GPU fine-tuning hackathon with TorontoAI, Dec 16, 2026, 5 PM ET. Every participant gets a GPU lab launched by labagent.
Apache-2.0. SECURITY.md, CONTRIBUTING.md, docs/packs.md. Related: db-agent, labagent-datasets. Maintained by BeCloudReady.
Metadata
Release files for labagent 0.4.1
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 |
|---|---|---|---|---|
| labagent-0.4.1.tar.gz | 550.6 kB | With provenance | Details for labagent-0.4.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| labagent-0.4.1-py3-none-any.whl | Python 3 | none | any | Details for labagent-0.4.1-py3-none-any.whl |
Total release size: 981.2 kB
Release files / labagent-0.4.1.tar.gz
| Download URL | labagent-0.4.1.tar.gz |
|---|---|
| Size | 550.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4dc05c82c80e67ea7001d906d99b796944591130d3c0fcaaf1c572ad58e8354d
|
|
BLAKE2b-256 checksum How to use checksums |
0ceb79bdfa0c70989a47c5a80b5639ffea4baaa502a7517bf703cebbf10fc8d3
|
| 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 17, 2026.
Transparency logRelease files / labagent-0.4.1-py3-none-any.whl
| Download URL | labagent-0.4.1-py3-none-any.whl |
|---|---|
| Size | 430.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0388b9d54bc5eb136110a0b040a33bdc8a00f0e3f3ff9a3f32682f6ec5cee1ae
|
|
BLAKE2b-256 checksum How to use checksums |
f2da9cdd5a67da37f4d958c58e9928d67dde6783dd7ea3428ca64f3e7218c500
|
| 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 17, 2026.
Transparency logSecurity for labagent 0.4.1
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 labagent-0.4.1.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 17, 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.