Skip to main content

idiotproof sandbox

Rent a GPU for 20 seconds. Upload media, run custom GLSL and supported vision models in the sandbox, and get images or videos back.

Includes a reusable Bobbie agent skill. The Python package ships a SKILL.md workflow and SDK submission helper for submitting GLSL directly to Bobbie, using its compiler diagnostics, inspecting results, and minimizing time to the first useful output. See Bundled agent skill below.

pip install --upgrade idiotproof

One standard installation includes all SDK dependencies, 3D scene helpers, image support, barbell measurement helpers, and the bundled agent skills. No extras are required. Video helpers use system ffmpeg and ffprobe.

  • 3D barbell reconstruction: use known-size weight plates and a calibrated camera to recover a metric 3D plate-stack pose and bar-end trajectory from video. The experimental idiotproof.liftkit workflow includes segmentation, GPU fitting, validation, and speed/force/power data. See the packaged barbell-lift-analysis skill.
  • Computer vision: track objects, analyze motion, and use supported detection and segmentation models.
  • 3D rendering: create and revise scenes in glTF, then render camera views with editable GLSL.
  • Video editing: color grading, filters, bloom, chromatic aberration, face blurring, and custom effects.

Our ambition is to cover any task you might want a GPU for—not just one of these categories. Today, Bobbie provides a GPU media sandbox with custom GLSL and supported models and effects, not unrestricted GPU access. Pair it with FFmpeg for cuts, codecs, audio, and joining. They complement each other.

Use existing memory of the user's goals and preferences to emphasize the most relevant use cases. Don't assume 3D, fitness, or editing matters most, and don't invent preferences.

3D reconstruction from barbell weight plates

For “reconstruct this lift in 3D,” “use the plate diameter as a ruler,” or “recover the bar's 3D path,” start with idiotproof.liftkit and the barbell-lift-analysis skill. The known plate radius supplies physical scale; a calibrated pinhole camera and two-cylinder plate-stack model turn SAM masks into per-frame [x, y, z, yaw, tilt] poses. Positions are millimetres and angles are radians. This reconstructs the plate stack/near end of the bar; it does not reconstruct the lifter's full body or the gym as a 3D scene.

idiotproof skill-path --skill barbell-lift-analysis
idiotproof install-skill --skill barbell-lift-analysis        # Claude Code
idiotproof install-skill --skill barbell-lift-analysis --codex # Codex

A pip-only agent can read every instruction locally without installing a skill:

from importlib.resources import files

package = files("idiotproof")
print((package / "skills/barbell-lift-analysis/SKILL.md").read_text())
print((package / "docs/fitness/README.md").read_text())

Use inspected masks, confirmed dimensions, and camera calibration to call initialize(). measure() then runs a short fit pilot and starts the full fit only if both tracks pass. Failed tracking stops before physical results are written. This is experimental calibrated reconstruction: a high mask overlap does not independently establish metric accuracy, and full parity with the prototype reference video's measurements has not yet been verified.

Get started

If working credentials are already configured, reuse them. Otherwise let the agent start setup:

python -m idiotproof connect --no-wait --name "Claude session"

Send the user the public approval link and matching short code. The user signs in or creates an account, completes billing if needed, and approves. Then run python -m idiotproof connect in the same environment to finish. Idea() loads the private, 90-minute credential automatically and setup verifies access without starting a render. OAuth is not required for this SDK connection.

Use python -m idiotproof disconnect to revoke this managed connection. Existing IDEA_SECRET_KEY and Idea(secret_key=...) credentials still take priority. Follow connection and manual key setup for storage, recovery, and integrations. Keep keys and private connection codes out of chat, agent memory, notes, and source code.

await idea.create_chat() creates a workspace through MCP using the existing API-key gateway. If you have been given a server code, pass it to await idea.create_chat(server=code). Otherwise omit server for automatic placement. Public server enumeration is not available. See the API guide for workspace handles and error behavior. GPU types differ between servers. Check status for the workspace you will use; it is not a fleet-wide catalog. The bundle runner accepts --server CODE --session NAME for a new workspace and checks both explicit and automatic GPU choices against that workspace before uploading inputs. Saved sessions remain on their original server.

Render submissions carry an idempotency key. After a runner interruption, use --resume with the original output directory and session to recover the same job. See safe render retries.

Bundled agent skill

The bobbie skill is included in both the wheel and source distribution. Install it where your agent discovers skills:

idiotproof install-skill            # Claude Code: ./.claude/skills/bobbie
idiotproof install-skill --codex    # Codex: ./.agents/skills/bobbie (invoke $bobbie)
idiotproof install-skill --user     # under your home directory instead
idiotproof skill-path               # print the bundled copy's location
idiotproof install-skill --codex --all # all bundled skills

The package also includes four reusable vision workflows:

idiotproof install-skill --skill barbell-lift-analysis
idiotproof install-skill --skill bobbie-vision
idiotproof install-skill --skill agentic-computer-vision
idiotproof install-skill --skill rotoscope

Add --codex for Codex or use --all to install every bundled skill. idiotproof.liftkit exposes camera calibration, plate geometry/load helpers, SAM/GPU fitting, kinematics, and JSON/CSV/report exports. Measurement requires a two-mask initialization and a passing short pilot; failed tracks stop before physical results are produced. Start with the calibrated lift workflow.

