chopratejas 9c9bb30ded Add persistent memory system with zero-latency inline extraction ... Features: - with_fast_memory(): Zero-latency inline extraction (Letta-style) - Memory extracted as part of LLM response, no extra API calls - Semantic retrieval with local embeddings (sub-50ms) - with_memory(): Background extraction for non-blocking memory - SQLite + FTS5 storage with vector similarity search - Multi-user isolation by user_id Memory enables temporal compression - extract key facts instead of carrying full conversation history (4000 tokens → 50 tokens). Includes: - Comprehensive test suite (71 new tests) - Documentation (docs/memory.md) - Benchmark examples comparing approaches - E2E test with LLM-as-judge evaluation		2026-01-14 21:32:09 -08:00
..
__init__.py	Initial commit: Headroom SDK - LLM context optimization toolkit	2026-01-06 23:16:58 -08:00
test_cache_aligner.py	Fix all ruff lint and format errors for CI	2026-01-10 15:33:44 -08:00
test_code_compressor.py	Add AST-based code compression and custom model configuration	2026-01-14 13:46:55 -08:00
test_content_router.py	Add AST-based code compression and custom model configuration	2026-01-14 13:46:55 -08:00
test_llmlingua_compressor.py	Add LLMLingua-2 opt-in support to proxy server	2026-01-14 12:21:51 -08:00
test_rolling_window.py	Add persistent memory system with zero-latency inline extraction	2026-01-14 21:32:09 -08:00
test_smart_crusher.py	Fix all ruff lint and format errors for CI	2026-01-10 15:33:44 -08:00
test_tool_crusher.py	Fix all ruff lint and format errors for CI	2026-01-10 15:33:44 -08:00