AbdelStark / worldforge
Harness framework to build world model based workflows for physical AI systems.
Why this job: matched by what the repo talks about: framework, system, workflow, harness
What it does
WorldForge is the application builder's counterpart to model-training stacks like Stable World Model. Those stacks *train* world models. WorldForge helps roboticists *compose, evaluate, and benchmark* workflows on top of them — so they can pick a provider and configuration for a task.
Get started
uv add worldforge-ai
# or: pip install worldforge-ai- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 109
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 77% closed
- 43 still open
- Pull requests
- 147 merged
- 8 waiting
- Releases
- None
- Never published
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| RobotecAI / rai | 615 | yesterday | Apache-2.0 | No downloads |
| AIScientists-Dev / WorldSeed | 828 | 6 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Shell <1%
Topics
- jepa
- machine-learning
- physical-ai
- robotics
- world-models
Project record
- JobAgent frameworks
- StatusListed
- Commits485
- Forks10
- Watching1
- Stars in 28 days+1
- CreatedMar 14, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026