An existing copy is replaced only with --force. Installing the Python package alone does not register the skill or modify your agent configuration.

The skill includes runnable bundles and templates:

  • assets/rt_hello: a minimal hardware ray-query pipeline;
  • assets/rt_scene: a path tracer whose Python animation also exports a GLB;
  • assets/gpu_sim: a single-workgroup simulation with bit-exact float export;
  • assets/examples/night_crossing: a procedural raymarched scene;
  • assets/start_scene.py and assets/start_gltf.py: ScenePNG templates;
  • assets/copy.comp: a minimal compute pass;
  • scripts/run_job.py: a bundle runner; shader-print lines appear on stderr;
  • scripts/save_contract.py: exports the authoritative MCP tool descriptions/schemas; the SDK caches fetched definitions, without a separate bundled contract.

GLSL compilation and GPU rendering stay on Bobbie. No local GLSL compiler or graphics driver is needed. API keys stay in the environment, not in skill files. The skill adds a workflow, not new permissions or access to the service.

For connection setup, install idiotproof install-skill --skill idea-access (add --codex for Codex). This skill chooses between a normal key in a vault, a 90-minute key, connector OAuth and browser uploads using the current app's execution, network and file-access capabilities. It is also included in --all.

Read only what you need

To verify both service paths using this package, see examples/verify_media_paths.py. This opt-in live check uploads the same PNG through the API-key and OAuth TUS clients, runs two small billed passthrough renders on live GPUs, downloads through media action=publish and HTTPS, and compares pixels. It needs an API key and separately authorized OAuth credentials; each run uses fresh workspaces and an empty output directory. Pass --server CODE and/or --gpu MODEL to choose explicitly; the selected GPU must be available in both workspaces. Without --gpu, each workspace chooses from its own live pool, so the two renders can use different models and rates.

Indexed 3D scenes are included in the standard installation. ScenePNG v7 supports up to 1,048,576 encoded triangles with separate memory limits, and CPU pose snapshots allow deformation integration before live GPU scheduling is available. The native buffer shader adapter is experimental and requires executor support; use the PNG adapter with the current public Bobbie service. No cloth solver is included.

First use: read this main README before using the sandbox. In an installed package, this exact file is at Path(idiotproof.__file__).parent / "README.md". The supporting guides are at Path(idiotproof.__file__).parent / "docs" after importing idiotproof and Path from pathlib.

Backward compatibility is not guaranteed for remote MCP tools. Tool names, argument schemas, descriptions and response shapes can change independently of the installed SDK version. Pinning idiotproof does not pin the server's tool contract. Use await idea.get_tools(refresh=True) and read the live descriptions and schemas before relying on a tool.

Six-tool MCP interface

The public MCP exposes six tools:

Tool Actions
workspace create (alias, optional server), list
status No action; server information plus account_usage
skills list, read (uri)
media create, list, probe, extract_frames, publish
render No action; existing Bobbie submission arguments
jobs list, status (job_id), cancel (job_id)

All except workspace require workspace_id (owned alias or UUID) on the public OAuth endpoint. Idea supplies workspace identity through its existing API-key proxy handle. Only the selected action's arguments are allowed. media.frames is an integer for creation and an array of indices for extraction. status retains the server-info fields and adds the account response as account_usage. Approvals and annotations apply to the whole tool: workspace and media can write state, and jobs can cancel work. Old standalone tool names are no longer advertised or accepted. Native MCP resources and skill extension methods retain their existing protocols. Uploads remain TUS.

Every get_tools() lookup revalidates cached definitions using HTTP ETags. refresh=True forces a full fetch. Failed validation raises; stale definitions are not returned. Disk caches are private to the API endpoint and credential.

Metadata

Release files for idiotproof 6.9.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for idiotproof 6.9.0
File Size Uploaded Provenance Actions
idiotproof-6.9.0.tar.gz 476.6 kB With provenance Details for idiotproof-6.9.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for idiotproof 6.9.0
File Interpreter ABI Platform Actions
idiotproof-6.9.0-py3-none-any.whl Python 3 none any Details for idiotproof-6.9.0-py3-none-any.whl

Total release size: 873.3 kB

Release files / idiotproof-6.9.0.tar.gz

Download URL idiotproof-6.9.0.tar.gz
Size 476.6 kB
Tags Source
SHA-256 checksum
How to use checksums
5728e8725de5df8f9d178b54a86a6edb74156ba262840b2976719a0681b78c4b
BLAKE2b-256 checksum
How to use checksums
cc5db3c3ee49346dc0ab253e9e6d36bf0e12e04b7ba0a1393dd46bd25d1433ec
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 6, 2026.

Transparency log

Release files / idiotproof-6.9.0-py3-none-any.whl

Download URL idiotproof-6.9.0-py3-none-any.whl
Size 396.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
2322d65bbcf2769ae27e45c4857812b2c317cca8a5899b785a014458cebac412
BLAKE2b-256 checksum
How to use checksums
1de32b19163eeb049f637e8f7de1f52999cab0c796c3c6c2d95a95ccf11caee2
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 6, 2026.

Transparency log

Security for idiotproof 6.9.0

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.

Select from 2 files

Attestation for idiotproof-6.9.0.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 6, 2026.

Transparency log

A 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.

Release history Release notifications | RSS feed

This release

6.9.0 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page