Version history for every DjangoPlay app — pick one to see what changed and when. Looking for what’s coming next? Explore the latest roadmap and upcoming releases?
The first release of astwire — a dependency-aware context compiler that turns a codebase into compact, structured context for LLMs.
Dependency-aware context follows internal imports and builds dependency closures without executing application code
Python AST analysis understands Python projects through AST-based import discovery and structural analysis rather than treating source files as disconnected text
LLM-ready output generates compact XML-style context designed for LLM consumption, alongside Markdown and JSON formats
Intelligent skeletonization strips implementation bodies while preserving function signatures, type hints, and docstrings to reduce context size without losing structural information
Token-aware context profiles token usage and partitions generated context within configurable token budgets while preserving file boundaries
Waste reduction normalizes source content by removing unnecessary whitespace and formatting noise before it enters the context
Project-aware ignore rules respect both .gitignore and .astwireignore patterns when collecting project files
Secret redaction detects and redacts sensitive credentials such as API keys, bearer tokens, AWS keys, and private key blocks before generating context
Configurable workflow controls output formats, skeletonization, waste stripping, token limits, output paths, and skip patterns through .astwire.toml
Native distribution foundation includes a native compilation and distribution pipeline, installers, release automation, and Cloudflare R2 artifact publishing