Files

T

Milla Jovovich 068dbd9a7b MemPalace: palace architecture, AAAK compression, knowledge graph

The memory system:
- Palace structure: Wings (people/projects) → Rooms (topics) → Closets (AAAK compressed) → Drawers (verbatim transcripts)
- Halls connect related rooms within a wing
- Tunnels cross-reference rooms across wings
- AAAK: 30x lossless compression dialect for AI agents
- Knowledge graph: temporal entity-relationship triples (SQLite)
- Palace graph: room-based navigation with tunnel detection
- MCP server: 19 tools — search, graph traversal, agent diary, AAAK auto-teach
- Onboarding: guided setup generates wing config + AAAK entity registry
- Contradiction detection: catches wrong pronouns, names, ages
- Auto-save hooks for Claude Code

96.6% Recall@5 on LongMemEval — highest zero-API score published.
100% with optional Haiku rerank (500/500).
Local. Free. No API key required.

2026-04-04 18:16:04 -07:00

3.3 KiB

Raw Blame History

Contributing to MemPalace

Thanks for wanting to help. MemPalace is open source and we welcome contributions of all sizes — from typo fixes to new features.

Getting Started

git clone https://github.com/milla-jovovich/mempalace.git
cd mempalace
pip install -e ".[dev]"    # installs with dev dependencies (pytest, build, twine)

Running Tests

pytest tests/ -v

All tests must pass before submitting a PR. Tests should run without API keys or network access.

Running Benchmarks

# Quick test (20 questions, ~30 seconds)
python benchmarks/longmemeval_bench.py /path/to/longmemeval_s_cleaned.json --limit 20

# Full benchmark (500 questions, ~5 minutes)
python benchmarks/longmemeval_bench.py /path/to/longmemeval_s_cleaned.json

See benchmarks/README.md for data download instructions and reproduction guide.

Project Structure

mempalace/          ← core package (see mempalace/README.md for module guide)
benchmarks/         ← reproducible benchmark runners
hooks/              ← Claude Code auto-save hooks
examples/           ← usage examples
tests/              ← test suite
assets/             ← logo + brand

PR Guidelines

Fork the repo and create a feature branch: git checkout -b feat/my-thing
Write your code
Add or update tests if applicable
Run pytest tests/ -v — everything must pass
Commit with a clear message following conventional commits:
- feat: add Notion export format
- fix: handle empty transcript files
- docs: update MCP tool descriptions
- bench: add LoCoMo turn-level metrics
Push to your fork and open a PR against main

Code Style

Formatting: Ruff with 100-char line limit (configured in pyproject.toml)
Naming: snake_case for functions/variables, PascalCase for classes
Docstrings: on all modules and public functions
Type hints: where they improve readability
Dependencies: minimize. ChromaDB + PyYAML only. Don't add new deps without discussion.

Good First Issues

Check the Issues tab. Great starting points:

New chat formats: Add import support for Cursor, Copilot, or other AI tool exports
Room detection: Improve pattern matching in room_detector_local.py
Tests: Increase coverage — especially for knowledge_graph.py and palace_graph.py
Entity detection: Better name disambiguation in entity_detector.py
Docs: Improve examples, add tutorials

Architecture Decisions

If you're planning a significant change, open an issue first to discuss the approach. Key principles:

Verbatim first: Never summarize user content. Store exact words.
Local first: Everything runs on the user's machine. No cloud dependencies.
Zero API by default: Core features must work without any API key.
Palace structure matters: Wings, halls, and rooms aren't cosmetic — they drive a 34% retrieval improvement. Respect the hierarchy.

Community

Discord: Join us
Issues: Bug reports and feature requests welcome
Discussions: For questions and ideas

License

MIT — your contributions will be released under the same license.

3.3 KiB Raw Blame History