Files
Memba/pyproject.toml
T
emilandClaude Opus 4.7 75c9ee4576 Add memba MVP: C++ core, Python SDK, CLI, examples, experiments
C++ core (libmemba.so):
- include/memba/state.h — C API (state_new/free/save/load/get_size)
- src/state.cpp — MEMB file format: magic, version, SHA-256 model_id,
  CRC-32, opaque llama_state_*_data() blob
- src/cli.cpp — minimal demo binary with greedy sampler
- CMakeLists.txt + build.sh with llama.cpp submodule, CUDA auto-detect

Python SDK (memba):
- core.py — file I/O via llama-cpp-python's exposed C functions,
  unwraps _LlamaContext to access raw context pointer (≥0.3.x)
- session.py — high-level Session with auto-save/load, ChatML wrapper
  for instruct models, raw mode for base models
- cli.py — typer-based: chat (REPL), run (one-shot), list, rm, info

Examples:
- 01_basic_save_load.py, 02_chat_session.py

Experiments (throwaway POCs documenting product-direction findings):
- recall_poc.py — git log → state → cross-process query
- mood_poc.py — batch sentiment trajectory, Mamba vs Transformer
- mood_stream_poc.py, mood_batch_poc.py — variants
- diag_saveload.py — minimal save/load isolation test
- README.md documents the headline finding: save/load is byte-identical,
  but Falcon-Mamba-7B-Instruct does not retain facts across conversation
  turns even in-process — limits viable products to single-prompt analysis
  and persona priming.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 12:48:37 +03:00

65 lines
1.9 KiB
TOML

[build-system]
requires = ["setuptools>=68", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "memba"
version = "0.1.0"
description = "Persistent memory layer for SSM-based LLMs (Falcon-Mamba, Zamba)"
readme = "README.md"
license = { text = "MIT" }
requires-python = ">=3.10"
keywords = ["llm", "ssm", "mamba", "falcon-mamba", "memory", "llama-cpp"]
classifiers = [
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
"Intended Audience :: Science/Research",
"License :: OSI Approved :: MIT License",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
]
dependencies = [
"llama-cpp-python>=0.2.0",
"typer>=0.9.0",
"rich>=13.0.0",
"pydantic>=2.0.0",
]
[project.optional-dependencies]
dev = [
"pytest>=7.0",
"pytest-cov",
"ruff",
"mypy",
]
[project.scripts]
memba = "memba.cli:main"
[project.urls]
Homepage = "https://github.com/your-org/memba"
Repository = "https://github.com/your-org/memba"
# ── Package discovery ────────────────────────────────────────────
[tool.setuptools.packages.find]
where = ["python"]
# ── Ruff (linting) ───────────────────────────────────────────────
[tool.ruff]
line-length = 100
target-version = "py310"
[tool.ruff.lint]
select = ["E", "F", "W", "I"]
ignore = ["E501"]
# ── Mypy ────────────────────────────────────────────────────────
[tool.mypy]
python_version = "3.10"
ignore_missing_imports = true