emilandClaude Opus 4.7 564478710e Fix 'noted' contextual inertia in queries
Two changes to memwalk/ingest.py:

1. Ingest prompt now asks the model for a brief theme + standout
   projects summary instead of "Reply noted". The "X → noted"
   pattern was training the model in-context to reply "noted" to
   every follow-up regardless of question.

2. query() wraps the user question in a short framing prefix
   ("Drawing on the work activity I shared with you earlier,
   please answer this clearly and concretely: ...") which is
   enough to break the noted pattern even on pre-existing state
   files, so existing users don't need to rebuild to benefit.

Verified on the maintainer's state: vague greetings still
default to noted (degenerate case, CLI is for questions),
but real questions like "What did I work on this past month?"
and "What features did I ship in Randify.pro?" now produce
detailed accurate responses. Standup output now includes
real blockers extracted from commit messages.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-16 13:55:29 +03:00

memwalk

Walk through your work memory.

A local-first CLI that watches your git activity (and optionally your shell history) and feeds it into a Mamba-based LLM via persistent state. You can then ask in plain English what you were doing last week, why you started that branch, or generate a standup from yesterday's commits — without your data ever leaving the machine.

Built on memba for state persistence and NVIDIA Nemotron-3-Nano-4B (or any other GGUF SSM/hybrid model) for inference.

Status

v0.1 — alpha. Works end-to-end on Linux for the maintainer; APIs and on-disk format may change.

Install

# Until memba is on PyPI, install both editable from local clones:
pip install -e /path/to/Memba
pip install -e /path/to/memwalk

Make sure you have a GGUF Mamba-2 or hybrid model. Recommended:

hf download nvidia/NVIDIA-Nemotron-3-Nano-4B-GGUF \
    NVIDIA-Nemotron3-Nano-4B-Q4_K_M.gguf \
    --local-dir ~/.memwalk/models

Quickstart

memwalk init                                  # interactive setup
memwalk update                                # ingest last 30 days of git+bash
memwalk standup                               # auto-generate daily standup
memwalk ask "What was I working on last week?"
memwalk status

What it actually does

memwalk update walks your configured git repos and (optionally) your bash history, formats new events into a readable activity block, and feeds that into the SSM model. The model's hidden state — a fixed ~85 MB blob — is saved to ~/.memwalk/current.memb via memba.

memwalk ask and memwalk standup load that state and query it. The model recalls themes, projects, and trajectory across processes and reboots.

Layout

~/.memwalk/
├── config.toml
├── current.memb              ← rolling state
├── last_update.txt
└── snapshots/
    └── 2026-05-16.memb       ← daily snapshot before each update

License

MIT.

S
Description
No description provided
Readme
117 KiB
Languages
Python 100%