Add Kompress: ModernBERT token compressor replacing LLMLingua-2

fix(ci): add sqlite-vec to dev deps to fix memory tests on CI

Merge pull request #33 from angpt/angpt/any-llm-integration

Bump version to 0.3.7

Bump version to 0.3.6

Add compression summaries, multi-provider headers, Dockerfile fix

Fixing the DockerFile to have hnswlib working

Fix streaming crashes under concurrent sessions

Bump version to 0.3.2

Adding any-llm as a backed provider

Add MCP CLI for Claude Code subscription users

Bump version to 0.3.1

Fix: Include dashboard HTML templates in wheel package

Add SQLiteVectorIndex using sqlite-vec for bounded vector search

Add HTMLExtractor for web content extraction with OSS benchmarks

feat: Add AWS Strands Agents SDK integration

Add Click-based CLI with memory management commands

feat(proxy): add connection pooling, HTTP/2, and multi-worker support

feat: add streaming memory tool support with credential error handling

Add missing pillow dependency for image compression

Add image token compression with trained ML router

Add hnswlib to dev dependencies for CI testing

Replace legacy memory system with HierarchicalMemory

Add comprehensive evaluation framework for compression accuracy

Add pre-commit hooks for ruff linting and formatting

Bump version to 0.2.15

Bump version to 0.2.14

Bump version to 0.2.13

Fix HeadroomAgnoModel to extend agno.models.base.Model and add real integration tests

Enhance /stats endpoint and add comprehensive benchmarks

Add TOIN field-level learning and comprehensive integration tests

Bump version to 0.2.10

Bump version to 0.2.9

Add Agno agent framework integration

Use LiteLLM for model pricing instead of hardcoded values

Bump version to 0.2.8

Bump version to 0.2.7

Bump version to 0.2.6

Bump version to 0.2.5

Bump version to 0.2.4

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

Fix all mypy type errors and flaky embedding test

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