memgit 0.3.1__tar.gz → 0.5.0__tar.gz

{memgit-0.3.1 → memgit-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: memgit
-Version: 0.3.1
+Version: 0.5.0
 Summary: Git for AI memory — version-controlled context persistence across Claude, GPT, Gemini, Cursor, Windsurf, and more
 License: MIT
 Project-URL: Homepage, https://memgit.dev
@@ -44,7 +44,7 @@ Version-controlled, cross-AI context that persists, diffs, rolls back, and syncs
 
 [![PyPI](https://img.shields.io/pypi/v/memgit)](https://pypi.org/project/memgit/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
-[![Tests](https://img.shields.io/badge/tests-54%20passing-brightgreen)](tests/)
+[![Tests](https://img.shields.io/badge/tests-160%20passing-brightgreen)](tests/)
 
 ---
 
@@ -212,13 +212,22 @@ memgit resume --plain    # plain text, for piping into an AI context
 memgit resume --json     # for tooling
 ```
 
-Wire it into Claude Code so every new session **starts** with this digest in context — no tool call, no judgment required:
+Wire it into Claude Code so memory becomes **automatic** — no tool call, no judgment required:
 
 ```bash
-memgit setup hooks       # installs a SessionStart hook (~/.claude/settings.json)
+memgit setup hooks       # installs all four hooks (~/.claude/settings.json)
 ```
 
-The digest is deliberately bounded (~350 tokens measured on a 500-memory store): rules are clipped, the critical list is capped, and full text is one `get_memory` call away.
+| Hook | What it enforces |
+|---|---|
+| `SessionStart` | every session opens with the resume digest in context |
+| `UserPromptSubmit` | each prompt is BM25-matched against the store; relevant memories are injected (silent when nothing clears the relevance bar; never repeats within a session) — `--no-recall` to skip |
+| `Stop` (guard) | a session that did real work but saved nothing gets ONE nudge to save durable facts before finishing — `--no-guard` to skip |
+| `Stop` (sync) | markdown memories are checkpointed asynchronously at session end |
+
+Why hooks and not just good tool descriptions? We measured it: across 166 real sessions, hook-injected context was delivered in **100%** of them while voluntary memory-tool calls happened in **6%**. What a hook enforces happens.
+
+The resume digest is deliberately bounded (~350 tokens measured on a 500-memory store): rules are clipped, the critical list is capped, and full text is one `get_memory` call away.
 
 ---
 
@@ -275,6 +284,16 @@ The tool descriptions teach the AI **judgment** — "does this request depend on
 
 ---
 
+## Core operating guide (v0.5.0)
+
+A project's hardest onboarding problem isn't *what* it does — it's *how to work in it*: which skill to invoke, which command to run, which tool to reach for. That lives in a `CLAUDE.md` or a skills folder the AI host may or may not be configured to read. memgit carries it for you.
+
+`memgit core seed` distills a compact operating guide from the project's existing skills + rule files. `memgit core sync` writes it into **every AI host's own rules surface** as a dedicated, memgit-owned file — `.claude/rules/memgit.md`, `.cursor/rules/memgit.mdc`, `.windsurf/rules/memgit.md`, `.clinerules/`, `.roo/rules/`, `.continue/rules/`, `.gemini/`, and a marker-block in Codex's `AGENTS.md`. It's **additive only** — memgit never touches your own config or content — and injected at session start, so any tool knows how to work in the project even when its native setup is missing.
+
+And it **learns**: a sidecar usage ledger tracks which memories actually get recalled, and the most-used ones are auto-promoted as pointers into the guide over time (budget-capped, decaying, and always subordinate to the repo's own rules — it never restates or overrides them). Drifted? `memgit core heal` rebuilds it.
+
+---
+
 ## Commands
 
 ```bash
@@ -292,6 +311,13 @@ memgit search <query>             # BM25 relevance search
 memgit rollback <ref>             # restore state to a checkpoint (HEAD~N or SHA)
 memgit resume                     # where we left off — session-start digest
 memgit merge <thread>             # three-way merge a thread into the current one
+memgit remove <slug>              # (aliases: delete, rm, del) — mistypes get a "did you mean?"
+
+# Core operating guide — per-project, always-on, cross-host
+memgit core seed                  # draft a guide from this project's skills + rule files
+memgit core sync                  # deliver it into each AI host's own rules file (additive)
+memgit core show / edit           # view / curate the guide
+memgit core heal                  # self-repair a guide that has drifted
 
