openseek
moonbitlang/openseek
OpenSeek is a MoonBit-based foundation for a DeepSeek-backed coding agent, providing agent orchestration, durable session storage, and a built-in terminal UI.
49 10Apache-2.0Updated 2026-08-13
75
GreatOverview
OpenSeek is a modular coding agent framework written in MoonBit that integrates with the DeepSeek API. It provides a complete monorepo structure containing pure data models, HTTP transport, agent runtimes, durable session logging, a tool registry, MCP integration, a terminal user interface (TUI), and evaluation harnesses. It supports native execution loops, local file editing tools, background shell execution, and specialized MoonBit compilation commands.
Capabilities
- ▸DeepSeek chat completion integration and payload encoding
- ▸Durable append-only session logging and state resurrection
- ▸Extensible local tool registry supporting file manipulation, shell commands, and planning
- ▸Model Context Protocol (MCP) client support with stdio and Streamable HTTP transports
- ▸Interactive terminal user interface and visualization apps
- ▸MoonBit workspace compilation and test integration
Best for
Building and running autonomous AI coding agents backed by DeepSeek models, Developing terminal-based AI assistant interfaces (TUI), Executing local development tasks, file modifications, and shell commands via safe agent tool dispatch, Conducting code reviews and automated prompt-task evaluations
Works with
CodexClaude Code
Evoa Score breakdown= Σ (score × weight)
75Task 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%33 → +4.0
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%46 → +3.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
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 total74.6 / 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
The agent includes a shell tool capable of executing arbitrary system commands. Proper sandboxing or user oversight should be used when running autonomous agent loops in sensitive environments.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.