Metadata-Version: 2.4
Name: le-loopforge
Version: 0.5.0
Summary: Scaffold valid LSS loop specifications from common patterns
Author: Loop Engineering Community
License: MIT
Project-URL: Homepage, https://github.com/KanakMalpani/Loop-Engineering
Project-URL: Documentation, https://github.com/KanakMalpani/Loop-Engineering/blob/main/All%20about%20loops/LOOP_FORGE.md
Project-URL: Repository, https://github.com/KanakMalpani/Loop-Engineering
Keywords: loop-engineering,lss,agents,yaml
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: pyyaml>=6.0
Requires-Dist: jsonschema>=4.0
Provides-Extra: math
Requires-Dist: loopmath>=0.1.0; extra == "math"

# LoopForge

Scaffold and **combine** valid [LSS](https://github.com/KanakMalpani/Loop-Core-Engineering) loop specifications from patterns, recipes, or the bundled loop library.

```bash
pip install "le-loopforge>=0.5.0"

loopforge list-patterns
loopforge new --pattern reflection --name my-loop --objective "Your goal" -o my-loop.yaml

# Combine library templates (flat + compact — saves tokens)
loopforge combine --library research-agent,coding-agent -o pipeline.yaml --json

# Mix a named recipe
loopforge mix dev-agent -o agent.yaml
```

## Python API

```python
from loopforge import LoopChain, combine_loops, estimate_tokens

spec, meta = (
    LoopChain("my-pipeline", "Fix CI")
    .then_fork("autonomous-debugger")
    .then_fork("coding-agent")
    .build(flatten=True, compact=True)
)
print(meta["estimated_tokens"])
```

See [GOLDEN_PATH.md](../contributions/GOLDEN_PATH.md) and [00-planning/LOOP_FORGE.md](../00-planning/LOOP_FORGE.md).
