Code
How headroomlabs-ai/headroom is laid out, and where to start for common changes.
There is no import map for this report yet.
Where to start reading
- Repository root
- Repository root
- Likely public API
- Likely public API
- Likely start-up file
- Likely start-up file
- Suggested starting pointAI
- Suggested starting pointAI
Find files for a task
AIAdd a New Compression Handler
- Create handler class inheriting from headroom/compression/handlers/base.py
- Implement compress() and detect_type() methods for your content type
- Register handler in detector logic at headroom/compression/detector.py
- Add metrics and observability in headroom/observability/metrics.py
Add a New LLM Backend
- Create backend class inheriting from headroom/backends/base.py
- Implement call() and stream() methods for your provider
- Register model configurations in headroom/models/registry.py
- Add provider-specific tokenizer mapping in headroom/tokenizers/huggingface.py
Add a New Cache Backend
- Create cache backend inheriting from headroom/cache/backends/base.py
- Implement get(), set(), and invalidate() methods
- Register cache type in storage adapter at headroom/memory/adapters/cache.py
- Add cache TTL strategy in headroom/pricing/cache_ttl.py if cost-aware
Change the public API
Trace runtime behavior
Add or update tests
Change build or automation
RepoPilot lists up to 500 files, so a file missing here may still exist.
- Files marked “likely” are guessed from their names.