Repo Memory

Shared, git-tracked working memory for AI agents on the same codebase.

Connector by yubinkim444 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/yubinkim444-repo-memory

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Shared, git-tracked working memory for AI agents on the same codebase.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 2 read · 3 write · 0 delete
Secrets: None asked for
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 5

Read from the source code; the running server may list different tools.

Read 2 · Look things up without changing anything.

get_repo_memory
list_facts

Write 3 · Create, change, send or run things.

add_decision
add_fact
add_gotcha

Secrets and settings it asks for

Other settings (environment variables or headers).

REPO_MEMORY_ROOT

Files it touches

Any path the agent passes to its tools

Tools (5)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

add_decision
Record a non-trivial decision made while working in this repo (architecture choice, trade-off, deprecation, etc.) as a markdown file under `.ai-memory/decisions/`. Args: title: one-line headline of the decision. body: full markdown explanation — context, options considered, reasoning, who/when.
add_fact
Record a structured fact you just verified about this codebase, so the next agent (or your next session) doesn't have to re-verify it. Args: claim: the factual statement (one sentence). file: source file path (relative to repo root) that proves the claim. lines: line range like '42' or '42-50'. tool: name of tool used to verify ('grep', 'read', 'bash', etc.). command: exact command if reproducible. tags: optional tags for later filtering.
add_gotcha
Append a one-line 'watch out for X' note to `.ai-memory/gotchas.md`. Use for surprises that wasted your time and might trip the next agent.
get_repo_memory
Return the entire `.ai-memory/` of the current repo as a Markdown document ready to drop into your LLM context. Call this **before** starting any task in this repo so you don't redo work other agents already verified. Args: fact_limit: cap on number of facts (default 50, most recent first).
list_facts
List recorded facts, optionally filtered. Useful when you want only facts relevant to a specific area before reading them.

Signals

Stars: 1
Forks: 0
Open issues: 0
Weekly downloads: 87
Last commit: Aug 26, 2026 (2 months ago)
Last release: Aug 26, 2026 (2 months ago)
Last package publish: Aug 26, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.yubinkim444/repo-memory
Version: 0.2.1
Auth: No auth
Packages: pypi repo-memory-mcp
License: MIT
Repository: github.com/yubinkim444/repo-memory
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql