A personal context store that gives AI coding agents like Codex, Claude Code and OpenCode persistent, searchable project knowledge via a CLI, MCP server and desktop app.
agent-sh/agentsys
A modular orchestration system of plugins, agents and skills that automates task selection, code review, PR shipping and docs sync for AI coding agents.
- スター
- 1,004
- フォーク
- 0
- 未解決の Issue
- 0
- 最終コミット
- 一昨日
主な機能
- 01Orchestrates task discovery, implementation, review, and PR merge as gated pipelines.
- 02Runs parallel multi-agent code reviews with severity-graded findings.
- 03Detects and removes AI slop such as debug statements and placeholder comments.
- 04Monitors CI, fixes failures, and replies to PR review comments.
- 05Lints agent configuration files such as SKILL.md, CLAUDE.md, and hooks via agnix.
- 06Works across Claude Code, OpenCode, Codex CLI, Cursor, and Kiro.
ユースケース
- Automating the path from a GitHub issue to a merged pull request with AI agents.
- Running pre-ship quality gates such as review, test coverage checks, and docs sync before opening a PR.
- Maintaining and linting custom skills, agents, and prompts for AI coding tools.
- Consulting or debating between different AI CLI tools on a design decision.
トピック
よくある質問
- agentsys とは?
- A modular orchestration system of plugins, agents and skills that automates task selection, code review, PR shipping and docs sync for AI coding agents.
- agentsys は無料で使えますか?ライセンスは?
- agentsys は MIT ライセンスのオープンソースです。商用製品で使う前にライセンス条件を確認してください。
- agentsys は今もメンテナンスされていますか?
- 活発にメンテナンス中。agentsys の最終コミットは 2026年10月18日 です。
- agentsys は何に使えますか?
- Automating the path from a GitHub issue to a merged pull request with AI agents. Running pre-ship quality gates such as review, test coverage checks, and docs sync before opening a PR. Maintaining and linting custom skills, agents, and prompts for AI coding tools. Consulting or debating between different AI CLI tools on a design decision.
- agentsys はどこで入手できますか?
- ソースコードとインストール手順は GitHub にあります:https://github.com/agent-sh/agentsys
概要はプロジェクトの README をもとに AI が生成しています。GitHub の数値は毎日更新されます。
関連プロジェクト
Open-source self-improving AI agent for terminal and desktop that takes an outcome, works out the steps, and writes code as needed.
A macOS CLI and AI agent skill that draws arrows, boxes and signs on screen to point humans at UI elements, without clicking or taking focus.
A skills framework and software development methodology that guides coding agents through brainstorming, planning, TDD, and reviewed subagent-driven implementation.
A collection of agent skills for coding assistants like Claude Code and Codex, covering grilling sessions, TDD, bug diagnosis, planning and code review.
A macOS notch companion (with Windows, Linux and iPhone/Android companions) that monitors AI coding agent sessions and lets you approve permissions from the notch.