 # Scale & proof
 memgit squash                     # compress old history (archives what it collapses)
@@ -322,7 +348,8 @@ memgit setup windsurf
 memgit setup cline
 memgit setup continue
 memgit setup gemini-cli
-memgit setup hooks                # Claude Code SessionStart hook → auto-inject resume digest
+memgit setup hooks                # Claude Code hooks: resume at start, per-prompt recall,
+                                  # capture guard + auto-sync at stop (--no-recall / --no-guard)
 
 # Server
 memgit serve                      # MCP stdio (Claude Code, Cursor, Windsurf, Cline)
@@ -405,7 +432,7 @@ git clone https://github.com/code4161/memgit.git
 cd memgit
 python -m venv .venv && source .venv/bin/activate
 pip install -e ".[dev]"
-pytest    # 48 tests, all passing, < 1 second
+pytest    # 160 tests, all passing, < 3 seconds
 ```
 
 See [CONTRIBUTING.md](CONTRIBUTING.md).
@@ -425,6 +452,8 @@ See [CONTRIBUTING.md](CONTRIBUTING.md).
 - [x] Flat `memories/` directory — grep/diff/blame your memories
 - [x] D3.js graph visualization of memory relationships
 - [x] `memgit resume` + SessionStart hook — sessions start with "where we left off"
+- [x] Guardrail hooks — per-prompt auto-recall + end-of-session capture guard (v0.4.0)
+- [x] Core operating guide — per-project, always-on, cross-host, self-improving (v0.5.0)
 - [x] `memgit gc` — space reclamation (mark-and-sweep, lossless squash archive)
 - [x] Multi-agent write safety — store lock, auto-merge commits, `memgit merge`
 - [x] PyPI + Homebrew (tap) + npm published (v0.1.5)

{memgit-0.3.1 → memgit-0.5.0}/README.md

@@ -10,7 +10,7 @@ Version-controlled, cross-AI context that persists, diffs, rolls back, and syncs
 
 [![PyPI](https://img.shields.io/pypi/v/memgit)](https://pypi.org/project/memgit/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
-[![Tests](https://img.shields.io/badge/tests-54%20passing-brightgreen)](tests/)
+[![Tests](https://img.shields.io/badge/tests-160%20passing-brightgreen)](tests/)
 
 ---
 
@@ -178,13 +178,22 @@ memgit resume --plain    # plain text, for piping into an AI context
 memgit resume --json     # for tooling
 ```
 
-Wire it into Claude Code so every new session **starts** with this digest in context — no tool call, no judgment required:
+Wire it into Claude Code so memory becomes **automatic** — no tool call, no judgment required:
 
 ```bash
-memgit setup hooks       # installs a SessionStart hook (~/.claude/settings.json)
+memgit setup hooks       # installs all four hooks (~/.claude/settings.json)
 ```
 
-The digest is deliberately bounded (~350 tokens measured on a 500-memory store): rules are clipped, the critical list is capped, and full text is one `get_memory` call away.
+| Hook | What it enforces |
+|---|---|
+| `SessionStart` | every session opens with the resume digest in context |
+| `UserPromptSubmit` | each prompt is BM25-matched against the store; relevant memories are injected (silent when nothing clears the relevance bar; never repeats within a session) — `--no-recall` to skip |
+| `Stop` (guard) | a session that did real work but saved nothing gets ONE nudge to save durable facts before finishing — `--no-guard` to skip |
+| `Stop` (sync) | markdown memories are checkpointed asynchronously at session end |
+
+Why hooks and not just good tool descriptions? We measured it: across 166 real sessions, hook-injected context was delivered in **100%** of them while voluntary memory-tool calls happened in **6%**. What a hook enforces happens.
+
+The resume digest is deliberately bounded (~350 tokens measured on a 500-memory store): rules are clipped, the critical list is capped, and full text is one `get_memory` call away.
 
