memo-code

Name: memo-code
Rating: 77 (1 reviews)
Author: minorcell

MCP Server

minorcell/memo-code

Memo Code is a lightweight terminal-based coding agent and TUI workflow assistant that integrates Model Context Protocol (MCP) servers, auto-compaction context management, and customizable skills.

29 4MITUpdated 2026-08-02

Great

View on GitHub Open source file

Overview

Memo Code provides an efficient terminal user interface (TUI) coupled with an agentic core engine. It supports OpenAI-compatible endpoints, smart context compression, enterprise-grade tool execution approvals, and modular skill integration. The system emphasizes minimal, surgical code modifications, clear step-by-step verification loops, and robust multi-workspace task execution.

Capabilities

▸Terminal TUI interface
▸Smart context management with token estimation and auto-compaction
▸Deep Model Context Protocol (MCP) integration
▸Enterprise-grade tool approval permissions
▸Filesystem read, write, search, and patch application
▸Agent collaboration and sub-agent spawning
▸Dynamic skills system loading SKILL.md configurations

Best for

Executing terminal-based coding assistant tasks with interactive or one-shot command modes, Managing and querying local or remote Model Context Protocol (MCP) servers, Performing structured file patching, workspace searching, and executing shell commands safely, Automating documentation updates, GitHub issue tracking, and debugging workflows

Works with

Claude CodeCodexChatGPTCursor

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%40 → +4.8

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%39 → +3.1

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%100 → +5.0

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total77.4 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

Includes granular tool approval systems with auto-approve and manual-approve policies (once, session, deny modes) to protect against unauthorized command execution or filesystem edits.