iGibson
Interactive household simulation environment for embodied AI tasks including navigation and manipulation.
iGibson
iGibson is an interactive simulation environment from Stanford Vision and Learning Lab built for training embodied AI agents in realistic indoor scenes. It features fully interactive objects, physics simulation, and a rich sensor suite, making it ideal for household robot learning tasks.
Key Features
- 15 fully interactive household scenes with 500+ object categories
- Physics-based interaction: grasp, push, place, pour, and toggle objects
- High-fidelity rendering with physically based materials and lighting
- Sensor suite: RGB, depth, LiDAR, instance/semantic segmentation
- OpenAI gym-compatible API with predefined task benchmarks
Quick Start
pip install igibson
python -m igibson.utils.assets_utils --download_assets
from igibson.envs.igibson_env import iGibsonEnv
env = iGibsonEnv(
config_file="fetch_reaching.yaml",
mode="gui_interactive",
)
obs = env.reset()
for _ in range(100):
action = env.action_space.sample()
obs, rew, done, info = env.step(action)
npx ai-supply add igibson-interactive-simulation
Curated mirror of the open-source iGibson (MIT). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/igibson-interactive-simulation/check). Click a policy:
Consume iGibson programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/igibson-interactive-simulation
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/igibson-interactive-simulation/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add igibson-interactive-simulation
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/igibson-interactive-simulation/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "igibson-interactive-simulation" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.