 ---
 
@@ -241,6 +250,16 @@ The tool descriptions teach the AI **judgment** — "does this request depend on
 
 ---
 
+## Core operating guide (v0.5.0)
+
+A project's hardest onboarding problem isn't *what* it does — it's *how to work in it*: which skill to invoke, which command to run, which tool to reach for. That lives in a `CLAUDE.md` or a skills folder the AI host may or may not be configured to read. memgit carries it for you.
+
+`memgit core seed` distills a compact operating guide from the project's existing skills + rule files. `memgit core sync` writes it into **every AI host's own rules surface** as a dedicated, memgit-owned file — `.claude/rules/memgit.md`, `.cursor/rules/memgit.mdc`, `.windsurf/rules/memgit.md`, `.clinerules/`, `.roo/rules/`, `.continue/rules/`, `.gemini/`, and a marker-block in Codex's `AGENTS.md`. It's **additive only** — memgit never touches your own config or content — and injected at session start, so any tool knows how to work in the project even when its native setup is missing.
+
+And it **learns**: a sidecar usage ledger tracks which memories actually get recalled, and the most-used ones are auto-promoted as pointers into the guide over time (budget-capped, decaying, and always subordinate to the repo's own rules — it never restates or overrides them). Drifted? `memgit core heal` rebuilds it.
+
+---
+
 ## Commands
 
 ```bash
@@ -258,6 +277,13 @@ memgit search <query>             # BM25 relevance search
 memgit rollback <ref>             # restore state to a checkpoint (HEAD~N or SHA)
 memgit resume                     # where we left off — session-start digest
 memgit merge <thread>             # three-way merge a thread into the current one
+memgit remove <slug>              # (aliases: delete, rm, del) — mistypes get a "did you mean?"
+
+# Core operating guide — per-project, always-on, cross-host
+memgit core seed                  # draft a guide from this project's skills + rule files
+memgit core sync                  # deliver it into each AI host's own rules file (additive)
+memgit core show / edit           # view / curate the guide
+memgit core heal                  # self-repair a guide that has drifted
 
 # Scale & proof
 memgit squash                     # compress old history (archives what it collapses)
@@ -288,7 +314,8 @@ memgit setup windsurf
 memgit setup cline
 memgit setup continue
 memgit setup gemini-cli
-memgit setup hooks                # Claude Code SessionStart hook → auto-inject resume digest
+memgit setup hooks                # Claude Code hooks: resume at start, per-prompt recall,
+                                  # capture guard + auto-sync at stop (--no-recall / --no-guard)
 
 # Server
 memgit serve                      # MCP stdio (Claude Code, Cursor, Windsurf, Cline)
@@ -371,7 +398,7 @@ git clone https://github.com/code4161/memgit.git
 cd memgit
 python -m venv .venv && source .venv/bin/activate
 pip install -e ".[dev]"
-pytest    # 48 tests, all passing, < 1 second
+pytest    # 160 tests, all passing, < 3 seconds
 ```
 
 See [CONTRIBUTING.md](CONTRIBUTING.md).
@@ -391,6 +418,8 @@ See [CONTRIBUTING.md](CONTRIBUTING.md).
 - [x] Flat `memories/` directory — grep/diff/blame your memories
 - [x] D3.js graph visualization of memory relationships
 - [x] `memgit resume` + SessionStart hook — sessions start with "where we left off"
+- [x] Guardrail hooks — per-prompt auto-recall + end-of-session capture guard (v0.4.0)
+- [x] Core operating guide — per-project, always-on, cross-host, self-improving (v0.5.0)
 - [x] `memgit gc` — space reclamation (mark-and-sweep, lossless squash archive)
 - [x] Multi-agent write safety — store lock, auto-merge commits, `memgit merge`
 - [x] PyPI + Homebrew (tap) + npm published (v0.1.5)

{memgit-0.3.1 → memgit-0.5.0}/memgit/__init__.py

@@ -1,3 +1,3 @@
 """memgit — git for AI memory."""
 
-__version__ = "0.3.1"
+__version__ = "0.5.0"