Fix HeadroomAgnoModel to optimize tool outputs at invoke level

Rewrite README with verified before/after examples

Add Agno integration documentation

Add universal compression module with ML-based content detection

Add persistent memory system with zero-latency inline extraction

Add seamless LangChain integration

Add AST-based code compression and custom model configuration

v0.2.2: Add CCR Response Handler, Context Tracker, and restructure docs

Add LLMLingua-2 opt-in support to proxy server

Add opt-in text compression utilities for coding tasks

Fix GitHub URLs and PyPI badge links (v0.2.1)

Publish headroom-ai v0.2.0 to PyPI with DevEx fixes

Prepare for OSS release v0.2.0

Initial commit: Headroom SDK - LLM context optimization toolkit